Digital Image Processing
Chapters (16)
Image acquisition is the first step of digital image processing and is often not properly taken into account. However, quantitative analysis of any images requires a good understanding of the image formation process. Only with a profound knowledge of all the steps involved in image acquisition, is it possible to interpret the contents of an image correctly. The steps necessary for an object in the three-dimensional world to become a digital image in the memory of a computer are as follows: Becoming visible. An object becomes visible by the interaction with light or, more generally, electromagnetic radiation. The four basic types of interaction are reflection, refraction, absorption, and scattering. These effects depend on the optical properties of the material from which the object is made and on its surface structure. The light collected by a camera system is determined by these optical properties as well as by the illumination, i. e., position and nature of the light or, more generally, radiation sources. Projection. An optical system collects the light rays reflected from the objects and projects the three-dimensional world onto a two-dimensional image plane. Digitization. The continuous image on the image plane must be converted into image points on a discrete grid. Furthermore, the intensity at each point must be represented by a suitable finite number of gray values (Quantization).
Fourier transform, i.e., decomposition of an image into periodic structures, proved to be an extremely helpful tool to understanding image formation and digitization. Throughout the whole discussion in the last chapter we used the continuous Fourier transform. Proceeding now to discrete imagery, the question arises whether there is a discrete analogue to the continuous Fourier transform. Such a transformation would allow us to decompose a discrete image directly into its periodic components.
Discrete images are composed of individual image points, which we denoted in section 2.3.1 as pixels. Pixels are the elementary units in digital image processing. The simplest processing is to handle these pixels as individual objects or measuring points. This approach enables us to regard image formation as a measuring process which is corrupted by noise and systematic errors. Thus we learn to handle image data as statistical quantities. As long as we are confined to individual pixels, we can apply the classical concepts of statistics which are used to handle point measurements, e. g., the measurement of meteorological parameters at a weather station such as air temperature, wind speed and direction, relative humidity, and air pressure.
The contents of an image can only be revealed when we analyze the spatial relations of the gray values. If the gray value does not change in a small neighborhood, we are within an area of constant gray values. This could mean that the neighborhood is included in an object. If the gray value changes, we might be at the edge of an object. In this way, we recognize areas of constant gray values and edges.
In this chapter we will apply neighborhood operations to analyze two elementary structures: the mean gray value and changes in the gray values. The determination of a correct mean value also includes the suppression of distortions in the gray values caused by sensor noise or transmission errors. Changes in the gray value mean, in the simplest case, the edges of objects. Thus edge detection and smoothing are complementary operations. While smoothing gives adequate averages for the gray values within the objects, edge detection aims at estimating the boundaries of objects.
In the last chapter we became acquainted with neighborhood operations. In fact, we only studied very simple structures in a local neighborhood, namely the edges. We concentrated on the detection of edges, but we did not consider how to determine their orientation. Orientation is a significant property not only of edges but also of any pattern that shows a preferred direction. The local orientation of a pattern is the property which leads the way to a description of more complex image features. Local orientation is also a key feature in motion analysis (chapter 17). Furthermore, there is a close relationship between orientation and projection (section 13.4.2).
The effect of all the operators discussed so far — except for recursive filters — is restricted to local neighborhoods which are significantly smaller than the size of the image. This inevitably means that they can only extract local features. We have already seen a tendency that analysis of a more complex feature such as local orientation (chapter 7) requires larger neighborhoods than computing, for example, a simple property such as the Laplacian (section 6.2). It is quite obvious that a larger neighborhood can show a larger set of features which requires more complex operations to reveal them. If we extrapolate our approach by analyzing larger scales in the image with larger filter kernels, we inevitably run into a dead end. The computation of the more complex operators will become so tedious that they are not longer useful.
Local orientation (chapter 7) was the first example of a more complex feature describing the structure of the gray values in a local neighborhood. It enabled us to distinguish objects not only because of their gray values but also because of the orientation of the patterns (compare figure 7.1). Real-world objects often carry patterns which differ not only in their orientation, but also in many other parameters. Our visual system is capable of recognizing and distinguishing such patterns with ease, but it is difficult to describe the differences precisely (figure 9.1). Patterns which characterize objects are called textures in image processing. Actually, textures demonstrate the difference between an artificial world of objects whose surfaces are only characterized by the color and reflectivity properties to that of real-world imagery. We can see a similar trend in computer graphics. If we place a texture on the surface of objects, a process called texture mapping, we obtain much more realistic images (see also plate 3).
All image processing operations discussed so far have helped us to “recognize” objects of interest, i. e., to find suitable local features which allow us to distinguish them from other objects and from the background. The next step is to check each individual pixel whether it belongs to an object of interest or not. This operation is called segmentation and produces a binary image. A pixel has the value one if it belongs to the object; otherwise it is zero. Segmentation is the operation at the threshold between low-level image processing and the operations which analyze the shape of objects, such as those discussed in chapter 11. In this chapter, we discuss several types of segmentation methods. Basically we can think of three concepts for segmentation. Pixel-based methods only use the gray values of the individual pixels. Edge-based methods detect edges and then try to follow the edges. Finally, region-based methods analyze the gray values in larger areas.
After the segmentation process, which we discussed in the previous chapter, we know which pixels belong to the object of interest. Now we can perform the next step and analyze the shape of the objects. This is the topic of this chapter. First we will discuss a class of neighborhood operations, the morphological operators on binary images, which work on the form of objects. Second, we will consider the question how to represent a segmented object. Third, we will discuss parameters to describe the form of objects.
When objects are detected with suitable operators and their shape is described (see chapter 11), image processing has reached its goal for some applications. For other applications, further tasks remain to be solved. In this introduction we explore several examples which illustrate how the image processing tasks depend on the questions we pose.
In chapter 2 we discussed in detail how a discrete two-dimensional image is formed from a three-dimensional scene by an optical system. In this chapter we discuss the inverse process, the reconstruction of a three-dimensional scene from two-dimensional projections. Reconstruction from only one projection is an underdetermined inverse problem which generally shows an infinite number of solutions. As an illustration, figure 13.1 shows the perspective projection of a bar onto an image plane. We will obtain identical projections at the image plane, whenever the endpoints of a bar lie on the same projection beams. Even if the bar shows a curvature in the projection plane, we will still see a straight line at the image plane.
In this chapter we extend our considerations from single images to image sequences. We may compare this step with the transition from still photography to motion pictures. Only in image sequences can we recognize and analyze dynamic processes. Thus the analysis of image sequences opens up far-reaching possibilities in science and engineering. A few examples serve as illustration: Flow visualization is an old tool in fluid dynamics but has been used for a long time mainly for qualitative description, because manual quantitative evaluation has been prohibitively laborious. Digital image sequence analysis allows area-extended velocity data to be extracted automatically. In section 2.2.8 we discussed an example of flow visualization by particle tracking. Some results are shown in plate 4. Satellite image sequences of the sea surface temperature (see section 1.2.1 and plate 1) can be used to determine near-surface ocean currents [Wahl and Simpson, 1990]. In the industrial environment, motion sensors based on image sequence analysis are beginning to play an important role. Their usage covers a wide spectrum starting with remote velocity measurements in industrial processes [Massen et al., 1987] to the control of autonomous vehicles and robots [Dickmanns, 1987].
In the last chapter we worked out the basic knowledge which is necessary for a successful motion analysis. Depending on the motion model used, we either need to determine the displacement vectors (DV) at single points, or the displacement vector field (DVF) in order to compute the first-order spatial derivatives (rotation and deformation terms).
So far we have discussed the problem how displacement vectors (DV) can be determined at single points in the image. Now we turn to the question how a continuous displacement vector field (DVF) can be estimated. The idea is to collect the sparse velocity information obtained with the local operations discussed in the last chapter and to compose it into a consistent picture of the motion in the scene observed.
So far, we have analyzed motion from only two consecutive images of a sequence, but did not consider the whole sequence. This stemmed from a limited capacity to handle image sequence data. Nowadays, video and computer hardware can record, store, and evaluate long image sequences (see section 1.2.2 and appendix B). It is much more important, however, to recognize that there is no principal reason to limit image sequence processing to an image pair. On the contrary, it seems to be an unjustified restriction. That is certainly true for the concepts developed so far. In the differential approach (section 15.2) temporal derivatives play an essential role (see (15.5), (15.12), and (15.27)). With only two consecutive images of a sequence, we can approximate the temporal derivative just by the difference between the two images. This may be the simplest approximation, but not necessarily the best (see section 6.3.5)
... Let us estimate the defocusing parameters of an image (see Figure 1b,c) using the "spectral method" [8,9,30]. ...
... This is due to the fact that in the case when the kernel is a homogeneous circle, we have clear landmarks-the zeros of the Bessel function (26) and the corresponding ellipses of the function F(ω 1 ,ω 2 ) (Figure 1b). Meanwhile, in the case when the kernel is Gaussian (28), there are no such clear guidelines since F(ω), according to (30), is a smooth monotonically decreasing function ω. ...
... According to the type of spectra in Figure 1b,c, we conclude that Figure 3b,c show defocused images. Let us estimate the parameters of the defocused image by the "spectral method" [8,9,30]. Variant 1. ...
A set of one-dimensional (as well as one two-dimensional) Fredholm integral equations (IEs) of the first kind of convolution type is solved. The task for solving these equations is ill-posed (first of all, unstable); therefore, the Wiener parametric filtering method (WPFM) and the Tikhonov regularization method (TRM) are used to solve them. The variant is considered when a kernel of the integral equation (IE) is unknown or known inaccurately, which generates a significant error in the solution of IE. The so-called “spectral method” is being developed to determine the kernel of an integral equation based on the Fourier spectrum, which leads to a decrease of the error in solving the IE and image improvement. Moreover, the authors also propose a method for diffusing the solution edges to suppress the possible Gibbs effect (ringing-type distortions). As applications, the problems for processing distorted (smeared, defocused, noisy, and with the Gibbs effect) images are considered. Numerical examples are given to illustrate the use of the “spectral method” to enhance the accuracy and stability of processing distorted images through their mathematical and computer processing.
... Examples of feature detection tasks that can be realized by a convolution include edge detection, image restoration, image enhancement, or texture filtering [7]. For example, in the case of edge detection, the filter U can be chosen as a smooth approximation of differential operators, e.g., of the Laplacian operator [8]. In our practical examples, we will mainly focus on edge detection in tomography. ...
... For example, this can be achieved by choosing the feature extraction filter U as the Laplacian of an approximation to the Delta distribution (e.g., Laplacian of Gaussian (LoG)). Then, Problem 1 boils down to an approximate recovery of the Laplacian of f , which is used in practical edge-detection algorithms (e.g., LoG-filter [7,8]); 3. ...
... The first step in our framework is a filter design for (8). That is, given a feature extraction kernel U, we first need to calculate the corresponding filter u Θ = R Θ U for the CT data, cf. ...
In this paper, we consider the problem of feature reconstruction from incomplete X-ray CT data. Such incomplete data problems occur when the number of measured X-rays is restricted either due to limit radiation exposure or due to practical constraints, making the detection of certain rays challenging. Since image reconstruction from incomplete data is a severely ill-posed (unstable) problem, the reconstructed images may suffer from characteristic artefacts or missing features, thus significantly complicating subsequent image processing tasks (e.g., edge detection or segmentation). In this paper, we introduce a framework for the robust reconstruction of convolutional image features directly from CT data without the need of computing a reconstructed image first. Within our framework, we use non-linear variational regularization methods that can be adapted to a variety of feature reconstruction tasks and to several limited data situations. The proposed variational regularization method minimizes an energy functional being the sum of a feature dependent data-fitting term and an additional penalty accounting for specific properties of the features. In our numerical experiments, we consider instances of edge reconstructions from angular under-sampled data and show that our approach is able to reliably reconstruct feature maps in this case.
... Digital Image Processing (DIP) is used to assist or automate the solution of several problems, such as remote sensing, automated inspection of manufactured products, analysis of medical images, and security systems (JäHNE, 2005). DIP, unlike human vision, can cover almost the entire electromagnetic spectrum (GONZALEZ; WOODS, 2018). ...
... The computational representation of a digital image can be performed in several ways, the most common being the spatial representation (JäHNE, 2005). The spatial representation is composed of a finite set of M × N elements, where M and N correspond, respectively, to the height and width of the image (GONZALEZ; WOODS, 2018). ...
... A monochrome digital image f (x, y), where x and y are spatial coordinates, and f corresponds to the intensity or level of gray in the image, can be represented as a 2D matrix (JäHNE, 2005;GONZALEZ;WOODS, 2018). For a color digital image, in general, a 3D representation is required (BURGER; BURGE, 2009). ...
CONTEXT: Advances in studies at the molecular and genetic sequencing have brought significant progress in understanding the behavior, treatment, and prognosis of breast cancer. However, the diagnosis of breast cancer in the early stages is still essential for successful treatment. Currently, the gold standard for breast cancer diagnosis, treatment, and management is a histological analysis of a suspected section. Histopathology consists of analyzing the characteristics of the lesions through sections of tissue stained with Hematoxylin and Eosin. However, pathologists are currently subjected to high workloads, mainly due to the fundamental role played by histological analysis in the treatment of the patient. In this context, applications that can reduce the time of histological analysis, provide a second opinion, or even point out suspicious locations as a screening tool can help the pathologist. OBJECTIVE: We envision two main challenges: the first, how to identify cancerous regions in Whole Slide Imaging (WSI) using Deep Learning (DL) with an accuracy comparable to the pathologist's annotations, considered the gold standard in the literature. And second, how a DL-based model can provide an interpretable diagnosis. The scientific contribution consists in proposing a model based on Convolutional Neural Networks (CNN) to provide a refined and multi-class segmentation of WSI in breast cancer. METHODOLOGY: The methodology consists of proposing and developing a model called DeepBatch. The DeepBatch is divided into four modules: Preprocessing, ROI Detection, ROI Sampling, and Cell Segmentation. These modules are organized to decode the information learned using CNNs in interpretable predictions for pathologists. The Preprocessing module is responsible for removing background and noise from WSI. At ROI Detection, we use the U-Net convolutional architecture to identify suspicious regions in low magnification WSI. Suspected areas identified are mapped from low magnifications by ROI Sampling to 40X magnifications. Cell Segmentation then segments high-magnification areas. Segmentation is performed using a ResNet50/U-Net. To validate the DeepBatch, we use datasets from different sources that can be used together or separately in each module, depending on the module's objective. RESULTS: The evaluations performed demonstrate the feasibility of the model. We assessed the impact of four-color spaces (RGB, HSV, YCrCb, and LAB) for multi-class segmentation of breast cancer WSI. We used 205 WSI of breast cancer for training, validation, and testing. For the detection of suspicious regions by ROI Detection we obtained a IoU of 93.43%, accuracy of 91.27%, sensitivity of 90.77%, specificity of 94.03%, F1-Score of 84.17%, and an AUC of 0.93. For the refined segmentation of WSI by the Cell Segmentation module we obtained a IoU of 88.23%, accuracy of 96.10% , sensitivity of 71.83%, specificity of 96.19%, F1 -Score of 82.94%, and an AUC of 0.86 . CONCLUSION: As a contribution, DeepBatch provides refined segmentation of breast cancer WSIs using a cascade of CNNs. This segmentation helps the interpretation of the diagnosis by the pathologist, accurately presenting the regions considered during the inference of WSI. The results indicate the possibility of using the model as a second reading system.
... Moreover, it directly operates on vectorial functions defined in the 3D space, and it adopts a terrain description relying on a Delaunay triangulation. It should be noted that forward-mapping-based schemes typically suffer from the burden of pixel-area fragmentation and relevant integration [24]. In addition, adopting Delaunay triangulation might introduce abrupt changes in terrain slopes, as recognized in [25,26]. ...
... The formulation, which is established in terms of continuous space functions, is then translated into its numerical counterpart that is also described and discussed in this paper. In particular, an inverse cylindrical mapping approach is adopted, thus avoiding the drawback of pixel-area fragmentation and integration [24]. The logical structure of the resulting calibration method reflects the advantages, in terms of conceptual and computational simplicity, of the compact analytical formulation, as discussed in the rest of the paper. ...
... The mathematical formulation presented in Section 2 considers point-to-point mappings (spatial transformations) in the continuous domain. Conversely, as a discrete mapping is concerned, implementing a spatial transformation as point-to-point mapping might however be not appropriate [24], since pixels concern finite elements defined on a (discrete) integer lattice (Figure 4). In particular, here the focus is on the 2D to 2D spatial transformation τ, which is expressed as Remote Sens. 2021, 13, x FOR PEER REVIEW 10 of 24 introduced in general (Section 3.1), and then the adopted discrete scheme is presented (Section 3.2). ...
Modeling of synthetic aperture radar (SAR) imaging distortions induced by topography is addressed and a novel radiometric calibration method is proposed in this paper. An analytical formulation of the problem is primarily provided in purely geometrical terms, by adopting the theoretical notions of the differential geometry of surfaces. The novel and conceptually simple formulation relies on a cylindrical coordinate system, whose longitudinal axis corresponds to the sensor flight direction. A 3D representation of the terrain shape is then incorporated into the SAR imaging model by resorting to a suitable parametrization of the observed ground surface. Within this analytical framework, the area-stretching function quantitatively expresses in geometrical terms the inherent local radiometric distortions. This paper establishes its analytical expression in terms of the magnitude of the gradient of the look-angle function uniquely defined in the image domain, thus resulting in being mathematically concise and amenable to a straightforward implementation. The practical relevance of the formulation is also illustrated from a computational perspective, by elucidating its effective discrete implementation. In particular, an inverse cylindrical mapping approach is adopted, thus avoiding the drawback of pixel area fragmentation and integration required in forward-mapping-based approaches. The effectiveness of the proposed SAR radiometric calibration method is experimentally demonstrated by using COSMO-SkyMed SAR data acquired over a mountainous area in Italy.
... When looking at angular sampling from the perspective of computer vision, one wants to synthesize intermediate images between a pair of input tilts with a certain motion. In general, it is possible to address this with traditional methods based on linear or tricubic interpolation 29 or more advanced DLbased image interpolation techniques 30 . The latter leverage the power of convolutional neural networks (CNNs) 31 , recurrent neural networks (RNNs) 32 , and generative adversarial networks (GANs) 33 to learn representations of image content and spatial relationships. ...
... The partial derivatives are often approximated using convolution filters, such as the Sobel filter 29 , to calculate the gradient in each direction. A higher gradient contrast value indicates a higher degree of contrast in the image, with sharper transitions between pixel intensities. ...
Cryo-electron tomography enables the visualization of macromolecular complexes within native cellular environments, but is limited by incomplete angular sampling and the maximal electron dose that biological specimen can be exposed to. Here, we developed cryoTIGER (Tilt Interpolation Generator for Enhanced Reconstruction), a computational workflow leveraging a deep learning-based frame interpolation to generate intermediate tilt images. By interpolating between tilt series projections, cryoTIGER improves angular sampling, leading to enhanced 3D reconstructions, more refined particle localization, and improved segmentation of cellular structures. We evaluated our interpolation workflow on diverse datasets and compared its performance against non-interpolated data. Our results demonstrate that deep learning-based interpolation improves image quality and structural recovery. The presented cryoTIGER framework offers a computational alternative to denser sampling during tilt series acquisition, paving the way for enhanced cryo-ET workflows and advancing structural biology research.
... which includes three noise sources: (i) shot noise with a variance of σ 2 e unit: e À ð Þ 2 À Á ; (ii) all the noise sources related to the sensor read out and amplifier circuits represented by σ 2 d unit: e À ð Þ 2 À Á ; (iii) the quantization noise with a variance of σ 2 q ¼ 1=12 unit: DN ð Þ 2 À Á . 42 Substituting Eqs. (30) and (31) into Eq. ...
... The ROI is changed from entire frame to a central area 40×50 pixels, which is reasonable as we only concern the precision limit; In Step (iv), in the ROI, A c and B c vary from 122:57DN to 132:63DN and from 117:61DN to 127:26DN , respectively, thus both A c and B c have higher values and A c % B c ; In Step (v), we substitute the saturation capacity measured in Validation of the camera noise model into Eq. (42) to obtain the phase variance; and in Step (vi), we obtain the mean of PVD to be 7.85 × 10 −7 , showing that M P-S matches the experimental result well. It is worth highlighting that, for this model, we can skip Step (iv), and only require the saturation capacity to obtain the phase variance. ...
Three-dimensional (3D) surface geometry provides elemental information in various sciences and precision engineering. Fringe Projection Profilometry (FPP) is one of the most powerful non-contact (thus non-destructive) and non-interferometric (thus less restrictive) 3D measurement techniques, featuring at its high precision. However, the measurement precision of FPP is currently evaluated experimentally, lacking a complete theoretical model for guidance. We propose the first complete FPP precision model chain including four stage models (camera intensity, fringe intensity, phase and 3D geometry) and two transfer models (from fringe intensity to phase and from phase to 3D geometry). The most significant contributions include the adoption of a non-Gaussian camera noise model, which, for the first time, establishes the connection between camera's electronics parameters (known in advance from the camera manufacturer) and the phase precision, and the formulation of the phase to geometry transfer, which makes the precision of the measured geometry representable in an explicit and concise form. As a result, we not only establish the full precision model of the 3D geometry to characterize the performance of an FPP system that has already been set up, but also explore the expression of the highest possible precision limit to guide the error distribution of an FPP system that is yet to build. Our theoretical models make FPP a more designable technique to meet the challenges from various measurement demands concerning different object sizes from macro to micro and requiring different measurement precisions from a few millimeters to a few micrometers.
... The stochastic modeling of images by spatial random fields allows to set up a convenient statistical framework for different issues in image processing for image denoising, pattern detection, segmentation or classification [29,22,12]. ...
... the standard deviation of the ratio under H 0 (t) and σ the standard deviation in (22). Let φ P m (σ) as in Equation (8). ...
... Bhandarkar et al. (2005) have used the orientation of the rings to detect cracks, given that cracks are typically perpendicular to the wood rings in cross-sections. They employ Sobel-like operators (Jähne 2005) to detect the rings, followed by fork detection and clustering methods to locate the cracks, achieving better performance than the previous method. Wang and Huang (2010) compare four detection methods in their study: an integrated algorithm (pre-processing before threshold-based segmentation), a morphological approach (mathematical morphology and curvature evaluation), a percolation-based method (model based on the natural phenomenon of liquid permeation), also used in Yamaguchi and Hashimoto (2009), and a practical technique (semi-manual, requiring operator intervention). ...
Automated detection of lathe checks in wood veneers presents significant challenges due to their variability and the natural properties of wood. This study explores the use of two convolutional neural networks (U-Net architecture) to enhance the precision and efficiency of lathe checks detection in poplar veneers. The approach involves sequential application of two U-Nets: the first for detecting lathe checks through semantic segmentation, and the second for refining these predictions by connecting fragmented lathe checks. Post-processing techniques are applied to denoise the mappings and extract precise lathe check characteristics. The first U-Net demonstrated strong performance in predicting lathe check presence, with precision and recall scores of 0.822 and 0.835, respectively. The second U-Net refined predictions by linking disjointed segments, improving the overall lathe checks mapping process. Comparative analysis with manual methods revealed comparable or superior performance of the automated approach, especially for shallow lathe checks. The results highlight the potential of the proposed method for efficient and reliable lathe check detection in wood veneers.
... It includes the harvest area of three major crops (rice, maize, and wheat) in China from 2000 to 2015 and has a resolution of 1 km. We resampled the crop coverage maps from 2003 to 2015 to a spatial resolution of 500 m using nearest neighbor sampling [43] (Figure 1). The green parts show the maize distribution in 2015. ...
Maize is the world’s largest food crop and plays a critical role in global food security. Accurate phenology information is essential for improving yield estimation and enabling timely field management. Yet, much of the research has concentrated on general crop growth periods rather than on pinpointing key phenological stages. This gap in understanding presents a challenge in determining how different vegetation indices (VIs) might accurately extract phenological information across these stages. To address this, we employed the shape model fitting (SMF) method to assess whether a multi-index approach could enhance the precision of identifying key phenological stages. By analyzing time-series data from various VIs, we identified five phenological stages (emergence, seven-leaf, jointing, flowering, and maturity stages) in maize cultivated in Jilin Province. The findings revealed that each VI had distinct advantages depending on the phenological stage, with the land surface water index (LSWI) being particularly effective for jointing and flowering stages due to its correlation with vegetation water content, achieving a root mean square error (RMSE) of three to four days. In contrast, the normalized difference vegetation index (NDVI) was more effective for identifying the emergence and seven-leaf stages, with an RMSE of four days. Overall, combining multiple VIs significantly improved the accuracy of phenological stage identification. This approach offers a novel perspective for utilizing diverse VIs in crop phenology, thereby enhancing the precision of agricultural monitoring and management practices.
... We intentionally disregard the orientation (phase) of the gradient and use the magnitude for its effectiveness in revealing intricate textures and fine details in local regions. To reduce computational burden, we use the sum of the absolute values of the two gradient components instead of square or square-root operations in calculating gradient magnitude [34]. ...
Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often overlook the complexity of object surfaces. These neural network models, which exclusively rely on photometric images for training, often produce blurred results in high-frequency regions characterized by local discontinuities, such as wrinkles and edges with significant gradient changes. To address this, we propose the Image Gradient-Aided Photometric Stereo Network (IGA-PSN), a dual-branch framework extracting features from both photometric images and their gradients. Furthermore, we incorporate an hourglass regression network along with supervision to regularize normal regression. Experiments on DiLiGenT benchmarks show that IGA-PSN outperforms previous methods in surface normal estimation, achieving a mean angular error of 6.46 while preserving textures and geometric shapes in complex regions.
... The approximation of the local orientation using the partial derivatives [38] such as ünite diûerences can be made more efficient. This approximation is based on the structure tensor (ST) which becomes a powerful tool for studying low-level features. ...
The structure tensor (ST), also named a second-moment matrix, is a popular tool in image processing. Usually, its purpose is to evaluate orientation and to conduct local structural analysis. We present an efficient algorithm for computing eigenvalues and linking eigenvectors of the ST derived from a material structure. The performance and efficiency of our approach are demonstrated through several numerical simulations. The proposed approach is evaluated qualitatively and quantitatively using different two-dimensional/three-dimensional wood image types. This article reviews the properties of the first- and second-order STs, their properties, and their application to illustrate their usefulness in analyzing the wood data. Our results demonstrate that the suggested approach achieves a high-quality orientation trajectory from high-resolution micro-computed tomography ( {\rm{\mu }} CT)-imaging. These orientations lead to establishing a description of fiber orientation states in thermo-mechanical models for fiber-reinforced composite materials. We conclude with an overview of open research and problem directions.
... Blooming can be approximated as a blurring effect followed by an enhancement of the blurred image, which results in a reduction of contrast [59]. The spatial response of an imaging system is characterized by its point-spread function (PSF) [60], where the blurring effect, caused by imperfect focus, follows a two-dimensional Gaussian distribution [61]. The blurred pixels can be modeled as the convolution of the received pixels with the PSF, as follows [42]:Ỹ ...
Display field communication (DFC) is an emerging technology that enables seamless communication between electronic displays and cameras. It utilizes the frequency-domain characteristics of image frames to embed and transmit data, which are then decoded and interpreted by a camera. DFC offers a novel solution for screen-to-camera data communication, leveraging existing displays and camera infrastructures. This makes it a cost-effective and easily deployable solution. DFC can be applied in various fields, including secure data transfer, mobile payments, and interactive advertising, where data can be exchanged by simply pointing a camera at a screen. This article provides a comprehensive survey of DFC, highlighting significant milestones achieved in recent years and discussing future challenges in establishing a fully functional DFC system. We begin by introducing the broader topic of screen–camera communication (SCC), classifying it into visible and hidden SCC. DFC, a type of spectral-domain hidden SCC, is then explored in detail. Various DFC variants are introduced, with a focus on the physical layer. Finally, we present promising experimental results from our lab and outline further research directions and challenges.
... In this study, we use four evaluation metrics-average time required for stylizing a single image, Structural Similarity (SSIM) [49], Peak Signal-to-Noise Ratio (PSNR) [50], and Learned Perceptual Image Patch Similarity (LPIPS) [51]-to quantitatively compare our method with the aforementioned style transfer methods. ...
With the rapid development of artificial intelligence technology, style transfer has become an important topic in current research. However, existing models are deficient in fusing content and style features, resulting in a large gap between the generated image and the target image. To solve this problem, we propose a feature-consistent landscape image style transfer model based on two-channel attention. Unlike traditional models that rely on VGG as a content encoder, VGG has a more limited detail extraction capability when dealing with high-resolution landscape images, so we introduce a Visual Transformer (VIT) to enhance the extraction of content features. In addition, by incorporating a channel attention mechanism in the latent space, we achieve consistency between content and style features, which in turn completes the alignment and fusion of feature distributions. Finally, contrast constraints are applied to accelerate the style transfer process. Comparison experiments show that our method outperforms other existing methods on the style transfer task.
... In the literature, the operation is called matching and ends with the detection of the object in the image [1][2]. In machining processes, the digital image is a matrix in which individual pixel processing does not provide information for interpreting the image but only for improving its visual appearance [3]. The pixel matrix can be processed to obtain relevant features represented by numerical values or descriptors that encode information found in different regions of the image [4]. ...
The present paper aims to conduct an experiment that compares different methods of detecting objects in images. Programs were developed to evaluate the efficiency of SURF, BRISK, MSER, and ORB object detection methods. Four static gray images with sufficiently different histograms were used. The experiment also highlighted the need for image preprocessing to improve feature extraction and detection. Thus, a programmed method for adjusting pixel groups was developed. This method proved useful when one of the listed algorithms failed to detect the object in the original image, but succeeded after adjustment. The effectiveness of detection methods and the evaluation of their performance depend on the application, image preparation, algorithms used, and their implementation. Results of the detection methods were presented numerically (similarities, gradients, distances, etc.) and graphically.
... There are several ways to measure the distance between pixels. Here, we used the Euclidean distance metric [29,30], which is the straight line distance between two pixels. It is a more realistic metric because it preserves isotropy and is defined in Equation (5). ...
Precise measurement of fiber diameter in animal and synthetic textiles is crucial for quality assessment and pricing; however, traditional methods often struggle with accuracy, particularly when fibers are densely packed or overlapping. Current computer vision techniques, while useful, have limitations in addressing these challenges. This paper introduces a novel deep-learning-based method to automatically generate distance maps of fiber micrographs, enabling more accurate fiber segmentation and diameter calculation. Our approach utilizes a modified U-Net architecture, trained on both real and simulated micrographs, to regress distance maps. This allows for the effective separation of individual fibers, even in complex scenarios. The model achieves a mean absolute error (MAE) of 0.1094 and a mean square error (MSE) of 0.0711, demonstrating its effectiveness in accurately measuring fiber diameters. This research highlights the potential of deep learning to revolutionize fiber analysis in the textile industry, offering a more precise and automated solution for quality control and pricing.
... The existing literature on HDR infrared image enhancement methods can be broadly classified into three categories: mapping-based methods, decomposition-based methods, and gradient domain methods [1]. Mapping-based enhancement methods usually exhibit limited detail enhancement capabilities and are susceptible to amplifying local noise [2][3][4][5]. On the other hand, due to the straightforward principles, low computational complexity, and ease of hardware implementation, methods such as contrast limited adaptive histogram equalization (CLAHE) and plateau histogram equalization (PHE) remain prevalent in the latest generation of various infrared imaging systems. ...
Infrared image enhancement technology plays a crucial role in improving image quality, addressing issues like low contrast, lack of sharpness, and poor visual effects within the original images. However, existing decomposition-based algorithms struggle with balancing detail enhancement, noise suppression, and utilizing global and local information effectively. This paper proposes an innovative method for enhancing details in infrared images using adaptive guided filtering and global–local mapping. Initially, the original image is decomposed into its base layer and detail layer through the adaptive guided filter and difference of the Gaussian filter. Subsequently, the detail layer undergoes enhancement using a detail gain factor. Finally, the base layer and enhanced detail layer are merged and remapped to a lower gray level. Experimental results demonstrate significant improvements in global and local contrast, as well as sharpness, with an average gradient enhancement of nearly 3% across various scenes.
... The application of Rayleigh Distribution ranges from clinical research and studies to real-life testing of experiments and life-data analysis. Its cumulative distribution function (cdf) and probability density function (pdf) are versatile in fields such as Wind Speed Modeling [28], Quality Control [20], Fluid Dynamic Simulation [19], Image Analysis [24], Measurement Of Wave Heights [26], etc, The Rayleigh Distribution has its pdf as: ...
In this paper, we introduce a novel probability distribution called the Lambert-Rayleigh (LR) distribution to address limitations observed in existing distributions, particularly the Rayleigh Distribution. Standard distributions often struggle to accurately model data that exhibits skewness and heavy tails. The LRD offers a flexible three-parameter framework that enhances its ability to model asym-metric and heavy-tailed data. This contrasts with the Rayleigh Distribution, which is constrained by a fixed shape parameter and a single-mode structure, limiting its applicability in diverse datasets. We applied the Lambert-Rayleigh Distribution (LRD) in two distinct case studies to demonstrate its efficacy. First, we analyzed a dataset from Shasta Reservoir, focusing on yearly water capacity within a specific range. Second, we examined Kevlar 373/epoxy materials in the context of fatigue fracture life. In both cases, the LRD exhibited superior modeling performance compared to other distributions commonly used in these domains. The Lambert-Rayleigh Distribution thus represents a significant advancement in probability modeling, offering enhanced flexibility and accuracy in capturing the complex statistical characteristics often found in real-world data.
... Texture features encompass contrast, energy, correlation, entropy, and angular second-moment graylevel texture features calculated via the Gray-Level Co-occurrence Matrix (GLCM) [32], as well as texture features depicting grayscale variation in the frequency domain, derived using the Local Binary Pattern (LBP) technique [33]. Edge features include those derived from Prewitt and Laplace operators [34,35]. Building index features utilize the Multi-Band Index (MBI) for feature representation. ...
Earthquake disasters are marked by their unpredictability and potential for extreme destructiveness. Accurate information on building damage, captured in post-earthquake remote sensing images, is critical for an effective post-disaster emergency response. The foundational features within these images are essential for the accurate extraction of building damage data following seismic events. Presently, the availability of publicly accessible datasets tailored specifically to earthquake-damaged buildings is limited, and existing collections of post-earthquake building damage characteristics are insufficient. To address this gap and foster research advancement in this domain, this paper introduces a new, large-scale, publicly available dataset named the Major Earthquake Damage Building Feature Set (MEDBFS). This dataset comprises image data sourced from five significant global earthquakes and captured by various optical remote sensing satellites, featuring diverse scale characteristics and multiple spatial resolutions. It includes over 7000 images of buildings pre- and post-disaster, each subjected to stringent quality control and expert validation. The images are categorized into three primary groups: intact/slightly damaged, severely damaged, and completely collapsed. This paper develops a comprehensive feature set encompassing five dimensions: spectral, texture, edge detection, building index, and temporal sequencing, resulting in 16 distinct classes of feature images. This dataset is poised to significantly enhance the capabilities for data-driven identification and analysis of earthquake-induced building damage, thereby supporting the advancement of scientific and technological efforts for emergency earthquake response.
... S. Hu et al. (2020) addressed the selection of optimal images for texture mapping in this context, highlighting the importance of precision and quality. Edge detectors, like the Canny and Sobel methods, play an essential role in template matching by identifying image boundaries and contours (Jähne, 2005). Advances in deep learning, particularly through CNNs, have significantly enhanced template-matching capabilities. ...
In the field of railway infrastructure maintenance, timely and accurate detection of component anomalies is crucial for safety and efficiency. This paper presents the Cascade Region‐based convolutional neural network with Predefined Proposal Templates (CR‐PPT), an innovative method for railroad components inspection in complex railway infrastructure using edge‐computing devices. Unlike previous systems, CR‐PPT employs a series of predefined templates that enable it to detect both the presence and missing elements within various fastening systems. Our experimental analysis pinpoints the most effective network configurations for CR‐PPT. Furthermore, the paper examines CR‐PPT's proficiency in zero‐shot learning and fine‐tuning, highlighting its adaptability to new fastening systems. We have developed an optimized inference pipeline on NVIDIA Jetson AGX Orin, significantly enhancing its applicability for railway inspection practices. Field blind tests validate the model's high precision and efficiency, greatly reducing the time and labor required for inspections. The findings highlight CR‐PPT's potential as an efficient and robust tool for track health assessment, marking a notable progression in the integration of AI and computer vision in rail track inspection.
... To address this issue, a method is proposed to distinguish different signal components based on the frequency variation relationship among the components. Consequently, a signal component segmentation approach utilizing image processing techniques is employed [41]. The specific algorithmic procedure is outlined as follows: ...
In response to the pressing requirement for prompt and precise heart rate acquisition during neonatal resuscitation, an adaptive motion artifact filter (AMF) is proposed in this study, which is based on the continuous wavelet transform (CWT) approach and takes advantage of the gradual, time-based changes in heart rate. This method is intended to alleviate the pronounced interference induced by random body movement (RBM) on radar detection in neonates. The AMF analyzes the frequency components at different time points in the CWT results. It extracts spectral peaks from each time slice of the frequency spectrum and correlates them with neighboring peaks to identify the existing components in the signal, thereby reducing the impact of RBM and ultimately extracting the heartbeat component. The results demonstrate a reliable estimation of heart rates. In practical clinical settings, we performed measurements on multiple neonatal patients within a hospital environment. The results demonstrate that even with limited data, its accuracy in estimating the resting heart rate of newborns surpasses 97%, and during infant movement, its accuracy exceeds 96%.
... Previous methods usually study hand-designed features for LLIE. Histogram equalization is one of the most classic low-light image enhancement methods [37]. Reza [38] designed a block-based histogram equalization method to model lighting changes in local areas. ...
Low-light image enhancement (LLIE) aims to improve the visual quality of images taken under complex low-light conditions. Recent works focus on carefully designing Retinex-based methods or end-to-end networks based on deep learning for LLIE. However, these works usually utilize pixel-level error functions to optimize models and have difficulty effectively modeling the real visual errors between the enhanced images and the normally exposed images. In this paper, we propose an adaptive dual aggregation network with normalizing flows (ADANF) for LLIE. First, an adaptive dual aggregation encoder is built to fully explore the global properties and local details of the low-light images for extracting illumination-robust features. Next, a reversible normalizing flow decoder is utilized to model real visual errors between enhanced and normally exposed images by mapping images into underlying data distributions. Finally, to further improve the quality of the enhanced images, a gated multi-scale information transmitting module is leveraged to introduce the multi-scale information from the adaptive dual aggregation encoder into the normalizing flow decoder. Extensive experiments on paired and unpaired datasets have verified the effectiveness of the proposed ADANF.
... The wavelet process, as described in [20,21], produces four frequency bands: LL (low pass-low pass), LH (low pass-high pass), HL (high pass-low pass), and HH (high passhigh pass), which are combined together in a matrix. When this process is applied to 2D signals such as images, a single-level discrete wavelet transform (DWT) decomposition involves the use of a scaling function called ϕ(x, y) and three wavelets denoted as ψ(x, y) . ...
Over the past few decades, there have been several successful methods developed for steganography. One popular technique is the insertion method, which is favored for its simplicity and ability to hold a reasonable amount of hidden data. This study introduces an adaptive insertion technique based on the two-dimensional discrete Haar filter (2D DHF). The technique involves transforming the cover image into the wavelet domain using 2D DWT and selecting a predetermined number of coefficients to embed the binary secret message. The selection process is carried out by analyzing the cover image in two non-orthogonal domains: 2D discrete cosine transform and 2D DHF. An adaptive algorithm is employed to minimize the impact on the unrepresented parts of the cover image. The algorithm determines the weights of each coefficient in each domain, and coefficients with low weights are chosen for embedding. To evaluate the effectiveness of the proposed approach, samples from the BOSSbase and custom databases are used. The technique’s performance is measured using three metrics: mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). Additionally, a visual inspection by humans is conducted to assess the resulting image. The results demonstrate that the proposed approach outperforms recently reported methods in terms of MSE, PSNR, SSIM, and visual quality.
... We can pass or reject different regions of frequency of interest. Moreover, the morphological operation was found to provide different image manipulations to provide the necessary image processing techniques [3]. Different algorithms are applied to the image [4][5]. ...
We suggested a cardioid aperture in the processing of cardiac images using the confocal laser scanning microscope (CSLM). We calculated the Point Spread Function (PSF) corresponding to the cardioid aperture and the cardiac images by using the FFT algorithm. Then, we studied the effect of the image rotation on the PSF. In addition, we computed the autocorrelation corresponding to the cardiac images and cardiac aperture and compared them with the autocorrelation of the uniform circular aperture. Also, we computed the cross-correlation of aligned and rotated cardiac images. Finally, we imaged the cardiac images using the confocal scanning microscope provided with the circular and cardioid shapes of apertures. The MATLAB code is used in the formation of all images and plots.
... In the field of digital image processing, the use of 2D window functions is prevalent, particularly in biomedical image processing where window functions play a crucial role in spectral analysis [20,33]. ...
Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings. Yet, previous work showed that even slight mistakes during sampling, leading to aliasing, can be directly attributed to the networks' lack in robustness. To address such issues and facilitate simpler and faster adversarial training, [12] recently proposed FLC pooling, a method for provably alias-free downsampling - in theory. In this work, we conduct a further analysis through the lens of signal processing and find that such current pooling methods, which address aliasing in the frequency domain, are still prone to spectral leakage artifacts. Hence, we propose aliasing and spectral artifact-free pooling, short ASAP. While only introducing a few modifications to FLC pooling, networks using ASAP as downsampling method exhibit higher native robustness against common corruptions, a property that FLC pooling was missing. ASAP also increases native robustness against adversarial attacks on high and low resolution data while maintaining similar clean accuracy or even outperforming the baseline.
... In the following, an appropriate three-step procedure is proposed to get an accurate segmentation of the data. In short, the Sobel edge detection operator 38 in conjunction with a cluster analysis was used to create a mask of the electrode, i.e., to roughly separate the electrode structure from the surrounding background. From this, a morphological closing was used to determine the boundaries of the sample and, finally, a random forest classifier was used to create the final segmentation. ...
Polymer-based batteries offer potentially higher power densities and a smaller ecological footprint compared to state-of-the-art lithium-ion batteries comprising inorganic active materials. However, in order to benefit from this potential advantages, further research to find suitable material compositions is required. In the present paper, we compare two different electrode composites of poly(2,2,6,6-tetramethylpiperidinyloxy-4-ylmethacrylate) (PTMA) and CMK-8, one produced with and one without crosslinking the PTMA. The influence of both approaches on the corresponding electrodes is comparatively investigated using electrochemical measurements and statistical 3D microstructure analysis based on synchrotron X-ray tomography. A particular focus is put on the local heterogeneity in the coating and how the crosslinking influences the interaction between PTMA and CMK-8. It is shown that crosslinked PTMA--compared to its non-crosslinked counterpart--exhibits a more heterogeneous microstructure and, furthermore, leads to better surface coverage of CMK-8, larger pores and shorter transportation pathways through the latter. These changes improve the electrochemical properties of the electrode.
... Despite the promising results obtained in these works, this coding has been 24 used traditionally. Indeed, Freeman's coding originally aims to represent the shapes 25 that do not contain other internal shapes and whose contour is continuous and closed 26 and does not intersect with itself [6,11]. And as described in [12], the traditional 27 Freeman coding gives a code only for the perimeter of the Arabic character. ...
This work goes through several stages: First, the Arabic character is preprocessed and thinned. And a preliminary classification of the character is done according to the number of its loops and the nature, number, and position of its complementary parts (Dots, Hamza, etc.). Then, the Freeman chain code of 8 directions is generated according to a new innovative algorithm that can represent the internal parts of the Arabic character if they exist and without redundant information. After that, a normalization process based on the generalization of the code of 8 directions to a code of 24 directions is done. Finally, and for comparison, the two algorithms, traditional and proposed, are implemented separately to recognize Arabic characters. After 1023 tests on a set of 300 printed characters, isolated and distributed over 10 fonts, the recognition rate obtained was always higher than that obtained with the traditional algorithm, from 90.7 to 100%. Also, the number of font combinations giving good results almost doubled, and the execution time when normalizing the generated code was less.KeywordsArabic character recognitionGeneralized Freeman chain codeCoding of 24 directionsFeature extraction
... Pada Awalnya citra hanya bisa ditangkap menggunakan fotografi. Seiring perkembangan teknologi, saat ini citra dapat ditangkap, disimpan serta dimanipulasi dengan mudah secara elektronik dengan bantuan komputer [Bernd, 1995]. ...
Ilmu pengetahuan dan teknologi terus berkembang sejalan semakin banyaknya peneliti yang berhasil menemukan metode, alat, bahan serta teknologi baru dalam rangka memudahkan serta mensejahterakan kehidupan manusia di dunia. Melalui buku ini, penulis berusaha untuk membagikan wawasan mengenai Pengolahan Citra: Teori Dan Implementasi mulai dari dasar, perkembangan hingga implementasinya pada berbagai bidang seperti keamanan, pendidikan, kesehatan serta pada bidang industri.
... In initial tests of the algorithm, it could be shown that a comparison between the Fourier analysis of the original heightmap and the 3D scanned embossing result can indeed provide a rough indication of the characteristics of an embossing substrate and by which degree details are altered in the embossing process. An intuitive assessment of the attenuation of details by the embossing process is given by a polar display (Jähne, 2005) of the CTF, this is shown in Figure 5. Here, the transfer ratio for each orientation is displayed for each frequency. The recognizable wave structure of the CTF can possibly be explained by the finite resolution of the underlying data or the physical embossing tool. ...
Short abstract The design and manufacture of embossing tools is a strong bottleneck in the development of new embossed paper and cardboard products. In the previous conventional process, a new embossing tool often has to go through several iteration loops until a satisfactory embossing result is achieved with it in trial embossings. This not only causes considerable cost and time expenditure, but also delays the market launch of new products. In order to provide the possibility of a preliminary evaluation and preview of the embossing result, a method was developed to determine the embossing behavior in the desired substrate. For this purpose, a universal test tool is used to emboss the substrate to be embossed. The embossing result is then scanned in three dimensions. The two data sets, original heightmap and fitted 3D scan relief data, are then transformed into the frequency domain utilizing a fast Fourier transformation (FFT). With a comparison it can be determined which frequency ranges deviate by which amount between the original data and the real embossing result. This allows conclusions to be drawn about the embossing capability of details and embossing features, as well as the creation of a preview of future embossing reliefs for this substrate. The results of this approach are presented and their significance for the future design process of new embossing tools is discussed.
... To resize an image, a re-sampling technique should be applied to create a new version of the original image in a different size. There are several algorithms applied for re-sampling such as Nearest Neighbour, Bilinear, Lanczos, etc. [26,27]. In principle, all these algorithms rely on the neighbour pixels of the original image I(x) to interpolate new pixels of the resized image I'(x), where x represents a point sample (that is, a pixel is a point sample). ...
This paper proposes a simple and effective model applied for image-based malware classification using machine learning in which malware images (converted from malware binary files) are directly fed into the classifiers, i.e. k nearest neighbour (k-NN), support vector machine (SVM) and convolution neural networks (CNN). The proposed model does not use the normalized fixed-size square images (e.g. 64 × 64 pixels) or features extracted by image descriptor (e.g. GIST) for training classifiers as existing models do in the literature. Instead, the input images are normalized and horizontally sized down (the width of the image) to a lower dimension of 32 × 64, 16 × 64 or even 8 × 64 than square ones (e.g. 64 × 64 pixels) to reduce the complexity and training time of the model. It is based on the fact that the texture of the malware image is mainly vertically distributed as analysed in this paper. This finding is significant for training those devices which have limited computational resources such as IoT devices. The experiment was conducted on the Malimg, Malheur datasets which contains 9339 (25 malware families) and 3133 variant samples (24 malware families) using k-NN, SVM and CNN classifiers. The achieved results show that it is possible to reduce the dimension of the input images (i.e. 32 × 64, 16 × 64 or even 8 × 64) while still retaining the accuracy of classification as the same as the accuracy obtained by classifier feeding by the fixed-size square image (i.e. 64 × 64 pixels). As a result, training time of the propose model reduces by a half, a quarter, and one-eighth compared to training time taken by the same machine learning-based classifier (i.e. k-NN, SVM and CNN) feeding by fixed-sized square images, i.e. 64 × 64, respectively.
... Edge-based segmentation [18] is a type of segmentation technique that is based on the intensities differences instead of defining the similarities of pixels to discover the closer borders analogous to the image scan object [19]. This technique can be used to get control of the size modification outcome of the segmented tumor caused because of inappropriate thresh-holding process, which has been used for segmentation [20]. This approach is designed to be variation sensitive, and it checks either pixel is on edges [21]. ...
... Edge-based segmentation [18] is a type of segmentation technique that is based on the intensities differences instead of defining the similarities of pixels to discover the closer borders analogous to the image scan object [19]. This technique can be used to get control of the size modification outcome of the segmented tumor caused because of inappropriate thresh-holding process, which has been used for segmentation [20]. This approach is designed to be variation sensitive, and it checks either pixel is on edges [21]. ...
Medical imaging techniques are a vital tool in disease diagnosis. The images are being developed to satisfy the growing need for important information from medical image scans by anticipating constitutional tissues for clinical analysis. The application of deep learning techniques is increasing with the demand for automatic diagnosis of medical imaging. Different layers are used in deep learning models to represent data abstraction and construct computational models. Imaging techniques allow medical experts such as radiologists to correctly recognize a patient’s condition, making medical procedures more accessible and automated. The review’s primary goal is to present a study on recent brain tumor detection segmentation and classification approaches. Brain tumors are reviewed because of their importance compared to other tumors and their high illness rate. Many brain tumor segmentation models have been described to grasp these methodologies well, along with their limits and benefits. The study focuses primarily on contemporary deep learning-based brain tumor detection technologies, such as deep generative and deep learning networks. The more advanced and recent techniques available in the literature are also reviewed to describe the methods for performing image segmentation and to emphasize the importance of segmentation models that are not used in real-time due to little or no interaction between clinicians and developers. Most research does not consider the data augmentation element of brain tumor segmentation, which is critical for improving performance. The most challenging feature, or limitation, is the fluctuation in the morphology of tumors or the intensity degree of tumors, both of which still require study in this arena.
... One of the urgent tasks of space monitoring is to determine the spatial movements of cloud formations in the atmosphere from different-time images obtained from geostationary Earth satellites. According to [1], one of the ways to determine the spatial movements of objects from different-time satellite images is the method based on finding the maxima of the cross-correlation coefficient. In [2], a similar approach is considered as a method of pattern recognition, known as correlation matching. ...
Methods of constructing vector fields of natural objects’ movements based on a series of consecutive satellite images are considered: cloud formations in the atmosphere based on a series of consecutive images obtained from geostationary satellites; water masses and ice fields based on a series of images from low-orbit satellites; using the example of the evolution of bipolar spots, the trajectories of trial corks in the Solar photosphere are constructed based on the data of sounders installed on heliophysical satellite observatories.
The brain is one of the most complex organs in the body, composed of billions of cells that work together to ensure proper functioning. However, when cells divide in a disorderly manner, abnormal growths can occur, forming colonies that can disrupt the normal functioning of the brain and damage healthy cells. Brain tumors can be classified as either benign or low-grade (grade 1 and 2), or malignant or high-grade (grade 3 and 4). In this article, we propose a novel method that uses contourlet transform and time adaptive self-organizing map, optimized by the whale optimization algorithm, in order to distinguish between benign and malignant brain tumors in MRI images. Accurate classification of these images is critical for medical diagnosis and treatment. Our method is compared to other methods used in past research and shows promising results for the precise classification of MRI brain images. Through conducting experiments on different test samples, our system has successfully attained a classification accuracy exceeding 98.5%. Furthermore, it has managed to maintain a satisfactory level of efficiency in terms of run-time.
We present an extensive grid of numerical simulations quantifying the uncertainties in measurements of the tip of the red giant branch (TRGB). These simulations incorporate a luminosity function composed of 2 mag of red giant branch (RGB) stars leading up to the tip, with asymptotic giant branch (AGB) stars contributing exclusively to the luminosity function for at least a magnitude above the RGB tip. We quantify the sensitivity of the TRGB detection and measurement to three important error sources: (1) the sample size of stars near the tip, (2) the photometric measurement uncertainties at the tip, and (3) the degree of self-crowding of the RGB population. The self-crowding creates a population of supra-TRGB stars due to the blending of one or more RGB stars just below the tip. This last population is ultimately difficult, although still possible, to disentangle from true AGB stars. In the analysis given here, the precepts and general methodology as used in the Chicago-Carnegie Hubble Program (CCHP) have been followed. However, in the appendix, we introduce and test a set of new tip detection kernels, which internally incorporate self-consistent smoothing. These are generalizations of the two-step model used by the CCHP (smoothing followed by Sobel-filter tip detection), where the new kernels are based on successive binomial-coefficient approximations to the derivative-of-a-Gaussian edge-detector, as is commonly used in modern digital image processing.
Today, the rapidly growth of cities has made it necessary to following up the performance of infrastructures and architectural works. In developing cities, it is of great importance for human life to follow the deformation of structures over time or materials worn out as a result of disasters. Today, many different methods have been developed for structural deformation evalutaions. In particular, the detection of cracks on material surfaces provides important inferences for performance evaluations. Manual analysis of performance in infrastructure and architectural works does not meet today's needs, both in terms of cost and due to subjective conclusions. Important developments in information technologies ensured that material analysis and audits are carried out objectively and reduced costs to a minimum. Thereby, surface performance analysis by processing images in a computer environment has allowed to obtain higher accuracy results with less cost. In this study, image processing methods were imposed on to analyze surface cracks in materials used in architectural structures and land roads. Surface cracks have been detected by using morphological image processing methods and Hough-line transformation. In order to evaluate the success of these two methods, machine learning methods were used. Comparisons were made using Naive Bayes, Random Forest, Knn and Multi-Layer Perceptron methods, which are machine learning methods for success evaluations. The results gathered as a result of the experiments showed that the Hough-line transform is more successful in extracting features. The highest accuracy was achieved with the Hough-line method, one of the image processing methods, and Random Forest, one of the machine learning methods. It has been successfully classified with an accuracy rate of 97% using Hough-line transformation from image processing methods and Random Forest from machine learning methods to detect cracks on surfaces.
According to the results, the corrosion inhibitor concentration was 1000
mg/l and the inhibition efficiency showed the maximum level at the temperature of 298
K. When the surfaces of the inhibited metal samples were analyzed and analyzed, the
inhibitor protected the metal surface from corrosion by adsorbing both physically and
chemically on the metal surface.
With the incarnation of novel COVID-19, health care is getting more preference in each country. IoT-based health monitoring systems might be the best option to monitor infected patients and be helpful for elderly population. In this paper, analyzed different IoT-based health monitoring systems and their challenges. Searched through established journal and conference databases using specific keywords to find scholarly works to conduct the analysis. Investigated unique articles related to this analysis. The selected papers were then sifted through to understand their contributions/research focus. Then tried to find their research gap and challenges, created them into opportunities and proposed a GSM-based offline health monitoring system that will conduct with the healthcare providers through communication networks. Hopefully, this model will work as an absolute pathway for the researchers to establish a sustainable IoT-based health monitoring system for humankind.
Crevasses - cracks in glaciers and ice sheets-pose a danger to polar researchers and glaciologists. We compare the capabilities of two techniques - geomorphometric modeling and texture analysis - to recognize open and hidden crevasses using high-resolution digital elevation models (DEMs) generated from images collected by an unmanned aerial system (UAS). The first technique includes derivation of local morphometric variables; the second includes calculation of the Haralick texture features. The study area is represented by the first 30 km of a sledge route between the Progress and Vostok polar stations, East Antarctica. The UAS survey was performed by a Geoscan 201 Geodesy UAS. For the sledge route area, DEMs with resolutions of 0.25, 0.5, and 1 m were generated. Models of 12 morphometric variables and 11 texture features were derived from the DEMs. In terms of crevasse recognition, the most informative morphometric variable and texture feature was horizontal curvature and inverse difference moment, respectively. In most cases, derivation and mapping of these variables allow one to recognize crevasses wider than 3 m; narrower crevasses can be recognized for lengths from 500 m. For crevasse recognition , the geomorphometric modeling and the Haralick texture analysis can complement each other.
In nerve regeneration, scaffolds play an important role in providing an artificial extracellular matrix with architectural, mechanical, and biochemical cues to bridge the site of injury. Directed nerve growth is a crucial aspect of nerve repair, often introduced by engineered scaffolds imparting linear tracks. The influence of physical cues, determined by well‐defined architectures, has been mainly studied for implantable scaffolds and is usually limited to continuous guiding features. In this report, the potential of short anisometric microelements in inducing aligned neurite extension, their dimensions, and the role of vertical and horizontal distances between them, is investigated. This provides crucial information to create efficient injectable 3D materials with discontinuous, in situ magnetically oriented microstructures, like the Anisogel. By designing and fabricating periodic, anisometric, discreet guidance cues in a high‐throughput 2D in vitro platform using two‐photon lithography techniques, the authors are able to decipher the minimal guidance cues required for directed nerve growth along the major axis of the microelements. These features determine whether axons grow unidirectionally or cross paths via the open spaces between the elements, which is vital for the design of injectable Anisogels for enhanced nerve repair.
Medical imaging (image acquisition, image transformation, and image visualization) is a standard tool for clinicians in order to make diagnoses, plan surgeries, or educate students. Each of these steps is affected by uncertainty, which can highly influence the decision‐making process of clinicians. Visualization can help in understanding and communicating these uncertainties. In this manuscript, we aim to summarize the current state‐of‐the‐art in uncertainty‐aware visualization in medical imaging. Our report is based on the steps involved in medical imaging as well as its applications. Requirements are formulated to examine the considered approaches. In addition, this manuscript shows which approaches can be combined to form uncertainty‐aware medical imaging pipelines. Based on our analysis, we are able to point to open problems in uncertainty‐aware medical imaging.
ResearchGate has not been able to resolve any references for this publication.