Algorithm for Calculating the Similarity between Histograms for Texture Segmentation

The purpose of the research is to develop a universal algorithm for partial texture segmentation of any visual images. The main peculiarity of the proposed segmentation procedure is the extraction of only homogeneous fine-grained texture segments present in the images. At first, an initial seed point is found for the largest and most homogeneous segment of the image. This initial seed point of the segment is expanded using a region growing method. Other texture segments of the image are extracted analogously in turn. At the second stage, the procedure of merging the extracted segments belonging to the same texture class is performed. Then, the detected texture segments are input to a neural network with competitive layers which accomplishes more accurate delineation of the shapes of the extracted texture segments. The proposed segmentation procedure is fully unsupervised, i.e., it does not use any a priori knowledge on either the type of textures or the number of texture segments in the image. The research results in development of the segmentation algorithm realized as a computer program tested in a series of experiments that demonstrate its efficiency on grayscale natural scenes.

In order to improve the edge accuracy and the areas consistency, to reduce the partition error rate in textural image segmentation, we propose a new method which using multi-scale wavelet analysis based on feature learning in this paper. It improves the textural image segmentation by reducing the effect of redundant features on segmentation results. The method includes three stages as feature extraction, optimizing the feature vectors and feature space clustering. In the stage of filtrating valid features, we optimize the feature vectors by feature learning. The experimental results demonstrate that the improved algorithm is effective for textural image segmentation.

In order to increase the edge accuracy and the areas consistency, and to reduce the partition error rate in textural image segmentation, we propose a new multi-scale wavelet analysis based on feature learning in this paper. It improves the textural image segmentation by reducing the effect of redundant features on segmentation results. This method includes three stages as follows: feature extraction, optimizing the feature vectors and feature space clustering. In the stage of filtrating valid features, we optimize the feature vectors by feature learning. The experimental results demonstrate that the improved algorithm is effective for textural image segmentation.

In the study of object recognition, image texture segmentation has being a hot and difficult aspect in computer vision. Feature extraction and texture segmentation algorithm are two key steps in texture segmentation. An effective texture description is the important factor of texture segmentation. In this paper, the neuronal activation degree (NAD) of visual model is exploited as the texture description of image patches. By processing the length and direction of NAD, we develop an effective segmentation strategy. First, the length of the NAD are used to partition blank area and non-blank area, then the mark index of neuron is used, which is maximally activated to identify the label of each segment unit to get an initial segmentation. Finally, region merging steps is exerted to get a desired result.

The authors present a linear feature-reduction technique for multicomponent or textured image segmentation. The transformation matrix is computed by simultaneously diagonalizing scatter matrices evaluated at two different spatial resolutions. Under reasonable conditions, this transform closely approximates the generalized Fisher linear discriminants which are optimal for region separability. Experimental examples suggest that this technique is superior to the Karhunen-Loeve transform for texture segmentation. >

The objective of this work is to simulate visual cortical cells, their sensitivities to frequencies and orientations, and their part in texture segmentation. The simulation of these cells is realised through band-pass, oriented filters (Gabor filters), and multiresolution image decomposition. By this means, the filter sensitivities represent cell sensitivities to preferred orientations according to their frequency and orientation bandwidths, and multiresolution represents the different band frequencies. For texture analysis and segmentation, overlaying of band-pass filters is necessary to completely cover the Fourier domain. A continuous sensitivity to frequency and orientation is achieved by the filters overlapping and consequently by their interpolation. We used here four octave frequency bands from 1 to 16 cycles deg−1 and six orientations per band. The results obtained for texture segmentation with these parameters are very promising (up to 97% recognition rate) [Guérin-Dugué and Palagi, 1994 Neural Processing Letters1(1) 25 – 29]. The images analysed cover a multitude of different domains such as psychophysical tests and natural textures of different roughness. In order to create a cortical cell representation closer to neurophysiological data, and to improve texture segmentation results, we represent cell sensitivities by their foveal and parafoveal projections [R L DeValois, K K DeValois, 1988 Spatial Vision (Oxford: Oxford Science Publications)]. Cells receiving projections from the foveal zone are modeled by five octave frequency bands (from 0.5 to 16 cycles deg−1) and six orientations. Cells receiving projections from the parafoveal zone have the same sensitivities but are modeled by four octave frequency bands (from 0.5 to 8 cycles deg−1). By using these two different resolutions, preliminary tests have shown the capability of detecting textured regions by the parafoveal projection and localisation of boundaries by the foveal projection.

A new approach to colour-texture segmentation is presented which uses Local Binary Pattern data and a new colour quantisation scheme based on hue and saturation to provide evidence from which pixels can be classified into texture classes. The proposed algorithm, which we contend to be the first use of evidence gathering in the field of texture classification, uses Generalised Hough Transform style R-tables as unique descriptors for each texture class. Tests on remotely sensed images demonstrate the superiority of the colour-texture algorithm compared to the established JSEG algorithm; a notable advantage of the new approach is the absence of over-segmentation. The VisTex database is used to compare the colour-texture algorithm with alternative methods, including its grey-scale equivalent, for the segmentation of colour texture images; providing good results with smooth texture boundaries and low noise within texture segments. (6 pages)

We present an approach for unsupervised segmentation of natural and textural images based on active contour, differential geometry and information theoretical concept. More precisely, we propose a new texture descriptor which intrinsically defines the geometry of textural regions using the shape operator borrowed from differential geometry. Then, we use the popular Kullback-Leibler distance to define an active contour model which distinguishes the background and textural objects of interest represented by the probability density functions of our new texture descriptor. We prove the existence of a solution to the proposed segmentation model. Finally, a fast and easy to implement texture segmentation algorithm is introduced to extract meaningful objects. We present promising synthetic and real-world results and compare our algorithm to other state-of-the-art techniques.

Perceptual segmentation of a boundary between two textures is conventionally thought to be based upon differences in their Fourier energy, i.e. in their low-order texture statistics. Most evidence supporting (or contradicting) this idea has arisen from studies using various synthetic texture patterns. But what role, if any, do higher-order texture statistics play in segmenting natural images? Here we extracted high resolution texture regions from monochrome photographs of natural scenes, rich in higher-order statistics. By phase-scrambling these textures, we could remove their high-order statistics, leaving mean luminance and RMS contrast unchanged. Using pairs of natural or phase-scrambled textures, we created RMS-balanced texture quilt boundaries in half-disc stimuli. We also created similar contrast boundaries from individual textures. Employing forced choice judgments of boundary orientation (left- vs. right-oblique), we measured modulation-depth thresholds for both contrast and texture boundaries. If only the low-order statistics are used, then phase-scrambling should have no effect on psychophysical performance. Boundaries between these texture pairs could usually be segregated (thresholds: 35–70%), though in some cases even 100% modulation-depth did not produce reliable performance. In most instances, phase-scrambling made the task impossible. However in a minority of scrambled texture pairs, thresholds were measurable and in some, performance was improved. Contrast boundaries yielded lower modulation-depth thresholds (10–30%) which were impervious to or improved by phase-scrambling, particularly at lower texture contrasts. These results suggest that higher-order texture statistics contribute importantly to boundary segmentation in natural scenes.

One of the more successful engineering applications of fractal geometry has been the utilization of fractal image models in medical image processing. These applications have included tissue characterization studies, textural image segmentation, and image restoration using fractal constraints. The class of fractal models used in medical image processing and the techniques used to estimate the fractal dimension associated with these models will be reviewed. An image segmentation algorithm that utilized a fractal textural feature and formulated the segmentation process as a configurational optimization problem is presented. The configurational optimization method allows information about both, the degree of correspondence between a candidate segment and an assumed textural model, and morphological information about the candidate segment to be used in the segmentation process. To apply this configurational optimization technique with a fractal textural model however, requires the estimation of the fractal dimension of an irregularly shaped candidate segment. The potential utility of a discrete Gerchberg-Papoulis bandlimited extrapolation algorithm to the estimation of the fractal dimension of an irregularly shaped candidate segment is also discussed.

This paper describes a neural network which detects the edges of different orientation and spatial frequency in an image. The proposed neural network is useful for image analysis, feature extraction, and texture segmentation.

Monocomponent image decomposition plays an important role in image analysis and related areas, such as image denoising, object detection, and texture segmentation. Existing image decomposition methods can extract monocomponents but their performances are insufficiently accurate because of interference and redundancy component problems caused by inaccurate spectrum segmentation. In this paper, an empirical monocomponent image decomposition (EMID) is proposed for fully recoverable monocomponents. The EMID method empirically decomposes an image into monocomponents based on energy concentration in Fourier support. This method is composed of two main processes: 1) energy concentration-based segmentation and 2) empirical image filter bank construction. In the former process, the base of a mountain-shaped energy concentration that can perfectly represent the monocomponent spectrum boundary is detected and identified. This process provides a more accurate spectrum segmentation which helps prevent the serious problems from interference and redundancy components. In the latter process, an empirical image filter bank is constructed in accordance with the actual monocomponent boundaries by means of ellipse and Gaussian functions and used to decompose an image into monocomponent images with fewer ringing artifacts. The experimental results show that the proposed EMID method achieves a better decomposition than the state-of-the-art methods in terms of the quality of monocomponent images that are evaluated by peak signal-to-noise ratio and structural similarity index. Furthermore, in a real world dataset, the EMID method is able to clearly detect text regions, thus significantly improving the efficiency of Thai text character localization in natural scene images.

In this paper, a novel chaos particle swarm optimization(PSO) clustering algorithm for texture image segmentation was proposed. By means of stochastic property and ergodicity of chaos search mechanism, chaos PSO algorithm can effectively avoid getting into the local convergence. The proposed method combined chaos PSO algorithm with nearest neighbor clustering theorem, which can enhance the efficiency and precision of clustering. And the proposed chaos PSO clustering algorithm was applied to texture image segmentation with gray level co-occurrence matrix. The experimental results indicate that the proposed method can get better segmentation results than PSO algorithm and effectively improve the segmentation precision of texture image.Keywordsparticle swarm optimizationchaostexture segmentationgray level co-occurrence matrix (GLCM)

Automatic computation of the area irradiated by ultrashort laser pulses in Sb materials through texture segmentation of TEM images

In this paper the problem of texture image analysis in the presence of noise is examined from a higher-order statistical perspective and in the context of noise. The objective is to develop analysis techniques through which robust texture characteristics are extracted and used for texture modelling and segmentation. The approaches taken involve the use of autoregressive models whose parameters derived first from joint and weighted second and third order cumulants and secondly as a solution to a weighted overdetermined set of equations in which the weights are appropriate functions of the eigenvalue spread. The required segmentation of such 2D random fields is effected through the additional stage of a neural network having as inputs the extracted autoregressive parameters. The paper describes the fundamental issues of the various components of the approach.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.