Super-Resolution Method for Face Recognition Using Nonlinear Mappings on Coherent Features

Abstract

Low-resolution (LR) of face images significantly decreases the performance of face recognition. To address this problem, we present a super-resolution method that uses nonlinear mappings to infer coherent features that favor higher recognition of the nearest neighbor (NN) classifiers for recognition of single LR face image. Canonical correlation analysis is applied to establish the coherent subspaces between the principal component analysis (PCA) based features of high-resolution (HR) and LR face images. Then, a nonlinear mapping between HR/LR features can be built by radial basis functions (RBFs) with lower regression errors in the coherent feature space than in the PCA feature space. Thus, we can compute super-resolved coherent features corresponding to an input LR image according to the trained RBF model efficiently and accurately. And, face identity can be obtained by feeding these super-resolved features to a simple NN classifier. Extensive experiments on the Facial Recognition Technology, University of Manchester Institute of Science and Technology, and Olivetti Research Laboratory databases show that the proposed method outperforms the state-of-the-art face recognition algorithms for single LR image in terms of both recognition rate and robustness to facial variations of pose and expression.

People Identification and Tracking Through Fusion of Facial and Gait Features

“…There are two directions to handle the problem of low resolution. 1) super-resolution (SR) based methods [24], [38], [27], [28], [32], which reconstruct high-resolution images from low resolution images for visual enhancement. After applying SR, a higher resolution image can be obtained and used for recognition.…”

A Novel Algorithm for Human Facial Expression Recognition using Gabor Filter and Eigenvector

“…Jun OuXiao-Bo Bai Yun Pei, Liang Ma, Wei Liu [8] presented a system that used 28 facial feature key-points in images detection and Gabor wavelet filter provided with five different frequencies and eight orientations at different angles. On the basis of actual demand, it was capable to extract the feature of low quality facial feature image target, having powerful automatic facial expression recognition.…”

A Novel Super-resolution Approach Based on Supervised Canonical Correlation Analysis

“…HR face image and its corresponding LR face image have the similarity intrinsic geometries, and in coherent subspaces, they have the statistical correlation. Huang Hua [6,7] proposes superresolution methods of face image using CCA and RBF. Yueting Zhuang [8] proposes LPH super-resolution and neighbor reconstruction for residue compensation.…”