The paper presents a novel approach for searching a very large image database employing frame sliced parallel signature file. Signature files have been proposed and used for retri...
This paper presents a search engine architecture, RETIN, aiming at retrieving complex categories in large image databases. For indexing, a scheme based on a two-step quantization ...
Philippe Henri Gosselin, Matthieu Cord, Sylvie Phi...
In this paper, we study how to build a vision-based system for global localization with accuracies within 10cm. for robots and humans operating both indoors and outdoors over wide...
We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley Segment...
We have proposed a complete system for text detection and localization in gray scale scene images. A boosting framework integrating feature and weak classifier selection based on...