國立高雄大學圖資館 |

Language: English

Back

植基於二階段區域紋理特徵之臉部表情辨識 = Facial Express...

國立高雄大學電機工程學系碩士班

植基於二階段區域紋理特徵之臉部表情辨識 = Facial Expression Recognition Based on Two-Stage Local Texture Features

Record Type:	Language materials, printed : monographic
Paralel Title:	Facial Expression Recognition Based on Two-Stage Local Texture Features
Author:	柯忠宏,
Secondary Intellectual Responsibility:	國立高雄大學
Place of Publication:	[高雄市]
Published:	撰者;
Year of Publication:	2013[民102]
Description:	54面圖，表 : 30公分;
Subject:	表情辨識
Subject:	Facial expression recognition
Online resource:	http://handle.ncl.edu.tw/11296/ndltd/44434308214682736940
Notes:	105年10月25日公開
Notes:	參考書目：面44-47
Summary:	臉部表情辨識在人機互動、機器人控制以及駕駛狀態監控等應用中扮演著重要的角色。如何有效且準確的擷取表情特徵，是臉部表情辨識最重要的步驟。本論文提出一個二階段區域紋理特徵之臉部表情辨識方法。我們將臉部影像進行全域的門檻值區域二元圖樣轉換為特徵影像，再以區塊式的中心對稱區域二元圖樣擷取出具鑑別度的臉部表情特徵，最後將這些特徵輸入支持向量機分類器進行表情辨識。實驗結果證明我們所提出的方法用於Cohn-Kanade以及JAFFE表情影像資料庫，確實能獲得不錯的辨識效果。 Facial expression recognition plays an important role in a variety of applications such as human-computer interaction, robot control, and driver state surveillance. One critical step for facial expression recognition is to accurately extract emotional features. In this paper, we proposed a facial expression recognition approach based on two-stage local facial textures. We use the threshold local binary pattern to transform a facial image into a feature image, and then we extract the most discriminate features based on the block-based center-symmetric local binary pattern. These features are classified by using the support vector machine. Experiment results show the effectiveness of the proposed approach on both the Cohn-Kanade and JAFFE databases.

植基於二階段區域紋理特徵之臉部表情辨識 = Facial Expression Recognition Based on Two-Stage Local Texture Features
柯, 忠宏

植基於二階段區域紋理特徵之臉部表情辨識 = Facial Expression Recognition Based on Two-Stage Local Texture Features / 柯忠宏撰 - [高雄市] : 撰者, 2013[民102]. - 54面 ; 圖，表 ; 30公分.
105年10月25日公開參考書目：面44-47.
表情辨識Facial expression recognition

植基於二階段區域紋理特徵之臉部表情辨識 = Facial Expression Recognition Based on Two-Stage Local Texture Features
LDR:02688nam0 2200277 450 001 389720
005 20161117141437.0
010 0 $b 精裝
010 0 $b 平裝
100 $a 20130926d2013 k y0chiy50 e
101 1 $a chi $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 植基於二階段區域紋理特徵之臉部表情辨識 $d Facial Expression Recognition Based on Two-Stage Local Texture Features $z eng $f 柯忠宏撰
210 $a [高雄市] $c 撰者 $d 2013[民102]
215 0 $a 54面 $c 圖，表 $d 30公分
300 $a 105年10月25日公開
300 $a 參考書目：面44-47
314 $a 指導教授：賴智錦博士
328 $a 碩士論文--國立高雄大學電機工程學系碩士班
330 $a 臉部表情辨識在人機互動、機器人控制以及駕駛狀態監控等應用中扮演著重要的角色。如何有效且準確的擷取表情特徵，是臉部表情辨識最重要的步驟。本論文提出一個二階段區域紋理特徵之臉部表情辨識方法。我們將臉部影像進行全域的門檻值區域二元圖樣轉換為特徵影像，再以區塊式的中心對稱區域二元圖樣擷取出具鑑別度的臉部表情特徵，最後將這些特徵輸入支持向量機分類器進行表情辨識。實驗結果證明我們所提出的方法用於Cohn-Kanade以及JAFFE表情影像資料庫，確實能獲得不錯的辨識效果。 Facial expression recognition plays an important role in a variety of applications such as human-computer interaction, robot control, and driver state surveillance. One critical step for facial expression recognition is to accurately extract emotional features. In this paper, we proposed a facial expression recognition approach based on two-stage local facial textures. We use the threshold local binary pattern to transform a facial image into a feature image, and then we extract the most discriminate features based on the block-based center-symmetric local binary pattern. These features are classified by using the support vector machine. Experiment results show the effectiveness of the proposed approach on both the Cohn-Kanade and JAFFE databases.
510 1 $a Facial Expression Recognition Based on Two-Stage Local Texture Features $z eng
610 # 0 $a 表情辨識 $a 區域二元圖樣 $a 門檻值區域二元圖樣 $a 中心對稱區域二元圖樣 $a 支持向量機
610 # 1 $a Facial expression recognition $a Local binary pattern $a Threshold local binary pattern $a Center-symmetric local binary pattern $a Support vector machine
681 $a 008M/0019 $b 542201 4153 $v 2007年版
700 1 $a 柯 $b 忠宏 $4 撰 $3 614578
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 20161014 $g CCR
856 7 # $u http://handle.ncl.edu.tw/11296/ndltd/44434308214682736940 $2 http $z PDF全文