Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples

Abstract

This paper addresses the problem of face recognition when there is only few, or even only a single, labeled examples of the face that we wish to recognize. Moreover, these examples are typically corrupted by nuisance variables, both linear (i.e., additive nuisance variables such as bad lighting, wearing of glasses) and non-linear (i.e., non-additive pixel-wise nuisance variables such as expression changes). The small number of labeled examples means that it is hard to remove these nuisance variables between the training and testing faces to obtain good recognition performance. To address the problem we propose a method called Semi-Supervised Sparse Representation based Classification (S${}^3$RC). This is based on recent work on sparsity where faces are represented in terms of two dictionaries: a gallery dictionary consisting of one or more examples of each person, and a variation dictionary representing linear nuisance variables (e.g., different lighting conditions, different glasses). The main idea is that (i) we use the variation dictionary to characterize the linear nuisance variables via the sparsity framework, then (ii) prototype face images are estimated as a gallery dictionary via a Gaussian Mixture Model (GMM), with mixed labeled and unlabeled samples in a semi-supervised manner, to deal with the non-linear nuisance variations between labeled and unlabeled samples. We have done experiments with insufficient labeled samples, even when there is only a single labeled sample per person. Our results on the AR, Multi-PIE, CAS-PEAL, and LFW databases demonstrate that the proposed method is able to deliver significantly improved performance over existing methods.

To appear in IEEE Transactions on Image Processing, 2017

References in corpus (2)

• Deep Learning Face Representation by Joint Identification-Verification
• Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation from Single and Multiple Images

Cited by in corpus (12)

• SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery
• Hyperspectral Image Classification in the Presence of Noisy Labels
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
• Domain-Specific Face Synthesis for Video Face Recognition from a Single Sample Per Person
• Pseudo-Zernike Moments Based Sparse Representations for SAR Image Classification
• Asymmetric Rejection Loss for Fairer Face Recognition
• Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
• Facial Feature Embedded CycleGAN for VIS-NIR Translation
• ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset
• Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
• Hyperspectral Image Classification Based on Adaptive Sparse Deep Network