No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Automatic Segmentation in Tongue Image by Mouth Location and Active Appearance Model
Abstract
We demonstrate a novel method to segment the tongue image automatically with the mouth location method and active appearance model (AAM). With the help of a particular feature of the mouth,we could locate the dark hole's position easily and quickly. For the close relationship between the mouth and tongue, we would predict the approximate area of the tongue. Then we apply the AAM to segment the tongue from the image completely, which uses texture and shape of an object. During the AAM search, we constrain the initial displacement and size in the approximate area. For those images that failed to locate the mouth, we use a multi-initial displacement method during the AAM search to optimize the result. The experiment shows that our method is accurate and effective.
... But there was only one sample in the experiment, so it was not enough to prove the accuracy of this method for various kinds of tongue images. Zhong et al. [14] suggested a novel method to segment the tongue image automatically with the mouth location method and active appearance model. Due to the different positions of tongues in the tongue images, this method needed to use different initial contours to segment tongue body region, which brought some inconvenience to the applications of tongue diagnoses. ...
Tongue image with coating is of important clinical diagnostic meaning, but traditional tongue image extraction method is not competent for extraction of tongue image with thick coating. In this paper, a novel method is suggested, which applies multiobjective greedy rules and makes fusion of color and space information in order to extract tongue image accurately. A comparative study of several contemporary tongue image extraction methods is also made from the aspects of accuracy and efficiency. As the experimental results show, geodesic active contour is quite slow and not accurate, the other 3 methods achieve fairly good segmentation results except in the case of the tongue with thick coating, our method achieves ideal segmentation results whatever types of tongue images are, and efficiency of our method is acceptable for the application of quantitative check of tongue image.
Many researchers make use of thresholding and morphological operations for feature extraction and segmentation. Efficient operations are still not included in the existing dental software majorly used by dental practitioners. Hence, the effective benefits of these methods are still not available to the end users. Some of the research work has been reported for human identification, but very few researchers have applied and realised the methods for diagnosis purpose. Geometrical features for measurements like area, length and angle are not detected by all software even though they are considered the basic features especially for the diagnosis of intra-oral diseases. Interactive portions of X-ray selected for further processing specifically for the purpose of diagnosis is the need of the hour as it would help both doctors and patients to understand the problem and depth of disease. No software exploits the power of AI tools and techniques such as neural network and fuzzy C-means. The usage of such methods may help better in identification and diagnosis of dental cavities. Exploration, development, and use of different automated and semi-automated methods for the analysis of dental radiographs may lead to progress in the knowledge and usage of more such methods that can be used for identification and diagnosis of some dental diseases. The overall contribution of this thesis attempts to make progress on these objectives which may finally contribute as an add-on help to dental practitioners and patients at large.
This paper reviews the recent advances in a significant constituent of traditional oriental medicinal technology, called tongue diagnosis. Tongue diagnosis can be an effective, non-invasive method to perform an auxiliary diagnosis any time anywhere, which can support the global need in the primary health care system. This work explores the literature to evaluate the works done on the various aspects of computerized tongue diagnosis, namely pre-processing, tongue detection, segmentation, feature extraction, tongue analysis especially in traditional Chinese medicine (TCM). In spite of huge volume of work done on automatic tongue diagnosis, there is a lack of adequate survey, especially to combine it with the current diagnosis trends. This paper studies the merits, capabilities and associated research gaps in current works on automatic tongue diagnosis systems. After exploring the algorithms used in tongue diagnosis, the current trend and global requirements in health domain motivates us to propose a conceptual framework for the automated tongue diagnostic system on mobile enabled platform. This framework will be able to connect tongue diagnosis with the future point-of-care health system.
According to the chroma distribution diversity (CDD) between lip color and skin color, the lip color area is segmented by the back propagation neural network (BPNN) with three typical color features. Isolated noisy points of the lip color area in binary image are eliminated by a proposed region connecting algorithm. An improved integral projection algorithm is presented to locate the lip boundary. Whether a driver is fatigued is recognized by the ratio of the frame number of the images with mouth opening continuously to the total image frame number in every 20 s. The experiments show that the proposed algorithm provides higher correct rate and reliability for fatigue driving detection, and is superior to the single color feature-based method in the lip color segmention. Besides, it improves obviously the accuracy and speed of the lip boundary location compared with the traditional integral projection algorithm.
Tongue diagnosis is one of the most important instruments in traditional Chinese medicine (TCM). While the tongue body segmentation acts an indispensable role in the automatic tongue diagnosis system. This study utilizes geodesic active contour model (level set function) to forward a novel segmentation approach. The tongue image is firstly divided into two parts according to the prior knowledge of tongue shape and location. Then, a double geodesic flow is applied, respectively, in which way both flows get their suitable evolutional modes. Experimental results show that the proposed approach can enhance the accuracy and practicability obviously, compared to the other state-of-arts works.
Lip feature extraction is one of the most challenging tasks in the lip reading systems' performance. In this paper, a new approach for lip contour extraction based on fuzzy clustering is proposed. The algorithm employs a stochastic cost function to partition a color image into lip and non-lip regions such that the joint probability of the two regions is maximized. First, the mouth location is determined and then, lip region is preprocessed using pseudo hue transformation. Fuzzy c-means clustering is applied to each transformed image along with b components of CIELAB color space. To delete the clustered pixels around lip, an ellipse and a Gaussian mask were used. In order to show the performance of the proposed method, the pseudo hue segmentation and fuzzy c-mean clustering without preprocessing are compared. The compared methods were applied to the VidTIMIT and M2VTS databases and the results show the superiority of the proposed method in comparison with other methods.
Statistical models of the shape and appearance of image structures can be matched to new images using both the Active Shape Model [7] algorithm and the Active Appearance Model algorithm [2]. The former searches along profiles about the current model point positions to update the current estimate of the shape of the object. The latter samples the image data under the current instance and uses the difference between model and sample to update the appearance model parameters. In this paper we compare and contrast the two algorithms, giving the results of experiments testing their performance on two data sets, one of faces, the other of structures in MR brain sections. We find that the ASM is faster and achieves more accurate feature point location than the AAM, but the AAM gives a better match to the texture.
A novel scheme for the detection of object boundaries is presented. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The evolving contours naturally split and merge, allowing the simultaneous detection of several objects and both interior and exterior boundaries. The proposed approach is based on the relation between active contours and the computation of geodesics or minimal distance curves. The minimal distance curve lays in a Riemannian space whose metric is defined by the image content. This geodesic approach for object segmentation allows to connect classical "snakes" based on energy minimization and geometric active contours based on the theory of curve evolution. Previous models of geometric active contours are improved, allowing stable boundary detection when their gradients suffer from large variations, including gaps. Formal results concerning existence, uniqueness, stability, and correctness of the evolution a...
Automated tongue image segmentation in Chinese medicine is difficult due to two special factors: (1) There are a lot of pathological details on the surface of the tongue, which have a large influence on edge extraction; (2) the shapes of tongue bodies captured from various diseases or persons are quite different, so they are impossible to be properly described by a predefined deformable template. To address these problems, We propose a technique based on the combination of a bi-elliptical deformable template and an active contour model, namely the bi-elliptical deformable contour. Applying our approach to clinical tongue images, the experimental results indicate that it is superior over both traditional deformable templates and active contour model or snakes with respect to stability and veracity.
Active Appearance Models (AAMs) and the closely related concepts of Morphable Models and Active Blobs are generative models of a certain visual phenomenon. Although linear in both shape and appearance, overall, AAMs are nonlinear parametric models in terms of the pixel intensities. Fitting an AAM to an image consists of minimising the error between the input image and the closest model instance; i.e. solving a nonlinear optimisation problem. We propose an efficient fitting algorithm for AAMs based on the inverse compositional image alignment algorithm. We show that the effects of appearance variation during fitting can be precomputed ("projected out") using this algorithm and how it can be extended to include a global shape normalising warp, typically a 2D similarity transformation. We evaluate our algorithm to determine which of its novel aspects improve AAM fitting performance.
Triangle is a robust implementation of two-dimensional constrained Delaunay triangulation and Ruppert's Delaunay refinement algorithm for quality mesh generation. Several implementation issues are discussed, including the choice of triangulation algorithms and data structures, the effect of several variants of the Delaunay refinement algorithm on mesh quality, and the use of adaptive exact arithmetic to ensure robustness with minimal sacrifice of speed. The problem of triangulating a planar straight line graph (PSLG) without introducing new small angles is shown to be impossible for some PSLGs, contradicting the claim that a variant of the Delaunay refinement algorithm solves this problem.
Model-based vision is firmly established as a robust approach to recognizing and locating known rigid objects in the presence of noise, clutter, and occlusion. It is more problematic to apply model-based methods to images of objects whose appearance can vary, though a number of approaches based on the use of flexible templates have been proposed. The problem with existing methods is that they sacrifice model specificity in order to accommodate variability, thereby compromising robustness during image interpretation. We argue that a model should only be able to deform in ways characteristic of the class of objects it represents. We describe a method for building models by learning patterns of variability from a training set of correctly annotated images. These models can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes). The key difference is that our Active Shape Models can only deform to fit the data in ways consistent with the training set. We show several practical examples where we have built such models and used them to locate partially occluded objects in noisy, cluttered images.
We demonstrate a novel method of interpreting images using an Active Appearance Model (AAM). An AAM contains a statistical
model of the shape and grey-level appearance of the object of interest which can generalise to almost any valid example. During
a training phase we learn the relationship between model parameter displacements and the residual errors induced between a
training image and a synthesised model example. To match to an image we measure the current residuals and use the model to
predict changes to the current parameters, leading to a better fit. A good overall match is obtained in a few iterations,
even from poor starting estimates. We describe the technique in detail and give results of quantitative performance tests.
We anticipate that the AAM algorithm will be an important method for locating deformable objects in many applications.
The extraction of tongue area from digital photos is essential to an automatic tongue diagnostic system in traditional Chinese medicine. Simple segmentation methods couldn't be effective due to the weak edge of tongue and the details on the tongue's surface. In this paper, we propose a unique segmentation method based on the combination of the watershed transform and active contour model (ACM). The watershed transform is used to get the initial contour, and an active contour model, or "snakes", is used to converge to the precise edge. This method is proved to be effective and steady in experiments on tongue image.
Color Tongue Image Segmentation Algorithm Based On Grey Space Auto-Thresholding Selection
- Ren Jijun