Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection

TL;DR

This paper introduces a novel face liveness detection method combining anisotropic diffusion, kernel matrix features, and deep learning to effectively prevent spoofing attacks, outperforming existing techniques.

Contribution

It proposes an integrated approach using anisotropic diffusion, kernel matrix features, and deep neural networks with multiple kernel learning for improved face liveness detection.

Findings

Outperforms state-of-the-art face liveness detection methods

Effective in enhancing face image features for spoofing detection

Demonstrates robustness across publicly available datasets

Abstract

Facial recognition and verification is a widely used biometric technology in security system. Unfortunately, face biometrics is vulnerable to spoofing attacks using photographs or videos. In this paper, we present an anisotropic diffusion-based kernel matrix model (ADKMM) for face liveness detection to prevent face spoofing attacks. We use the anisotropic diffusion to enhance the edges and boundary locations of a face image, and the kernel matrix model to extract face image features which we call the diffusion-kernel (D-K) features. The D-K features reflect the inner correlation of the face image sequence. We introduce convolution neural networks to extract the deep features, and then, employ a generalized multiple kernel learning method to fuse the D-K features and the deep features to achieve better performance. Our experimental evaluation on the two publicly available datasets shows that the proposed method outperforms the state-of-art face liveness detection methods.