A Maximum Correlation Feature Descriptor for Heterogeneous Face Recognition

Abstract

Heterogeneous Face Recognition (HFR) refers to matching probe face images to a gallery of face images taken from alternate imaging modality, for example matching near infrared (NIR) face images to photographs. Matching heterogeneous face images has important practical applications such as surveillance and forensics, which is yet a challenging problem in face recognition community due to the large within-class discrepancy incurred from modality differences. In this paper, a novel feature descriptor is proposed in which the features of both gallery and probe face images are extracted with an adaptive feature descriptor which can maximize the correlation of the encoded face images between the modalities, so as to reduce the within-class variations at the feature extraction stage. The effectiveness of the proposed approach is demonstrated on the scenario of matching NIR face images to photographs based on a very large dataset consists of 2800 different persons.