Discriminative Multimanifold Analysis for Face Recognition from a Single Training Sample per Person

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 35; no. 1; pp. 39 - 51
• Main Authors: Lu, Jiwen, Tan, Yap-Peng, Wang, Gang
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.01.2013; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Biometrics; Biometry - methods; Computer science; control theory; systems; Data processing. List processing. Character string processing; Discriminant Analysis; Educational institutions; Effectiveness; Exact sciences and technology; Face; Face - anatomy & histology; Face recognition; Feature extraction; Humans; Image Interpretation, Computer-Assisted - methods; Intelligence; Learning; Learning and adaptive systems; manifold learning; Manifolds; Memory organisation. Data processing; Pattern analysis; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Sample Size; Semantics; Signal Processing, Computer-Assisted; single training sample per person; Software; subspace learning; Subtraction Technique; Training; single training sample per person; Computer vision; Discriminant analysis; Image processing; Face recognition; Image databank; Subspace method; manifold learning; subspace learning; Dimension reduction; Image analysis; Experimental result; Multidimensional analysis; Official document; Facies; Selection criterion; Feature extraction; Reduced order model; Pattern extraction; Electronic government
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2012.70

Conventional appearance-based face recognition methods usually assume that there are multiple samples per person (MSPP) available for discriminative feature extraction during the training phase. In many practical face recognition applications such as law enhancement, e-passport, and ID card identification, this assumption, however, may not hold as there is only a single sample per person (SSPP) enrolled or recorded in these systems. Many popular face recognition methods fail to work well in this scenario because there are not enough samples for discriminant learning. To address this problem, we propose in this paper a novel discriminative multimanifold analysis (DMMA) method by learning discriminative features from image patches. First, we partition each enrolled face image into several nonoverlapping patches to form an image set for each sample per person. Then, we formulate the SSPP face recognition as a manifold-manifold matching problem and learn multiple DMMA feature spaces to maximize the manifold margins of different persons. Finally, we present a reconstruction-based manifold-manifold distance to identify the unlabeled subjects. Experimental results on three widely used face databases are presented to demonstrate the efficacy of the proposed approach.