WEKO3
アイテム
Facial Feature Land-marking with Optimized Gabor Parameters based on Maximization of Separation between Features
https://ipsj.ixsq.nii.ac.jp/records/41103
https://ipsj.ixsq.nii.ac.jp/records/4110320e74d3f-c4fc-430f-b677-1b568cdac535
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-AVM06055010.pdf (898.0 kB)
|
Copyright (c) 2006 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | SIG Technical Reports(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2006-12-14 | |||||||
| タイトル | ||||||||
| タイトル | Facial Feature Land-marking with Optimized Gabor Parameters based on Maximization of Separation between Features | |||||||
| タイトル | ||||||||
| 言語 | en | |||||||
| タイトル | Facial Feature Land-marking with Optimized Gabor Parameters based on Maximization of Separation between Features | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| 資源タイプ | ||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||||
| 資源タイプ | technical report | |||||||
| 著者所属 | ||||||||
| School of Information Science Japan Advanced Institute of Science and Technology | ||||||||
| 著者所属 | ||||||||
| School of Information Science Japan Advanced Institute of Science and Technology | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| School of Information Science, Japan Advanced Institute of Science and Technology | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| School of Information Science, Japan Advanced Institute of Science and Technology | ||||||||
| 著者名 |
Fan, CHEN
× Fan, CHEN
|
|||||||
| 著者名(英) |
Fan, CHEN
× Fan, CHEN
|
|||||||
| 論文抄録 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | Elastic Bunch Graph Matching(EBGM) is a popu lar method in automatic localization of facial feature points where the selection of optimal Gabor param eters plays a key role in the extraction of Gabor jets with a high degree of discrimination. We propose a method for the selection of parameters by minimiz ing the energy function consisting of within-class and between-class scatters using the gradient descendent method. We formulate the learning rule and design the algorithm for the learning of parameters. Numeri cal experiments have been performed to investigate the performance of estimated parameters in improving the precision of automatic localization. | |||||||
| 論文抄録(英) | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | Elastic Bunch Graph Matching(EBGM) is a popu lar method in automatic localization of facial feature points, where the selection of optimal Gabor param eters plays a key role in the extraction of Gabor jets with a high degree of discrimination. We propose a method for the selection of parameters by minimiz ing the energy function consisting of within-class and between-class scatters using the gradient descendent method. We formulate the learning rule and design the algorithm for the learning of parameters. Numeri cal experiments have been performed to investigate the performance of estimated parameters in improving the precision of automatic localization. | |||||||
| 書誌レコードID | ||||||||
| 収録物識別子タイプ | NCID | |||||||
| 収録物識別子 | AN10438399 | |||||||
| 書誌情報 |
情報処理学会研究報告オーディオビジュアル複合情報処理（AVM） 巻 2006, 号 132(2006-AVM-055), p. 53-58, 発行日 2006-12-14 |
|||||||
| Notice | ||||||||
| SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. | ||||||||
| 出版者 | ||||||||
| 言語 | ja | |||||||
| 出版者 | 情報処理学会 | |||||||
