融合可见光与热成像边缘信息，提升活体检测准确性
Face Liveness Detection Using RGB and Thermal Image Fusion
- 用可见光与热成像的边缘信息进行多模态融合
- 在ARISTOF数据集上，热成像检测准确率显著提升
- 适合安防、金融等需高鲁棒性活体验证的场景
基于可见光摄像头的人脸检测易被照片、面具或雕像等欺骗。以往依赖纹理、运动或生理信号的方法受光照影响大，对攻击手段鲁棒性差。热成像通过检测体温可自然排除伪造人脸。本研究提出一种混合方法，将可见光图像的边缘信息与对应热成像融合，使用自建的ARISTOF数据集（含真实与伪造人脸）。首先用YOLOv8-Face模型对比评估RGB、热成像及融合模态的检测性能，结果显示融合后热成像检测精度提升。随后以融合图像训练YOLOv8-Face模型进行活体/非活体分类，证明该多模态融合策略能有效支持鲁棒的人脸活体检测。
原文摘要 · Abstract (English)
Face detection with visible-spectrum cameras can capture facial features, but it often fails to distinguish live subjects from spoof sources such as photographs, masks, or statues. Previous approaches based on texture, motion, or physiological cues are sensitive to illumination changes and show limited robustness against spoofing attacks. Thermal imaging helps overcome these limitations by detecting heat emissions, naturally excluding spoof faces. This study proposes a hybrid approach that fuses the edge information of RGB images with corresponding thermal images using a custom ARISTOF dataset containing live and spoof faces. The fused images are first evaluated using the YOLOv8-Face model to compare face detection performance across RGB, thermal, and fused modalities. The results show that the proposed method enhances the face detection accuracy of thermal images. The fused images are subsequently used to train a YOLOv8-Face model for live and spoof classification, demonstrating that the proposed multimodal fusion effectively supports robust face liveness detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。