Title :
A new approach to 3D form recognition within video capsule endoscopic
Author :
Ayoub, Jad ; Granado, Bertrand ; Romain, Olivier ; Mohanna, Yasser
Author_Institution :
ENSEA, ETIS, Univ. de Cergy Pontoise, Cergy, France
Abstract :
This paper describes a novel approach to capsular endoscopy that takes advantage of existing wireless capsule endoscopy (WCE) and overcomes some of its important limits. The basic and essential task concerning the integration of SVM classifier is listed and discussed in details, as well as the new features required to improve its diagnostic capability. In addition, a large scale demonstrator has been evaluated and tested. In vitro experimental results were encouraging and show correct classification rate of intestinal polyps of approximately 93.7%. The work contains detailed statistics about the detection rate and the computing complexity.
Keywords :
computational complexity; endoscopes; feature extraction; image classification; image reconstruction; medical image processing; support vector machines; 3D form recognition; 3D reconstruction; SVM classifier; computing complexity; diagnostic capability; intestinal polyps; video capsule endoscopic; wireless capsule endoscopy; Cancer; Feature extraction; Kernel; Sensitivity; Support vector machines; Three dimensional displays; Vectors; 3D endoscopy; 3D reconstruction; Active stereovision; Support vector machines; feature selection; form recognition; polyps classification;
Conference_Titel :
Design and Architectures for Signal and Image Processing (DASIP), 2011 Conference on
Conference_Location :
Tampere
Print_ISBN :
978-1-4577-0620-2
Electronic_ISBN :
978-1-4577-0619-6
DOI :
10.1109/DASIP.2011.6136872
