Accurate and robust face recognition from RGB-D images with a deep learning approach

Yuancheng Lee, Jiancong Chen, Ching Wei Tseng and Shang-Hong Lai

Abstract

Face recognition from RGB-D images utilizes 2 complementary types of image data, i.e. colour and depth images, to achieve more accurate recognition. In this paper, we propose a face recognition system based on deep learning, which can be used to verify and identify a subject from the colour and depth face images captured with a consumer-level RGB-D camera. To recognize faces with colour and depth information, our system contains 3 parts: depth image recovery, deep learning for feature extraction, and joint classification. To alleviate the problem of the limited size of available RGB-D data for deep learning, our deep network is firstly trained with colour and grayscale images from CASIA-WebFace dataset, and later fine-tuned on depth images for transfer learning. Our experiments on some public and our own RGB-D face datasets show that the proposed face recognition system provides very accurate face recognition results and it is robust against variations in head rotation and environmental illumination.

Session

Posters 2

Files

Extended Abstract (PDF, 124K)
Paper (PDF, 1M)
Supplemental Materials (ZIP, 1M)

DOI

10.5244/C.30.123
https://dx.doi.org/10.5244/C.30.123

Citation

Bibtex

        @inproceedings{BMVC2016_123,
        	title={Accurate and robust face recognition from RGB-D images with a deep learning approach},
        	author={Yuancheng Lee, Jiancong Chen, Ching Wei Tseng and Shang-Hong Lai},
        	year={2016},
        	month={September},
        	pages={123.1-123.14},
        	articleno={123},
        	numpages={14},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.123},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.123}
        }