In this paper, we propose a novel occlusion invariant face recognition algorithm based on Selective Local Nonnegative Matrix Factorization (S-LNMF) technique. The proposed algorith...
Hyun Jun Oh, Kyoung Mu Lee, Sang Uk Lee, Chung-Hyu...
In order for a subspace projection based method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local r...
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3...
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constel...