講演抄録/キーワード |
講演名 |
2007-03-16 09:30
Face Recognition across pose using Self-organizing Maps ○Saleh Aly(Kyushu Univ.)・Naoyuki Tsuruta(Fukuoka Univ.)・Rin-Ichiro Taniguchi(Kyushu Univ.) |
抄録 |
(和) |
We present a comparison between Self-organizing map (SOM) and hierarchical SOM (HSOM) to tackle pose variation problem in face recognition. Self-organizing map (SOM) transforms the high dimensional face images into low dimensional topological space. However, in SOM, the hierarchical relation between data set doesn`t preserved. HSOM solve this problem, moreover it reduces the time required for winner searching. In this paper, CMU-PIE face database is utilized to show the accuracy of both models. |
(英) |
We present a comparison between Self-organizing map (SOM) and hierarchical SOM (HSOM) to tackle pose variation problem in face recognition. Self-organizing map (SOM) transforms the high dimensional face images into low dimensional topological space. However, in SOM, the hierarchical relation between data set doesn`t preserved. HSOM solve this problem, moreover it reduces the time required for winner searching. In this paper, CMU-PIE face database is utilized to show the accuracy of both models. |
キーワード |
(和) |
face recognition / pose variations / SOM / hierarchical SOM / / / / |
(英) |
face recognition / pose variations / SOM / hierarchical SOM / / / / |
文献情報 |
信学技報, vol. 106, no. 590, NC2006-200, pp. 75-78, 2007年3月. |
資料番号 |
NC2006-200 |
発行日 |
2007-03-09 (NC) |
ISSN |
Print edition: ISSN 0913-5685 |
PDFダウンロード |
|