Deep texture-depth-based attention for face recognition on IoT devices

Traditional face recognition systems use RGB images as input for feature extraction and classification. However, conventional methods based on color images experience non-trivial accuracy drop under several challenging conditions like occlusion, pose variation and facial expression changes. With the...

Повний опис

Бібліографічні деталі
Автори: Lin, Yuxin, Liu, Wenye, Chang, Chip Hong
Інші автори: School of Electrical and Electronic Engineering
Формат: Conference Paper
Мова:English
Опубліковано: 2024
Предмети:
Онлайн доступ:https://hdl.handle.net/10356/174142