We present a method for sampling feature vectors in large (e.g., 2000 5000 16 bit) images that finds subsets of pixel locations which represent "regions" in the image. Sa...
Load balancing is a critical issue for the efficient operation of peerto-peer networks. We give two new load-balancing protocols whose provable performance guarantees are within a...
Image classification or annotation is proved difficult for the computer algorithms. The Naive-Bayes Nearest Neighbor method is proposed to tackle the problem, and achieved the stat...
Inspired by tensor voting, we present luminance voting, a novel approach for image registration with global and local luminance alignment. The key to our modeless approach is the ...
This paper studies constraint satisfaction over connected row-convex (CRC) constraints. It shows that CRC constraints are closed under composition, intersection, and transposition...
Yves Deville, Olivier Barette, Pascal Van Hentenry...