How Low Can You Go? Low Resolution Face Recognition Study Using Kernel Correlation Feature Analysis on the FRGCv2 dataset

Abstract

In this paper we investigate the effect of image resolution of the face recognition grand challenge (FRGC) dataset on the kernel class-dependence feature analysis (KCFA) method. Good performance on low-resolution image data is important for any face recognition system using low- resolution imagery, such as in surveillance footage. We show that KCFA works reliably even at very low resolutions on the FRGC dataset Experiment 4 using the one-to-one matching protocol (greater than 70% verification rate (VR) at 0.1% false accept rate (FAR)). We observe reasonable performance at resolution as low as 16x16. However performance of KCFA degrades significantly below this resolution, but still outperforms the PCA baseline algorithm with 12% VR at 0.1% FAR.