A novel network model based ICA filter for face recognition

Abstract

Despite the great success of deep learning convolution networks, researchers are not yet clear about its feature learning mechanism and optimal network configuration. In this paper, we present a cascaded linear convolution network based on ICA filters, termed ICANet. ICANet mainly includes three parts: convolution layer, binary hash and block histogram. The results show that ICANet has a very good performance in face recognition tasks.