Name
Abstract | ||
|---|---|---|
Face recognition using depth data has attracted increasing attention from both academia and industry in the past five years. Previous works show a huge performance gap between high-quality and low-quality depth data. Due to the lack of databases and reasonable evaluations on data quality, very few researchers have focused on boosting depth-based face recognition by enhancing data quality or feature representation. In the paper, we carefully collect a new database including high-quality 3D shapes, low-quality depth images and the corresponding color images of the faces of 902 subjects, which have long been missing in the area. With the database, we make a standard evaluation protocol and propose three strategies to train low-quality depth-based face recognition models with the help of high-quality depth data. Our training strategies could serve as baselines for future research, and their feasibility of boosting low-quality depth-based face recognition is validated by extensive experiments. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.3390/s19194124 | SENSORS |
Keywords | Field | DocType |
depth-based face recognition,deep models,data quality,database | Facial recognition system,Data quality,3d shapes,Baseline (configuration management),Electronic engineering,Artificial intelligence,Boosting (machine learning),Engineering,Performance gap,Machine learning | Journal |
Volume | Issue | ISSN |
19 | 19.0 | 1424-8220 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhenguo Hu | 1 | 0 | 0.68 |
| Penghui Gui | 2 | 0 | 0.68 |
| Ziqing Feng | 3 | 0 | 0.68 |
| Qijun Zhao | 4 | 419 | 38.37 |
| Keren Fu | 5 | 295 | 26.25 |
| Feng Liu | 6 | 105 | 9.27 |
| Zhengxi Liu | 7 | 0 | 1.01 |