Cooperative Face Liveness Detection from Optical Flow

TL;DR

This paper introduces a novel cooperative face liveness detection method that uses controlled face movement and optical flow analysis to improve accuracy in distinguishing real faces from presentation attacks.

Contribution

It presents a new user interaction protocol combined with optical flow analysis and neural classification for enhanced face liveness detection.

Findings

Robust discrimination between genuine and fake faces achieved.

Effective detection across various attack types including masks and replays.

Improved reliability over passive detection methods.

Abstract

In this work, we proposed a novel cooperative video-based face liveness detection method based on a new user interaction scenario where participants are instructed to slowly move their frontal-oriented face closer to the camera. This controlled approaching face protocol, combined with optical flow analysis, represents the core innovation of our approach. By designing a system where users follow this specific movement pattern, we enable robust extraction of facial volume information through neural optical flow estimation, significantly improving discrimination between genuine faces and various presentation attacks (including printed photos, screen displays, masks, and video replays). Our method processes both the predicted optical flows and RGB frames through a neural classifier, effectively leveraging spatial-temporal features for more reliable liveness detection compared to passive methods.