國立高雄大學圖資館 |

Language: English

Back

植基於奇異值分解與改良式區域方向圖樣之人臉表情辨識 = Facial E...

周士弼

植基於奇異值分解與改良式區域方向圖樣之人臉表情辨識 = Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern

Record Type:	Language materials, printed : monographic
Paralel Title:	Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern
Author:	周士弼,
Secondary Intellectual Responsibility:	國立高雄大學
Place of Publication:	[高雄市]
Published:	撰者;
Year of Publication:	2015[民104]
Description:	61面圖，表 : 30公分;
Subject:	表情辨識
Subject:	Facial expression recognition
Online resource:	http://handle.ncl.edu.tw/11296/ndltd/74373851810438406859
Notes:	104年10月31日公開
Notes:	參考書目：面48-52
Summary:	由於人機互動介面受到重視,使得人臉辨識在電腦視覺領域中,成為熱門的研究主題之一。優秀人臉表情辨識系統的關鍵,在於如何建立能穩健描述人臉表情的特徵。本論文提出,奇異值分解與改良式區域方向圖樣結合的外觀特徵萃取方法,我們使用Cohn-Kanada、Extended Cohn-Kanada(CK+)、JAFFE與TFEID人臉表情資料庫,以支持向量機進行表情分類進行效能測試。實驗結果顯示,我們的方法能獲得相當良好的辨識準確率。 Facial expression recognition has received a considerable amount of attention by the computer vision research community due to its importance in both human-computer and social interaction. One of the critical issues for a successful facial expression recognition system is to develop a robust facial feature descriptor. In this paper, we present an appearance-based facial feature descriptor which combines singular value decomposition and the improved local directional pattern. The recognition performance of the proposed method is evaluated on the well-known Cohn-Kanada, Extended Cohn-Kanada (CK+), JAFFE, and TFEID databases with a support vector machine classifier, respectively. Experimental results show that the proposed method yields good recognition accuracy than other existing methods.

植基於奇異值分解與改良式區域方向圖樣之人臉表情辨識 = Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern
周, 士弼

植基於奇異值分解與改良式區域方向圖樣之人臉表情辨識 = Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern / 周士弼撰 - [高雄市] : 撰者, 2015[民104]. - 61面 ; 圖，表 ; 30公分.
104年10月31日公開參考書目：面48-52.
表情辨識Facial expression recognition

植基於奇異值分解與改良式區域方向圖樣之人臉表情辨識 = Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern
LDR:02681nam0a2200289 450 001 458460
005 20170214095730.0
009 458460
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214d2015 k y0chiy50 e
101 1 $a chi $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 植基於奇異值分解與改良式區域方向圖樣之人臉表情辨識 $d Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern $z eng $f 周士弼撰
210 $a [高雄市] $c 撰者 $d 2015[民104]
215 0 $a 61面 $c 圖，表 $d 30公分
300 $a 104年10月31日公開
300 $a 參考書目：面48-52
314 $a 指導教授：賴智錦博士、潘欣泰博士
328 $a 碩士論文--國立高雄大學電機工程學系碩士班
330 $a 由於人機互動介面受到重視,使得人臉辨識在電腦視覺領域中,成為熱門的研究主題之一。優秀人臉表情辨識系統的關鍵,在於如何建立能穩健描述人臉表情的特徵。本論文提出,奇異值分解與改良式區域方向圖樣結合的外觀特徵萃取方法,我們使用Cohn-Kanada、Extended Cohn-Kanada(CK+)、JAFFE與TFEID人臉表情資料庫,以支持向量機進行表情分類進行效能測試。實驗結果顯示,我們的方法能獲得相當良好的辨識準確率。 Facial expression recognition has received a considerable amount of attention by the computer vision research community due to its importance in both human-computer and social interaction. One of the critical issues for a successful facial expression recognition system is to develop a robust facial feature descriptor. In this paper, we present an appearance-based facial feature descriptor which combines singular value decomposition and the improved local directional pattern. The recognition performance of the proposed method is evaluated on the well-known Cohn-Kanada, Extended Cohn-Kanada (CK+), JAFFE, and TFEID databases with a support vector machine classifier, respectively. Experimental results show that the proposed method yields good recognition accuracy than other existing methods.
510 1 $a Facial Expression Recognition Based on Singular Value Decomposition and Improved Local Directional Pattern $z eng
610 0 $a 表情辨識 $a 區域方向圖樣 $a 奇異值分解 $a 支持向量機
610 1 $a Facial expression recognition $a Singular Value Decomposition $a Local Directional Pattern $a Improved Local Directional Pattern $a Support vector machine
681 $a 008M/0019 $b 542201 7741.1 $v 2007年版
700 1 $a 周 $b 士弼 $4 撰 $3 709699
712 0 2 $a 國立高雄大學 $b 電機工程學系碩士班 $3 166118
801 0 $a tw $b NUK $c 20151103 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/74373851810438406859