Fused Classification For Differential Face Morphing Detection
This work addresses security risks in face recognition systems by improving detection of sophisticated morphing attacks, though it appears incremental as it builds on existing differential detection approaches.
The paper tackles the problem of detecting face morphing attacks, which blend multiple face images to deceive face recognition systems, by proposing a fused classification method for differential detection in a no-reference scenario, and introduces a public benchmark for this scenario.
Face morphing, a sophisticated presentation attack technique, poses significant security risks to face recognition systems. Traditional methods struggle to detect morphing attacks, which involve blending multiple face images to create a synthetic image that can match different individuals. In this paper, we focus on the differential detection of face morphing and propose an extended approach based on fused classification method for no-reference scenario. We introduce a public face morphing detection benchmark for the differential scenario and utilize a specific data mining technique to enhance the performance of our approach. Experimental results demonstrate the effectiveness of our method in detecting morphing attacks.