Coupled Discriminative Feature Learning for Heterogeneous Face Recognition
- 9 January 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 10 (3), 640-652
- https://doi.org/10.1109/tifs.2015.2390414
Abstract
This paper presents a coupled discriminative feature learning (CDFL) method for heterogeneous face recognition (HFR). Different from most existing HFR approaches which use hand-crafted feature descriptors for face representation, our CDFL directly learns discriminative features from raw pixels for face representation. In particular, a couple of image filters is learned in CDFL to simultaneously exploit discriminative information and to reduce the appearance difference of face images captured across different modalities. With the help of the learned filters, CDFL can maximize the interclass variations and minimize the intraclass variations of the learned feature vectors, and meanwhile maximize the correlation of face images of the same person from different modalities by solving a generalized eigenvalue problem. Experimental results on three different heterogeneous face recognition applications show the effectiveness of our proposed approach.Keywords
Funding Information
- National Program on Key Basic Research Project (973 Program, Project 2012CB316304)
- National Natural Science Foundation of China (61403024, 61471032, 61472030, 61272355)
- Doctoral Foundation of China Ministry of Education (20120009120009)
- research grant for the Human Centric Cyber Systems (HCCS) Program at the Advanced Digital Sciences Center (ADSC) from the Agency for Science, Technology and Research (A*STAR) of Singapore
This publication has 32 references indexed in Scilit:
- Learning Discriminant Face DescriptorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Robust Kernel Representation With Statistical Local Features for Face RecognitionIEEE Transactions on Neural Networks and Learning Systems, 2013
- Fast multi-scale local phase quantization histogram for face recognitionPattern Recognition Letters, 2012
- A new method of feature fusion and its application in image recognitionPattern Recognition, 2005
- Canonical Correlation Analysis: An Overview with Application to Learning MethodsNeural Computation, 2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Face Sketch RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2004
- The FERET evaluation methodology for face-recognition algorithmsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- RELATIONS BETWEEN TWO SETS OF VARIATESBiometrika, 1936