Sparse representation-based classification (SRC) has become one of the most powerful methods for robust face recognition. However, there are some limitations of SRC performance at the presence of noise, occlusion, and illumination variation problems, which make it unstable. Therefore, we investigate the performance of SRC under different data conditions by applying the most powerful optimization methods based on SRC and focusing on the corrections between data samples and the sparseness. For evaluation, we utilize several challenging face datasets that include diversity of illumination and occlusion conditions.
Sparse representation based classification performance under different optimization forms for face recognition
2017-06-01
448157 byte
Conference paper
Electronic Resource
English
Robust face recognition via low-rank sparse representation-based classification
British Library Online Contents | 2015
|Robust face recognition via gradient-based sparse representation
British Library Online Contents | 2013
|Two-stage sparse representation-based face recognition with reconstructed images
British Library Online Contents | 2014
|Robust face recognition using sparse representation in LDA space
British Library Online Contents | 2015
|Modified Local Binary Pattern for Human Face Recognition Based on Sparse Representation
British Library Online Contents | 2014
|