We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
In this paper, a new unsupervised hierarchical approach to textured color images segmentation is proposed. To this end, we have designed a two-step procedure based on a grey-scale...
In this paper, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of 3D wate...
A new adaptive multispectral image compression technique based on the regions identified is proposed. The algorithm is adaptive in the sense that according to the data type class ...
In this paper we present a general framework for object detection and segmentation. Using a bottom-up unsupervised merging algorithm, a region-based hierarchy that represents the ...