We study the question of feature sets for robust visual object recognition, adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient ba...
Abstract Compressed domain image retrieval is going to play an increasingly important role in the future. It allows the calculation of image features and hence content-based image ...
Edge-based and region-based active contours are frequently used in image segmentation. While edges characterize small neighborhoods of pixels, region descriptors characterize entir...
Cristina Darolti, Alfred Mertins, Christoph Bodens...
A fast and robust 3D retrieval method is proposed based on a novel weighted structural histogram representation. Our method has the following steps: 1) adaptively segment any 3D sh...
Abstract. In this paper, we describe an approach for the automatic modality classification in medical image retrieval task of the 2010 CLEF cross-language image retrieval campaign ...