Face recognition based on weighted multi-channel Gabor sparse representation and optimized extreme learning machines
Wenbo Zheng, Xin Jin, Fei Deng, Shaocong Mo, Yili Qu, Zeyu Fan, Jiangwei Zhou, Rui Zou, Jia Shuai, Zefeng Xie · 2017
Very recently, the sparse representation theory in pattern recognition arouses widespread concern. In this paper, the sparse representation-based face recognition algorithms are studied. In order to make the representation coefficient vector sparser, a face recognition algorithm based on weighted multichannel Gabor sparse representation and optimized extreme learning machines is presented, which uses the Gabor local feature to construct dictionary to enhance the robustness for the external environment changes. By introducing the Gabor multi-channel model, our algorithm extracts Gabor features in different channels to construct dictionaries and sparse representation classifiers, and obtains the final classification result by performing the weighting fusion of classifiers which is the results of the optimized extreme learning machines based on parallel ant colony algorithm. Experimental results given in the paper on the ORL and AR face databases show the feasibility and effectiveness of the proposed methods.