Krzysztof Okarma

West Pomeranian University of Technology · Department of Signal Processing and Multimedia Engineering

In the paper the idea of the combined image quality metric based on the structural and feature similarity comparison is discussed. Since most of image quality assessment methods developed during last years require the nonlinear mapping to obtain high correlation with subjective quality scores, there is an important problem of choosing the proper ma...

Some of the main advantages of polynomial windows are their low computational complexity and ability to easily change their frequency response modifying the values of their coefficients in the time domain. Kulkarni [Polynomial windows with fast decaying sidelobes for narrow-band signals, Signal Processing 83 (2003) 1145-1149] presented the coeffici...

In this paper, a novel approach to Non-Destructive Testing (NDT) of defective materials for the aircraft industry is proposed, which utilizes an approach based on multifrequency and spectrogram eddy current method combined with an image analysis method previously applied for general-purpose full-reference image quality assessment (FR IQA). The prop...

In the paper, a novel hybrid method for an automatic quality assessment of binary images is proposed that may be useful, e.g., for computationally limited embedded systems or Optical Character Recognition applications. Since the quality of binary images used as the input for further image analysis strongly influences the obtained results, a reliabl...

In the paper a method supporting the optical character recognition from video sequences recorded with cameras without good stabilization is proposed. Due to the presence of various distortions, such as motion blur, shadows, lossy compression artifacts, auto-focusing errors, etc., the quality of individual video frames, e.g., recorded by a smartphon...

One of the continuous challenges related to the growing popularity of mobile devices and embedded systems with limited memory and computational power is the development of relatively fast methods for real-time image and video analysis. One such example is Optical Character Recognition (OCR), which is usually too complex for such devices. Considerin...

This chapter contains the results obtained during execution of Ukrainian-Polish Project in 2021 intended on design of methods and means for processing grayscale and multichannel images and video using visual quality metrics. The combined metrics have been designed and tested for remote sensing images as well as stitched panoramic images. Examples o...

The chapter describes the ways to design combined metrics and discusses several areas of their possible applications

Automatic recognition and classification of electronic integrated circuits based on optical character recognition combined with the analysis of the shape of their housings are essential to machine vision methods supporting the production of electronic parts, especially small-volume ones in the through-hole technology, characteristic of printed circ...

Since the number of acquired images and their size have the tendency to increase, their lossy compression is widely applied for their storage, transfer, and dissemination. Simultaneously with providing a relatively large compression ratio, lossy compression produces distortions that are inevitably introduced and have to be controlled. The propertie...

Unmanned aerial vehicle (UAV) imaging is a dynamically developing field, where the effectiveness of imaging applications highly depends on quality of the acquired images. No-reference image quality assessment is widely used for quality control and image processing management. However, there is a lack of accuracy and adequacy of existing quality met...

In the paper, an application of the recently proposed approach to hybrid image binarization based on pixel voting is considered for industrial images. Since such images typically contain the text embossed or engraved in metal nameplates, often non-uniformly illuminated, a proper binarization of such images is usually much harder than for scanned do...

Unmanned aerial vehicle (UAV) imaging is a dynamically developing field, where theeffectiveness of imaging applications highly depends on quality of the acquired images. No-reference image quality assessment is widely used for quality control and image processingmanagement. However, there is a lack of accuracy and adequacy of existing quality metri...

Magnetic field sensors installed in the road infrastructure can be used for autonomous traffic flow parametrization. Although the main goal of such a measuring system is the recognition of the class of vehicle and classification, velocity is the essential parameter for further calculation and it must be estimated with high reliability. In-field tes...

The optimal water flow in fish breeding tanks is one of the crucial elements necessary for the well-being and proper growth of fish, such as salmon or trout. Considering the round tanks and the uneven distribution of water-flow velocity, ensuring a nearly optimal flow is an important task that may be performed using various sensors installed to mon...

An automatic quality assessment of stitched images is an essential task in image analysis and is particularly useful not only in the creation of general-purpose panoramic images but also in terrain exploration and mapping made by mobile robots and drones. In Visual Simultaneous Localization and Mapping (VSLAM) solutions, the environment maps acquir...

This paper deals with providing the desired quality in the Better Portable Graphics (BPG)-based lossy compression of color and three-channel remote sensing (RS) images. Quality is described by the Mean Deviation Similarity Index (MDSI), which is proven to be one of the best metrics for characterizing compressed image quality due to its high convent...

No-reference image quality assessment is one of the most demanding areas of image analysis for many applications where the results of the analysis should be strongly correlated with the quality of an input image and the corresponding reference image is unavailable. One of the examples might be remote sensing since the transmission of such obtained...

Visual quality is important for remote sensing data presentedvas grayscale, color or pseudo-color images. Although several visual quality metrics (VQMs) have been used to characterize such data, only a limited analysis of their applicability in remotesensing applications has been done so far. In this paper, we study correlation factors for a wide s...

Image stitching is one of the relevant operations useful in virtual reality as well as in remote sensing applications which is used for the generation of panoramic images. The quality of the obtained panoramic images may be decreased due to the presence of various factors, e.g., geometric distortions, blur, ghosting, or colour distortions. Since th...

Thresholding of document images is one of the most relevant operations that influence the final results of their further analysis. Although many image binarization methods have been proposed during recent several years, starting from global thresholding, through local and adaptive methods, to more sophisticated multi-stage algorithms and the use of...

It is a common task in image lossy compression to provide a reasonable trade-off between a desired compression ratio (as large as possible) and an appropriate (preset according to a chosen metric) quality. Recently, a Better Portable Graphics (BPG) coder has been proposed that might become a new standard. A quality parameter Q is used in it to vary...

Lossy compression plays a vital role in modern digital image processing for producing a high compression ratio. However, distortion is unavoidable, which affects further image processing and must be handled with care. Providing a desired visual quality is an efficient approach for reaching a trade-off between introduced distortions and compression...

Quality assessment of stitched images is an important element of many virtual reality and remote sensing applications where the panoramic images may be used as a background as well as for navigation purposes. The quality of stitched images may be decreased by several factors, including geometric distortions, ghosting, blurring, and color distortion...

In the recent years, many objective image quality assessment methods have been proposed by different researchers, leading to a significant increase in their correlation with subjective quality evaluations. Although many recently proposed image quality assessment methods, particularly fullreference metrics, are in some cases highly correlated with t...

The main purpose of the conducted research is the development and experimental verification of the methods for detection of fish feeding as well as checking its uniformity in the recirculating aquaculture systems (RAS) using machine vision. A particular emphasis has been set on the methods useful for rainbow trout farming.

1

Quality assessment of the 3D printed surfaces is one of the crucial issues related to fast prototyping and manufacturing of individual parts and objects using the fused deposition modeling, especially in small series production. As some corrections of minor defects may be conducted during the printing process or just after the manufacturing, an aut...

The wide distribution of images of remote sensing (RS) of the Earth in various application areas makes it important to ensure the high quality of such images, which is important to identify necessary information. The complexity of the systems and the impact of various physical processes cause a significant number of distortions that lead to image c...

Quality assessment of the 3D printed surfaces is one of the crucial issues related to fast prototyping and manufacturing of individual parts and objects using the fused deposition modeling, especially in small series production. As some corrections of minor defects may be conducted during the printing process or just after the manufacturing, an aut...

A reliable automatic visual quality assessment of 3D-printed surfaces is one of the key issues related to computer and machine vision in the Industry 4.0 era. The colour-independent method based on image entropy proposed in the paper makes it possible to detect and identify some typical problems visible on the surfaces of objects obtained by additi...

Remote sensing images are subject to different types of degradations. The visual quality of such images is important because their visual inspection and analysis are still widely used in practice. To characterize the visual quality of remote sensing images, the use of specialized visual quality metrics is desired. Although the attempts to create su...

Image binarization is one of the most relevant preprocessing operations influencing the results of further image analysis conducted for many purposes. During this step a significant loss of information occurs and the use of inappropriate thresholding methods may cause difficulties in further shape analysis or even make it impossible to recognize di...

Objective quality assessment for 3D printing purposes may be considered as one of the most useful applications of machine vision in smart monitoring related to the development of the Industry 4.0 solutions. During recent years several approaches have been proposed, assuming observing the side surfaces, mainly based on the analysis of the regularity...

Image binarization is one of the key operations decreasing the amount of information used in further analysis of image data, significantly influencing the final results. Although in some applications, where well illuminated images may be easily captured, ensuring a high contrast, even a simple global thresholding may be sufficient, there are some m...

Binarization of document images is one of the most relevant preprocessing operations, leading to a significant decrease of the amount of information used during their further analysis. Since many document images, particularly historical, may be degraded over time, the application of some simple global thresholding methods usually lead to highly unsa...

Rapid growth of availability of modern electronic and robotic solutions, also for home and amateur use, related to the progress in home automation and popularity of the IoT systems, makes it possible to develop some unique hardware solutions, also by independent researchers and engineers, often with the help of the 3D printing technology. Although...

Increasing availability and popularity of 3D printers cause growing interest in monitoring of additive manufacturing processes as well as quality assessment and classification of 3D printed objects. For this purpose various methods can be used, in some cases dependent on the type of filament, including X-ray tomography and ultrasonic imaging as wel...

Automatic classification of electronic elements based on image analysis may be useful for verification of a proper selection of electronic integrated circuits previously assembled in the Printed Circuit Boards (PCBs), as well as for an automated sorting of such elements in robotic systems supporting their production. Although modern high speed pick...

Automatic visual quality assessment of the 3D printed surfaces is currently one of the most demanding challenges in additive manufacturing. Regardless of the applications of the computer vision for the 3D printing process monitoring purposes, a reliable surface quality evaluation during manufacturing may introduce brand new possibilities. The detec...

The main purpose of conducted research is the development of a new image thresholding method, which is faster than typical adaptive methods and more accurate than global binarization. Since natural images captured by cameras are usually unevenly illuminated, due to unknown and various lighting conditions, an appropriate binarization influences the...

One of the key operations during the image preprocessing step in Optical Character Recognition (OCR) algorithms is image binarization. Although for uniformly illuminated images, obtained typically by atbed scanners, the use of a single global threshold may be sufficient for further recognition of individual characters, it cannot be applied directly...

Automatic visual quality assessment of objects created using additive manufacturing processes is one of the hot topics in the Industry 4.0 era. As the 3D printing becomes more and more popular, also for everyday home use, a reliable visual quality assessment of printed surfaces attracts a great interest. One of the most obvious reasons is the possi...

Image quality assessment (IQA) is one of the constantly active areas of research in computer vision. Starting from the idea of Universal Image Quality Index (UIQI), followed by well-known Structural Similarity (SSIM) and its numerous extensions and modifications, through Feature Similarity (FSIM) towards combined metrics using the multi-metric fusi...

Automatic text recognition from the natural images acquired in uncontrolled lighting conditions is a challenging task due to the presence of shadows hindering the shape analysis and classification of individual characters. Since the optical character recognition methods require prior image binarization, the application of classical global threshold...

One of the most crucial steps of preprocessing of document images subjected to further text recognition is their binarization, which influences significantly obtained OCR results. Since for degrades images, particularly historical documents, classical global and local thresholding methods may be inappropriate, a challenging task of their binarizati...

Modern Intelligent Transportation Systems (ITS) are strictly related to the use of various types of sensors to allow gathering information about the parameters of vehicles and their motion. Rapid development of video technology and availability of relatively cheap high resolution cameras cause the increased interest in the use of vision sensors mou...

A rapid development and growing popularity of additive manufacturing technology leads to new challenging tasks allowing not only a reliable monitoring of the progress of the 3D printing process but also the quality of the printed objects. The automatic objective assessment of the surface quality of the 3D printed objects proposed in the paper, whic...

In the paper a texture classification method utilizing the Gray Level Co-occurrence Matrix (GLCM) is proposed which can be applied for autonomous cleaning robots. Our approach is based on the analysis of chosen Haralick features calculated locally together with their selected statistical properties allowing to determine the additional features used...

Adaptive binarization of unevenly lightened images is one of the key issues in document image analysis and further text recognition. As the global thresholding leads to improper results making correct text recognition practically impossible, an efficient implementation of adaptive thresholding is necessary. The most popular global approach is the u...

Fast and reliable adaptive binarization of unevenly lightened document images is one of the key issues for the Optical Character Recognition (OCR) purposes applied in mobile devices with limited computational power. Considering the document image captured in unknown lighting conditions the use of a single global thresholding in the binarization ste...

In this paper a novel approach to quality evaluation of flat surfaces of the 3D printed objects has been discussed. The proposed approach utilizes the regularity of the layers visible on the printed surfaces which are extracted using Hough transform. Nevertheless, due to the variety of filament’s colours, the application of a single metric which ca...

Binarization of highly degraded document images is one of the key steps of image preprocessing, influencing the final results of further text recognition and document analysis. As the contaminations visible on such documents are usually local, the most popular fast global thresholding methods should not be directly applied for such images. On the o...

The main purpose of the visual quality assessment of 3D prints is the detection of surface distortions which can be made using various approaches. Nevertheless, a reliable classification of 3D printed samples into low and high quality ones can be troublesome, especially assuming the unknown color of the filament. Such a classification can be effici...

In the paper the issue of quality assessment of 3D printed surfaces using image analysis is considered with particular attention paid to Fourier analysis of image fragments resized to one-dimensional vectors. Due to the application if Fourier analysis the regularity of visible patterns related to the consecutive layers of the filament can be assess...

The paper focuses on the presentation of the Binary Line Oriented Histogram (BLOH) algorithm, originating from the Edge Oriented Histogram (EOH). In the case of thin single-pixel lines, a problem related to the interpretation of the EOH bins may occur which can be eliminated using the proposed approach. The main goal of the conducted experimental t...

This paper presents a novel method for estimating the degree of deformations in 3D prints. The increased popularity of three-dimensional printing techniques introduces a necessity to create methods for quality assessment of printed materials. One of the key problems of 3D printing are strains and deformations of printed objects. This problem is det...

Visual quality inspection of 3D prints is one of the most recent challenges in image quality assessment domain. One of the natural approaches to this issue seems to be the use of some existing metrics successfully applied to general image quality assessment purposes. Since the application of basic Structural Similarity does not lead to satisfactory...

The paper is focused on the issue of visual quality assessment of 3D printed surfaces which can be helpful in detection of quality decrease during the printing process as well as the quality inspection of previously printed objects. The basic assumption of the proposed approach is the fact that each distortion of the regular patterns, visible on th...

Bezpośrednio po zakończeniu II wojny światowej społeczeństwo i władze szczecińskie zdawały sobie sprawę, że wobec dotkliwego braku kadr z wyższym wykształceniem należy jak najszybciej zacząć przygotowania zmierzające do utworzenia w tym mieście uczelni, które przede wszystkim powinny kształcić bardzo potrzebnych specjalistów dla gospodarki

In the paper the experimental results of texture classification based on Haralick features for autonomous cleaning robots are presented. Since the classification based on the application of four classical features has not led to satisfactory results, some additional features based on their variance have been considered. For verification purposes a...

In this paper the method of automatic quality assessment of the flat 3D prints based on the use of the Hough transform is presented. The idea of the method is based on the assumption of high visibility of relatively large number of long straight lines in the randomly chosen fragments of high quality printed surfaces. Obtained experimental results c...

In this paper an experimental system allowing an automatic recognition of digits and numbers has been presented. Strictly fitted character of the system and its industrial application is related to the requirements limiting the use of some typical OCR solutions e.g. based on Tesseract or application of the HOG descriptor. Obtained experimental resu...

In the paper the automatic method of visual quality assessment of surfaces of 3D prints is presented. The proposed approach is based on the use of entropy and may be applied for on-line inspection of 3D printing progress during the printing process. In case of observed decrease of the printed surface quality the emergency stop may be used allowing...

In this paper a short story of the 70 years of the Faculty of Electrical Engineering in Szczecin is presented. Starting from 1947 as one of 3 faculties founded at the Engineering School in Szczecin, it became, as a result of the school transformation in 1955, one of six Faculties of Technical University of Szczecin. Since 2009, after merging with A...

In the paper the method of “blind” quality assessment of 3D prints based on texture analysis using the GLCM and chosen Haralick features is discussed. As the proposed approach has been verified using the images obtained by scanning the 3D printed plates, some dependencies related to the transparency of filaments may be noticed. Furthermore, conside...

The paper is related to the verification of the usefulness of some metrics, typically used for image quality assessment and texture similarity evaluation, for no-reference quality assessment of 3D prints. The proposed approach is based on the assumption that a surface of high quality 3D print should be homogeneous and therefore some parts of it sho...

Quality assessment of 3D prints is one of the newest challenges for machine vision. As the 3D printing is relatively new technology, it is still far from perfection and there are many static or dynamically changing factors which can affect the quality of the final 3D prints. Considering the relatively long time necessary for printing, it may be reas...

In the paper the idea of multiple metrics fusion for binary image quality assessment is presented together with experimental results obtained using the images from Bilevel Image Similarity Ground Truth Archive. As the performance evaluation of any full-reference image quality assessment metric requires both the knowledge of reference images with pe...

This paper deals with the problem of estimating the similarity of clothing for the purpose of fashion-related e-commerce systems. The images presenting fashion models are segmented and analyzed in order to detect clothing characteristics. We propose a method based on human pose estimation and body parts segmentation, followed by the analysis of dom...

W publikacji przedstawiono genezę założenia oraz historię Wydziału Elektrycznego Zachodniopomorskiego Uniwersytetu Technologicznego w Szczecinie. Wydział powołany został w 1946 r. jako jeden z trzech wydziałów Szkoły Inżynierskiej w Szczecinie. W roku 1955, w wyniku przekształcenia uczelni, stał się jednym z sześciu Wydziałów Politechniki Szczecińs...

In the paper the problem of reliable evaluation of the effects of image binarization is discussed in view of image recognition accuracy. Considering the Optical Character Recognition methods, typically used for document images obtained by cameras or scanners, their accuracy is strongly dependent on the results of image binarization. Unfortunately,...

Reading text from natural images is much more difficult than from scanned text documents since the text may appear in all colors, different sizes and types, often with distorted geometry or textures applied. The paper presents the idea of high-speed image preprocessing algorithms utilizing the quasi-local histogram based methods such as binarization,...

Navigation of mobile robots based on video analysis becomes one of the most popular application areas of machine vision in automation and robotics. Recently growing popularity of Unmanned Aerial Vehicles (drones) as well as some other types of autonomous mobile robots leads to rapid increase of their application possibilities e.g. related to explor...

In the paper the idea of the visual self-localization of mobile robots based on the estimation of image similarity is discussed. It is assumed that a rough position of the mobile robot is known e.g. from the built-in GPS device. Assuming known orientation of the robot, the main advantage of the application of image analysis algorithms is the increa...

The article concerns the fast image binarization based on the application of the statistical Monte Carlo method applied for the recognition of the QR codes from colour images, especially captured by mobile devices’ cameras. Due to limited processing possibilities of some mobile devices as well as relatively low quality of some optical systems in bu...

Rapid progress in the field of machine vision applications can be especially clearly visible in robotics. For this reason many groups of image processing and analysis algorithms and solutions which have not been previously applied in automation and robotics require testing, verification and modifications before their application in any hardware sol...

The paper concerns with the problem of fully visual self-navigation of mobile robots based on the analysis of similarity of images, acquired by the cameras mounted on the robot, with some previously captured images stored in a database. In order to simplify and speed-up the extraction of the necessary data from the image database it is assumed that...

In the paper a fast algorithm of image downsampling is presented which is based on the estimation of mean local luminance using the Monte Carlo method assuming the division of an image into smaller non-overlapping blocks. Due to modifications proposed in the paper, one can obtain similar results than for classical methods compared using recently pr...

In the paper an algorithm for binarization of grayscale images representing text documents together with its optimization is presented. In the proposed approach two classical global thresholding algorithms proposed by Otsu and Kapur are combined with their local versions applied for blocks. The experimental results have been obtained for the H-DIBC...

Due to the growing popularity of 3D imaging technology which can be observed in recent years, one of the most relevant challenges for image quality assessment methods has become their extension towards reliable evaluation of stereoscopic images. Since known 2D image quality metrics are not necessarily well correlated with subjective quality scores...

In the paper the idea of using the super-resolution algorithms for the self-localization and vision based navigation of autonomous mobile robots is discussed. Since such task is often limited both by the limited resolution of the mounted video camera as well as the available computational resources, a typical approach for video based navigation of...

Since most of even recently proposed image quality assessment metrics are typically applied for a single color channel in both compared images, a reliable color image quality assessment is still a challenging task for researchers. One of the major drawbacks limiting the progress in this field is the lack of image datasets containing the subjective...

In this paper some experimental results obtained by the application of various image quality assessment methods for the estimation of similarity of textile materials are presented. Such approach is considered as a part of an artificial intelligence based system developed for the recognition of clothing styles based on multi-dimensional analysis of...

In the paper the idea of universal fast image binarization method is discussed which utilizes the histogram estimation using the Monte Carlo approach. Proposed reduction of the computational burden dependent on the number of analyzed pixels may be useful especially in real-time and embedded systems with limited amount of memory and processing power...

The paper deals with a problem of comparing and retrieving visual data representing various clothing styles. Proposed solution joins several sophisticated computer vision methods, such as face detection using AdaBoost strategy, human body segmentation and decomposition using pictorial structures and appearance models, together with visual descripto...