Name
Abstract | ||
|---|---|---|
Inspired by unsupervised feature learning (UFL) within the self-taught learning framework, we propose a method based on UFL, convolution representation, and part-based dimensionality reduction to handle facial age and gender classification, which are two challenging problems under unconstrained circumstances. First, UFL is introduced to learn selective receptive fields (filters) automatically by applying whitening transformation and spherical k-means on random patches collected from unlabeled data. The learning process is fast and has no hyperparameters to tune. Then, the input image is convolved with these filters to obtain filtering responses on which local contrast normalization is applied. Average pooling and feature concatenation are then used to form global face representation. Finally, linear discriminant analysis with part-based strategy is presented to reduce the dimensions of the global representation and to improve classification performances further. Experiments on three challenging databases, namely, Labeled faces in the wild, Gallagher group photos, and Adience, demonstrate the effectiveness of the proposed method relative to that of state-of-the-art approaches. (C) 2017 SPIE and IS&T |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1117/1.JEI.26.2.023007 | JOURNAL OF ELECTRONIC IMAGING |
Keywords | Field | DocType |
average pooling,convolution representation,dimensionality reduction,unsupervised feature learning | Dimensionality reduction,Normalization (statistics),Computer science,Artificial intelligence,Concatenation,Computer vision,Pattern recognition,Whitening transformation,Filter (signal processing),Feature extraction,Linear discriminant analysis,Feature learning,Machine learning | Journal |
Volume | Issue | ISSN |
26 | 2 | 1017-9909 |
Citations | PageRank | References |
0 | 0.34 | 27 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lihong Wan | 1 | 12 | 3.54 |
| Hong Huo | 2 | 126 | 17.77 |
| Tao Fang | 3 | 226 | 31.10 |