Aug 2026· International Conference on Computing Communication Control and automation· pp. 1-7· 0 citations· 13 references
Abstract
Face anti-spoofing (FAS) is vital for safeguarding biometric systems against presentation attacks, including photos, videos, or masks aimed at impersonating legitimate users. This paper presents an efficient multi-modal face liveness detection method that combines RGB, depth, and infrared (IR) images through a lightweight convolutional neural network. To find the right balance between security and usability, this paper introduces a new evaluation metric, Conditional Average Metric (CAM), which averages sensitivity and specificity. Our model achieves 94.46% accuracy, an F1-score of 0.908, and a CAM of 0.932 on the CASIA-SURF dataset, using only 81,857 parameters and allowing real-time inference on edge devices. Compared to traditional methods based on RGB color only, our model gains an improvement in F1-score by 0.432, representing a 90.8% improvement, and demonstrates strong generalization. The results indicate that multimodal fusion and the CAM metric provide effective solutions for the problem of face liveness detection in real-world scenarios.
A multi-dimensional feature fusion-based face anti-spoofing detection method based on the YOLOv8 architecture that integrates dynamic optical flow features with static texture analysis and achieves robust detection through the fusion of spatial and temporal cues.
Yanhua Liang, Pengcheng Zhou, Hongmei Qin et al.· International Conference on...· 0 citations
Biometric face recognition systems are progressively being used in security-sensitive areas and are vulnerable to presentation attacks (PAs) such as printed photograph recaptures, video replay attacks and 3D silicone mask attacks. Face Anti-Spoofing (FAS) also known as liveness detection is the first line of defence ag...
Shivakumar Dalali· Natural Resources for Human...· 0 citations
The results show that clean-set performance is not a reliable indicator of robustness under compression, resizing, and blurring, and reinforce the need for degraded evaluation protocols and highlight self-supervised visual representations as a promising direction for robust face forgery detection.
L. Cunha, Lucas Sotomaior, Lucas Gasperin et al.· 0 citations
Face recognition is widely used for biometric authentication in applications such as mobile devices, financial services, intelligent surveillance, access control, and border security. However, face recognition systems remain vulnerable to presentation attacks, including printed photographs, replay attacks, and three-di...
Mudunuru Suneel, Banothu Yedukondala Venkata Naga Raja Swamy, Madhava Rao Maganti et al.· International Journal of Eng...· 0 citations
The novelty of this work lies in the integration of a lightweight CNN-LSTM framework with LDA to achieve a balance between high recognition accuracy and computational efficiency, making it suitable for real-time facial authentication in edge and IoT environments.
Automated forgery detection has become a significant issue in image-forensics due to the
increasing realism of digitally altered or artificially created facial photographs. In order to
classify facial photos as either real or fake, a convolutional neural network (CNN) was created
and put through experimental testing...
Samaila Ahmed· International Journal of Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
