얼굴과 의복 정보를 활용한 딥러닝 기반 신원인식
홍성은, 임우빈, 박준우 et al. · 대한전자공학회 학술대회 · 2016
The key challenge of face recognition is to extract feature description which is robust to pose, illumination, and identity. In this paper, we show that it can be well solved with Convolutional Neural Network (CNN) and using both face and clothing regions. We also introduce a powerful CNN based face region verification scheme to reduce a lot of false positive face regions. Experimental results demonstrate the superiority of our CNN based method for face detection and person identification. The proposed method also yields outstanding results compared to the previous approaches.
Cited by 0 works.