Abstract | ||
---|---|---|
Existing Deep Convolutional Neural Network (DCNN) methods for Face Landmark Localization are based on Cascaded Networks or Tasks-Constrained Deep Convolutional Network (TCDCN), which are complicated and difficult to train. To solve this problem, this paper proposes a new Single Deep CNN (SDN). Unlike cascaded CNNs, SDN stacks three layer groups: each group consists of two convolutional layers and a max-pooling layer. This network structure can extract more global high-level features, which express the face landmarks more precisely. Extensive experiments show that SDN outperforms existing DCNN methods and is robust to large pose variation, lighting and even severe occlusion. While the network complexity is also reduced obviously compared to other methods. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46654-5_8 | BIOMETRIC RECOGNITION |
Keywords | Field | DocType |
DCNN,Face landmark localization,SDN | Network complexity,Pattern recognition,Computer science,Convolutional neural network,Artificial intelligence,Landmark,Network structure | Conference |
Volume | ISSN | Citations |
9967 | 0302-9743 | 1 |
PageRank | References | Authors |
0.38 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zongping Deng | 1 | 1 | 0.38 |
Ke Li | 2 | 1 | 0.38 |
Qijun Zhao | 3 | 419 | 38.37 |
Hu Chen | 4 | 97 | 8.61 |