Name
Abstract | ||
|---|---|---|
We proposed a novel age estimation scheme based on feature fusion according to Canonical Correlation analysis. Specifically, the shape and texture attributes of feature points in human faces are characterized by both Active Appearance Model (AAM) and Local Binary Pattern (LBP). Then, the canonical projective vectors are built via canonical correlation analysis for feature fusion. To improve computational efficiency, we first introduce Extreme Learning Machine (ELM) to the field of age estimation, and uncover the relation of the fused features and ground-truth age values for age prediction. The experimental results conducted on FG-NET age database show that the proposed method achieves better estimation accuracy while requires less computation time than the state of art algorithms such as BIF. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1007/978-3-319-25417-3_79 | BIOMETRIC RECOGNITION, CCBR 2015 |
Keywords | Field | DocType |
Age estimation,Canonical Correlation Analysis,Feature fusion,Extreme Learning Machine | Feature fusion,Pattern recognition,Extreme learning machine,Canonical correlation,Computer science,Age values,Local binary patterns,Active appearance model,Artificial intelligence,Computation | Conference |
Volume | ISSN | Citations |
9428 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jie Si | 1 | 0 | 0.34 |
| Jun Feng | 2 | 14 | 7.98 |
| Qirong Bu | 3 | 8 | 2.16 |
| Xiaohu Sun | 4 | 0 | 0.34 |
| Xiaowei He | 5 | 123 | 19.78 |
| Shi Qiu | 6 | 0 | 0.68 |