Name
Title | ||
|---|---|---|
Robust Face Recognition with Assistance of Pose and Expression Normalized Albedo Images |
Abstract | ||
|---|---|---|
Facial albedo images are believed to be invariant to external factors of pose, illumination and expression that can greatly affect the appearance of face images and thus face recognition accuracy as well. Unlike most existing face recognition methods that address the impact of one or two of these external factors, we propose an end-to-end network, which consists of De-Light Network (DL-Net) and Normalization Network (N-Net), to generate normalized albedo images with neutral expression and frontal pose for input face images. DL-Net aims to eliminate the effects of illumination and reconstruct a posed albedo image that has the same pose and expression as the input image. N-Net attempts to generate a pose and expression normalized albedo image and extract identity features under the supervision of the normalized albedo images. Our experiments on the Multi-PIE database show that the extracted identity features can effectively assist conventional face recognition methods to improve face recognition accuracy under varying poses, illuminations and expressions.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3330482.3330501 | Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence |
Keywords | Field | DocType |
Albedo image, face recognition, normalization | Computer vision,Facial recognition system,Normalization (statistics),Computer science,Albedo,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
978-1-4503-6106-4 | 978-1-4503-6106-4 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Huan Tu | 1 | 0 | 0.34 |
| Kunjian Li | 2 | 0 | 0.34 |
| Qijun Zhao | 3 | 419 | 38.37 |