Search

In this paper we study the problem of classification of wireless capsule endoscopy images (WCE). We aim at developing a computer system that would aid in medical diagnosis procedure. The goal is to automatically detect images showing pathological alterations in an 8-hour-long WCE video. We focus on three classes of pathologies, ulcers, bleedings and petechia, since they are typical for several diseases of intestines. Utilized are methods for image texture and color analysis to obtain numerical description of images. Then, three methods for selection of most discriminative descriptors are used, namely Vector Supported Convex Hull, Support Vector Machines and Radial Basis Function Networks. The results produced by the three methods are compared. [ABSTRACT FROM AUTHOR]

This paper presents a novel technique for automatic segmentation of wireless capsule endoscopic images. The main contribution resides in the integration of three computational blocks: 1) local polynomial approximation algorithm which finds locally-adapted neighborhood of each pixel; 2) color texture analysis which describes each pixel by a vector of numerical attributes that reflect this pixel local neighborhood characteristcs; and 3) cluster analysis (k-means) for grouping pixels into homgeneous regions based on their color information. The proposed approach leads to a robust segmentation procedure which produces fine segments well matched to the image contents. [ABSTRACT FROM AUTHOR]

In this paper we present a novel technique for unsupervised texture segmentation of wireless capsule endoscopic images of the human gastrointestinal tract. Our approach integrates local polynomial approximation algorithm with the well-founded methods of color texture analysis and clustering (k-means) leading to a robust segmentation procedure which produces fine-grained segments well matched to the image contents. [ABSTRACT FROM AUTHOR]

The research presented in this paper aimed at development of a robust feature space exploration technique for unsupervised selection of its subspace for feature vectors classification. Experiments with synthetic and textured image data sets show that current sequential and evolutionary strategies are inefficient in the cases of large feature vector dimensions (reaching the order of 102) and multiple-class problems. Thus, the proposed approach utilizes the concept of hybrid genetic algorithm and adopts it for specific requirements of unsupervised learning. [ABSTRACT FROM AUTHOR]

In this paper we propose and examine a Vector Supported Convex Hull method for feature subset selection. Within feature subspaces, the method checks locations of vectors belonging to one class with respect to the convex hull of vectors belonging to the other class. Based on such analysis a coefficient is proposed for evaluation of subspace discrimination ability. The method allows for finding subspaces in which vectors of one class cluster and they are surrounded by vectors of the other class. The method is applied for selection of color and texture descriptors of capsule endoscope images. The study aims at finding a small set of descriptors for detection of pathological changes in the gastrointestinal tract. The results obtained by means of the Vector Supported Convex Hull are compared with results produced by a Support Vector Machine with the radial basis function kernel. [ABSTRACT FROM AUTHOR]

In this paper we present a novel feature selection method that is applicable in unsupervised learning tasks. The method is based on clustering quality measures, which reflect different aspects of clustering performance. Sequential Floating Forward Search algorithm is employed to search through the original feature space for the best possible subset. Main stress has been put on the objectivism of the new technique, so that it could be applied in various classification tasks. Results of experiments with texture images are presented in order to confirm effectiveness of the method. [ABSTRACT FROM AUTHOR]