WestminsterResearch will not be accepting deposits until 9th March 2015. This is to allow for a system upgrade and server migration.

Neural network-based approach for the classification of wireless-capsule endoscopic images

Kodogiannis, Vassilis and Boulougoura, Maria (2005) Neural network-based approach for the classification of wireless-capsule endoscopic images. In: 2005 IEEE International Joint Conference on Neural Networks (IJCNN). IEEE Computer Society, USA, pp. 2423-2428. ISBN 0780390482


Official URL: http://dx.doi.org/10.1109/IJCNN.2005.1556282


The importance of computer-assisted diagnosis in endoscopy is to assist the physician in detecting the status of tissues by characterising the features from the endoscopic image. In this paper schemes have been developed to extract new texture features from the texture spectra in the chromatic and achromatic domains for a selected region of interest from each colour component histogram of images acquired by the new M2A Swallowable Imaging Capsule. The concept of fusion of multiple classifiers dedicated to specific feature parameters and the implementation of an advanced intelligent scheme have been also adopted in this study. The high detection accuracy of the proposed systems provides thus an indication that such intelligent schemes could be used as a supplementary diagnostic tool in capsule endoscopy.

Item Type:Book Section
Research Community:University of Westminster > Electronics and Computer Science, School of
ID Code:2186
Deposited On:26 Jun 2006
Last Modified:11 Aug 2010 15:30

Repository Staff Only: item control page