3-D object recognition based on SVM and stereo-vision: Application in endoscopic imaging
Résumé
In this paper we focus on the recognition of threedimensional objects captured by an active stereo vision sensor. The study is related to our research project Cyclope, this embedded sensor based on active stereo-vision approach allows real time 3D objects reconstruction. Our medical application requires differentiation between hyperplastic and adenomatous polyps during 3D endoscopic imaging. The detection algorithm consists of SVM classifier trained on robust feature descriptors of a surfacic 3D point cloud extracted from the surface of studied object. We compared our feature extraction method with others. Experimental results were encouraging and show correct classification rate of approximately 97%. The work contains many techniques concerning image processing and system calibration and provides detailed statistics about the detection rate and the computing complexity.