Abstract | ||
---|---|---|
Despite a great deal of progress in face recognition technologies, current solutions are still vulnerable to spoof attacks. In fact, it is easy to access digital replicas of facial biometric information from readily available photos, videos and 3D masks. The literature contains several face anti spoofing methods that try to detect whether the face in the front of the recognition system is real or an artificial replica. However, these methods are not robust and require many improvements since they are sensitive to lightening conditions and pose variations. In order to address these issues, we propose a novel face anti spoofing method based on Multi Color Convolutional Neural Network (CNN) architecture named DeepColorFASD. Our approach investigates the effect of space colors (RGB, HSV and YCbCr) on CNN architectures and proposes a fusion based voting method for face anti spoofing. In addition, we also explain the resulting feature maps visualizations. We evaluate our system through an experimental study using CASIA FASD: a well-known face anti spoofing database. The results using this challenging database demonstrate that our solution performs better than recent works as measured by Half Total Error Rate (HTER) and ROC curve. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/SMC.2018.00680 | 2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) |
Keywords | Field | DocType |
face anti Spoofing, Multi Color Spaces, Convolutional Neural Networks, Feature maps Visualizing, CASIA Database | Facial recognition system,Replica,HSL and HSV,Computer vision,Color space,Convolutional neural network,Computer science,Artificial intelligence,RGB color model,Biometrics,Machine learning,Anti spoofing | Conference |
ISSN | Citations | PageRank |
1062-922X | 2 | 0.36 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kaouthar Larbi | 1 | 2 | 0.36 |
Wael Ouarda | 2 | 34 | 7.36 |
Hassen Drira | 3 | 117 | 14.18 |
Boulbaba Ben Amor | 4 | 380 | 24.19 |
Chokri Ben Amar | 5 | 643 | 82.72 |