| Presentation | 2007-01-18 Face detection with GA and Adaboost Takeshi YAMADA, Haiyuan WU, Toshikazu WADA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, the face detection method using Adaboost and a cascaded classifier has been getting attention, which has been proposed by Viola et al. This method has a problem that it takes a long time for learning because features available for classification are selected from a large amount of Haar like features that have been prepared. Only a few features are actually used for a constructed classifier. In this paper, we propose the face detection method using Genetic Algorithm, Ternary logic, Real Adaboost and the cascaded classifier. This method requires only a few initial Haar like features. For every layer of the cascaded classifier (here, we regard each layer as a generation), feature candidates for the next layer (generation) are generated by GA and Ternary logic. Then the classifier is constructed by selecting available features by Adaboost. It has an advantage that it takes less time for learning than the method by Viola. We confirmed that proposed method was efficient through experiments using the common face database. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Face detection / Adaboost learning algorithm / Haar like feature / Genetic Algorithm |
| Paper # | PRMU2006-190 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2007/1/11(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Face detection with GA and Adaboost |
| Sub Title (in English) | |
| Keyword(1) | Face detection |
| Keyword(2) | Adaboost learning algorithm |
| Keyword(3) | Haar like feature |
| Keyword(4) | Genetic Algorithm |
| 1st Author's Name | Takeshi YAMADA |
| 1st Author's Affiliation | Graduate School of Systems Engineering, Wakayama University() |
| 2nd Author's Name | Haiyuan WU |
| 2nd Author's Affiliation | Graduate School of Systems Engineering, Wakayama University |
| 3rd Author's Name | Toshikazu WADA |
| 3rd Author's Affiliation | Graduate School of Systems Engineering, Wakayama University |
| Date | 2007-01-18 |
| Paper # | PRMU2006-190 |
| Volume (vol) | vol.106 |
| Number (no) | 469 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |