1 We address the problem of vector-valued image regularization with variational methods and PDE's. From the study of existing formalisms, we propose a unifying framework base...
The problem of dense optical flow computation is addressed from a variational viewpoint. A new geometric framework is introduced. It unifies previous art and yields new efficient ...
In this paper we propose an approach to vehicle classification under a mid-field surveillance framework. We develop a repeatable and discriminative feature based on edge points an...
This article proposes a new framework to regularize linear inverse problems using the total variation on non-local graphs. This nonlocal graph allows to adapt the penalization to t...
To achieve a face recognition system robust to the presence of glasses, we have developped a glasses detection and extraction algorithm. Detection is realized using edge informati...