Deep Feature Encoding for Age-invariant Face Recognition

Abstract

Facial aging variation is a major problem for face recognition systems, due to large intra-personal variations caused by age progression. A major challenge is to develop an efficient, discriminative feature representation and matching framework, which is robust to facial aging variations. In this talk, we will present a robust deep-feature encoding-based discriminative model for age-invariant face recognition. Our method learns high-level deep features using a pretrained deep-CNN model. These features are then encoded by learning a codebook with S codewords or atoms, which converts each of the features into a discriminant S-dimensional codeword for image representation. By incorporating the locality information in the whole learning process, a closed-form solution is obtained for both the codebook-updating and encoding stages. Furthermore, as the features of the same person at different ages should have certain correlations, canonical correlation analysis is utilized to fuse the pair of training features from the same person, but at two different ages, to make the codebook discriminative in terms of age progression. In the testing stage, the gallery and query image’s features are encoded using the learned codebook. Then, linear mapping based on linear regression is employed for face matching. We will present the performance of the method on three publicly available challenging facial aging datasets, FGNET, MORPH Album 2, and Large Age-Gap.

Biography

Prof. Kin-Man Lam received his Associateship in Electronic Engineering with distinction from the Hong Kong Polytechnic University (formerly called Hong Kong Polytechnic) in 1986. He won the S.L. Poa Education Foundation Scholarship for overseas studies and was awarded an M.Sc. degree in communication engineering from the Department of Electrical Engineering, Imperial College of Science, Technology and Medicine, England, in 1987. In August 1993, he undertook a Ph.D. degree program in the Department of Electrical Engineering at the University of Sydney, Australia, and won an Australia Postgraduate Award for his studies. He completed his Ph.D. studies in August 1996, and was awarded the IBM Australia Research Student Project Prize.

Prof. Lam joined the Department of Electronic and Information Engineering, The Hong Kong Polytechnic University as an Assistant Professor in October 1996. He became an Associate Professor in 1999, and has been a Professor since 2010. Currently, he is also an Associate Dean of the Faculty of Engineering. He was actively involved in professional activities. He has been a member of the organizing committee or program committee of many international conferences. In particular, he was the Technical Chair of the 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing (ISIMP 2004), a Technical Co-Chair of the 2005 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2005) and 2010 Pacific-Rim Conference on Multimedia (PCM 2010), and a General Co-Chair of the 2012 IEEE International Conference on Signal Processing, Communications, & Computing (ICSPCC 2012), the APSIPA Annual and Summit 2015 (APSIPA ASC 2015), and the 2017 IEEE International Conference on Multimedia and Expo (ICME 2017), which were held in Hong Kong in August 2012, December 2015, and July 2017. Prof. Lam was the Chairman of the IEEE Hong Kong Chapter of Signal Processing between 2006 and 2008. He received an Honorable Mention of the Annual Pattern Recognition Society Award for an outstanding contribution to the Pattern Recognition Journal in 2004.

Prof. Lam was the Director-Student Services and the Director-Membership Services of the IEEE Signal Processing Society between 2012 and 2014, and between 2015 and 2017, respectively. He was an Associate Editor of IEEE Trans. on Image Processing between 2009 and 2014, an Associate Editor of Digital Signal Processing between 2014 and 2018, an Editor of HKIE Transactions between 2013 and 2018, and an Area Editor of the IEEE Signal Processing Magazine between 2015 and 2017. Currently, he is the VP-Publications of the Asia-Pacific Signal and Information Processing Association (APSIPA). Prof. Lam serves as an Associate Editor of APSIPA Trans. on Signal and Information Processing and EURASIP International Journal on Image and Video Processing. His current research interests include human face recognition, image and video processing, and computer vision.