TY - GEN
T1 - Robust heterogeneous discriminative analysis for single sample per person face recognition
AU - Pang, Meng
AU - CHEUNG, Yiu Ming
AU - Wang, Binghui
AU - Liu, Risheng
N1 - Funding Information:
This work was supported in part by NSFC (Nos. 61272366, 61672444, 61672125, 61300086, 61572096, 61432003 and 61632019), by the Faculty Research Grant (No. FRG2/16-17/051) and KTO Grant (No. MPCF-004-2017/18) of HKBU, and by the SZSTI Grant (No. JCYJ20160531194006833).
PY - 2017/11/6
Y1 - 2017/11/6
N2 - Single sample face recognition is one of the most challenging problems in face recognition (FR), where only one single sample per person (SSPP) is enrolled in the gallery set for training. Although patch-based methods have achieved great success in FR with SSPP, they still have significant limita-tions. In this work, we propose a new patch-based method, namely Robust Heterogeneous Discriminative Analysis (RH-DA), to tackle FR with SSPP. Compared with the existing patch-based methods, RHDA can enhance the robustness against complex facial variations from two aspects. First, we develop a novel Fisher-like criterion, which incorporates two manifold embeddings, to learn heterogeneous discriminative representations of image patches. Specifically, for each patch, the Fisher-like criterion is able to preserve the reconstruction relationship of neighboring patches from the same person, while suppressing neighboring patches from different persons. Second, we present two distance metrics, i.e., patch-to-patch distance and patch-to-manifold distance, and develop a fusion strategy to combine the recognition outputs of above two distance metrics via joint majority voting for identification. Experimental results on the AR and FERET benchmark datasets demonstrate the efficacy of the proposed method.
AB - Single sample face recognition is one of the most challenging problems in face recognition (FR), where only one single sample per person (SSPP) is enrolled in the gallery set for training. Although patch-based methods have achieved great success in FR with SSPP, they still have significant limita-tions. In this work, we propose a new patch-based method, namely Robust Heterogeneous Discriminative Analysis (RH-DA), to tackle FR with SSPP. Compared with the existing patch-based methods, RHDA can enhance the robustness against complex facial variations from two aspects. First, we develop a novel Fisher-like criterion, which incorporates two manifold embeddings, to learn heterogeneous discriminative representations of image patches. Specifically, for each patch, the Fisher-like criterion is able to preserve the reconstruction relationship of neighboring patches from the same person, while suppressing neighboring patches from different persons. Second, we present two distance metrics, i.e., patch-to-patch distance and patch-to-manifold distance, and develop a fusion strategy to combine the recognition outputs of above two distance metrics via joint majority voting for identification. Experimental results on the AR and FERET benchmark datasets demonstrate the efficacy of the proposed method.
KW - Het-erogeneous subspace analysis
KW - Joint majority voting.
KW - Representation learning
KW - Single sample face recognition
UR - http://www.scopus.com/inward/record.url?scp=85037356168&partnerID=8YFLogxK
U2 - 10.1145/3132847.3133096
DO - 10.1145/3132847.3133096
M3 - Conference proceeding
AN - SCOPUS:85037356168
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 2251
EP - 2254
BT - CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
PB - Association for Computing Machinery (ACM)
T2 - 26th ACM International Conference on Information and Knowledge Management, CIKM 2017
Y2 - 6 November 2017 through 10 November 2017
ER -