Convex Hull-Based Feature Selection in Application to Classification of Wireless Capsule Endoscopic Images
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.
KeywordsWireless capsule endoscopy feature selection convex hull support vector machines
Unable to display preview. Download preview PDF.
- 2.Tuceryan, M., Jain, A.: Texture Analysis. In: The Handbook of Pattern Recogntion and Computer Vision, pp. 207–248. World Scientific Publishing Co., Singapore (1998)Google Scholar
- 5.Coimbra, M., Campos, P., Cunha, J.: Extracting clinical information from endoscopic capsule exams using mpeg-7 visual descriptors. In: The 2nd European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology, EWIMT 2005, pp. 105–110 (2005)Google Scholar
- 7.Mackiewicz, M., Berens, J., Fisher, M., Bell, G.: Colour and texture based gastrointestinal tissue discrimination. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, May 2006, vol. 2, pp. 597–600 (2006)Google Scholar
- 8.Mackiewicz, M., Berens, J., Fisher, M.: Wireless capsule endoscopy video segmentation using support vector classifiers and hidden markov models. In: Proceedings of the International Conference on Medical Image Understanding and Analyses (June 2006)Google Scholar
- 9.Li, B., Meng, M.H.: Ulcer recognition in capsule endoscopy images by texture features. In: 7th World Congress on Intelligent Control and Automation, WCICA 2008, June 2008, pp. 234–239 (2008)Google Scholar
- 13.Szczypinski, P.: (2009), http://www.eletel.p.lodz.pl/MaZda (Visited: April 2009)
- 14.Nalbantov, G., Groenen, P., Bioch, J.: Nearest convex hull classification. Econometric Institute Report EI 2006-50 Revision_Date: Erasmus University Rotterdam, Econometric Institute (January 2007)Google Scholar