Expression Invariant Face Recognition Using Convolutional Neural Networks
Authors: Bhat, F.A. and Wani, M.A.
Journal: 12th Indiacom 5th International Conference on Computing for Sustainable Global Development Indiacom 2018
Pages: 3034-3039
Abstract:From the past several years face recognition is one of the important area of research in computer vision, due to three challenging problems in it i.e. expression problem: in which same person shows more than one expression, illumination problem: in which face images of the person are strongly corrupted by lightning and poses problem: in which large portion of the face becomes invisible due to occlusion. To this end we propose a Deep Convolutional Neural Network architecture which consists of number of layers to overcome these challenging problems in face recognition. General discussion on deep learning is given, brief introduction of various deep architectures are also given. Detailed discussion on convolutional neural network is given. Experimental results on the two benchmark face datasets varying in expression i.e. ORL face data set and Faces94 data set is given. Performance comparison of the proposed approach with other shallow architectures i.e. Independent Component Analysis (ICA), Gabor Wavelet Transform (GWT) Linear Discriminant Analysis (LDA) and Principle Component Analysis are also given.
Source: Scopus