Face Recognition via Deep Sparse Graph Neural Networks

Renjie Wu, Sei-ichiro Kamata and Toby Breckon


Abstract
In recent years, deep learning based approaches have substantially improved the performance of face recognition. Most existing deep learning techniques work well, but neglect effective utilization of face correlation information. The resulting performance loss is noteworthy for personal appearance variations caused by factors such as illumination, pose, occlusion, and misalignment. We believe that face correlation information should be introduced to solve this network performance problem originating from by intra-personal variations. Obviously, different poses of same person have similar feature structure, and even different people may have some similar facial sub-regions. We pro-pose a graph representation based on the face correlation information that is embedded via the sparse reconstruction and deep learning within an irregular domain. The pro-posed method achieves high recognition rates of 99.58%on the benchmark LFW facial evaluation database.


Files
Paper (PDF)


DOI
Coming soon


Bibtex
@inproceedings{dlid2017_3,

title = {Face Recognition via Deep Sparse Graph Neural Networks},
author = {R. Wu, S. Kamata and T. Breckon},
booktitle = {British Machine Vision Conference Workshop: Deep Learning on Irregular Domains (DLID)},
year = {2017},
pages={3.1--3.10}

}