We investigate in this paper the combination of DBN (Dynamic Bayesian Network) classifiers, either independent or coupled, for the recognition of degraded characters. The independ...
This paper proposes a simple voting scheme for off-line recognition of handprinted numerals. One of the main features of the proposed scheme is that this is not script dependent. ...
Translucent objects pose a difficult problem for traditional structured light 3D scanning techniques. Subsurface scattering corrupts the range estimation in two ways: by drastical...
Tongbo Chen, Hendrik P. A. Lensch, Christian Fuchs...
This paper proposes a novel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geo...
We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized corre...