Recognizing Very Small Face Images Using Convolution Neural Networks

• Published in: IEEE transactions on intelligent transportation systems Vol. 23; no. 3; pp. 2103 - 2115
• Main Authors: Horng, Shi-Jinn, Supardi, Julian, Zhou, Wanlei, Lin, Chin-Teng, Jiang, Bin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-03-2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Access control; Artificial neural networks; Cameras; Convolution; convolution neural networks; Face recognition; Feature extraction; Image enhancement; Image recognition; Image reconstruction; low resolution; Neural networks; Object recognition; residual learning; super-resolution; Surveillance; Tracking control; Very low resolution
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2020.3032396

Face recognition can be installed in a surveillance system so that it can be used for monitoring, tracking and access control. An excellent, intelligent surveillance system should be sensitive to the objects far away from the camera. Unfortunately, due to the long-distance, objects like human faces captured by the camera are too small to identify. As to enhance the subtle color differences in the face image, in this paper we first improve the resolution of the captured image using deep convolution neural networks (DCNNs). Then the efficient features are extracted and used to do classification. As for verifying the effectiveness of the proposed method, we used three databases including AR face database, Georgia Tech face database (GT) database, and Labelled Faces in the Wild (LFW) database, altogether, to conduct the training and testing. Compared to the existing approaches, experimental results show that the identification accuracy of the proposed method outperforms any existing approaches.