Free training object detection based on multi-stage fusion using belief functions
Mariem Farhat, Slim Mhiri, Moncef Tagina · 2016
Many of object detection methods are based on training phase. Theses methods are constrained to a known object. In this paper, we present a free training method for object detection that can deal with large viewpoint change. We exploit Dempster theory to combine between multiple descriptors in a multi stage method. To show the effectiveness of the technique, we apply it on multiple images from Coil100 database. Compared to existing methods, our method has proved to be more generic and more efficient.