UCDCN: a nested architecture based on central difference convolution for face anti-spoofing

Jing Zhang

doi:10.1007/s40747-024-01397-0

UCDCN: a nested architecture based on central difference convolution for face anti-spoofing

2024-04-09

1

OA

AI

DOI：10.1007/s40747-024-01397-0

Original

Original request for help

Save

Abstract

En 中文

The significance of facial anti-spoofing algorithms in enhancing the security of facial recognition systems cannot be overstated. Current approaches aim to compensate for the model's shortcomings in capturing spatial information by leveraging spatio-temporal information from multiple frames. However, the additional branches to extract inter-frame details increases the model's parameter count and computational workload, leading to a decrease in inference efficiency. To address this, we have developed a robust and easily deployable facial anti-spoofing algorithm. In this paper, we propose Central Difference Convolution UNet++ (UCDCN), which takes advantage of central difference convolution and improves the characterization ability of invariant details in diverse environments. Particularly, we leverage domain knowledge from image segmentation and propose a multi-level feature fusion network structure to enhance the model's ability to capture semantic information which is beneficial for face anti-spoofing tasks. In this manner, UCDCN greatly reduces the number of model parameters as well as achieves satisfactory metrics on three popular benchmarks, i.e., Replay-Attack, Oulu-NPU and SiW.

Keywords:

Face anti-spoofing

Semantic information

Easy-to-deploy

Efficiency

UCDCN: a nested architecture based on central difference convolution for face anti-spoofing

Abstract

Journal

Organization