Laser & Optoelectronics Progress, Volume. 56, Issue 3, 031002(2019)
3D Printing Mask Attacks Detection Based on Multi-Feature Fusion
Fig. 1. Flowchart of the proposed algorithm
Fig. 2. Computation of local descriptor in nine regions and generating HOC
Fig. 3. Calculation process of shearlet-based image texture feature
Fig. 4. (a) Autoencdoer of three layer network; (b) structure of stacked autoencoder
Fig. 5. Flow chart of the multi-feature fusion based on 3D printing mask attack detection using neural networks
Fig. 6. 2D texture image and corresponding 3D meshed scans in BFFD database. (a) Genuine faces sample; (b) AA, AB spoofing samples
Fig. 7. ROC curves of intra tests for BFFD database
|
|
|
|
Get Citation
Copy Citation Text
Jingwei Lu, Hetian Chen, Xiaopan Ma, Jimin Chen. 3D Printing Mask Attacks Detection Based on Multi-Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(3): 031002
Category: Image Processing
Received: Jul. 4, 2018
Accepted: Aug. 13, 2018
Published Online: Jul. 31, 2019
The Author Email: Lu Jingwei (18810815230@126.com)