Kernel Selection using Multiple Kernel Learning and Domain Adaptation in Reproducing Kernel Hilbert Space, for Face Recognition under Surveillance Scenario

TL;DR

This paper introduces a novel kernel selection method combining Multiple Kernel Learning and domain adaptation in RKHS to improve face recognition accuracy in low-resolution surveillance images.

Contribution

It proposes MFKL, a new kernel selection technique that optimally pairs features with kernels using MKL and domain adaptation for surveillance face recognition.

Findings

Outperforms state-of-the-art methods on three surveillance datasets.

Achieves higher Rank-1 recognition accuracy.

Demonstrates effectiveness of combined MKL and domain adaptation approach.

Abstract

Face Recognition (FR) has been the interest to several researchers over the past few decades due to its passive nature of biometric authentication. Despite high accuracy achieved by face recognition algorithms under controlled conditions, achieving the same performance for face images obtained in surveillance scenarios, is a major hurdle. Some attempts have been made to super-resolve the low-resolution face images and improve the contrast, without considerable degree of success. The proposed technique in this paper tries to cope with the very low resolution and low contrast face images obtained from surveillance cameras, for FR under surveillance conditions. For Support Vector Machine classification, the selection of appropriate kernel has been a widely discussed issue in the research community. In this paper, we propose a novel kernel selection technique termed as MFKL (Multi-Feature Kernel Learning) to obtain the best feature-kernel pairing. Our proposed technique employs a effective kernel selection by Multiple Kernel Learning (MKL) method, to choose the optimal kernel to be used along with unsupervised domain adaptation method in the Reproducing Kernel Hilbert Space (RKHS), for a solution to the problem. Rigorous experimentation has been performed on three real-world surveillance face datasets : FR\_SURV, SCface and ChokePoint. Results have been shown using Rank-1 Recognition Accuracy, ROC and CMC measures. Our proposed method outperforms all other recent state-of-the-art techniques by a considerable margin.