Please use this identifier to cite or link to this item:
|Title:||Joint Feature Learning for Face Recognition||Authors:||Lu, Jiwen
Liong, Venice Erin
|Issue Date:||2015||Source:||Lu, J., Liong, V. E., Wang, G., & Moulin, P. (2015). Joint Feature Learning for Face Recognition. IEEE Transactions on Information Forensics and Security, 10(7), 1371-1383.||Series/Report no.:||IEEE Transactions on Information Forensics and Security||Abstract:||This paper presents a new joint feature learning (JFL) approach to automatically learn feature representation from raw pixels for face recognition. Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for face representation, we propose an unsupervised feature learning method to learn hierarchical feature representation. Since different face regions have different physical characteristics, we propose to use different feature dictionaries to represent them, and to learn multiple yet related feature projection matrices for these regions simultaneously. Hence position-specific discriminative information can be exploited for face representation. Having learned these feature projections for different face regions, we perform spatial pooling for face patches within each region to enhance the representative power of the learned features. Moreover, we stack our JFL model into a deep architecture to exploit hierarchical information for feature representation and further improve the recognition performance. Experimental results on five widely used face data sets show the effectiveness of our proposed approach.||URI:||https://hdl.handle.net/10356/81670
|ISSN:||1556-6013||DOI:||10.1109/TIFS.2015.2408431||Rights:||© 2015 IEEE.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||EEE Journal Articles|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.