國立高雄大學圖資館 |

Language: English

Back

基於特定區域紋理特徵之人臉表情辨識 = Facial Expressio...

國立高雄大學電機工程學系碩士班

基於特定區域紋理特徵之人臉表情辨識 = Facial Expression Recognition Based on Salient Local Texture-based Features

Record Type:	Language materials, printed : monographic
Paralel Title:	Facial Expression Recognition Based on Salient Local Texture-based Features
Author:	謝鴻瑲,
Secondary Intellectual Responsibility:	國立高雄大學
Place of Publication:	[高雄市]
Published:	撰者;
Year of Publication:	民103[2014]
Description:	43葉部分彩圖，表格 : 30公分;
Subject:	人臉表情辨識
Subject:	Facial expression recognition
Online resource:	http://hdl.handle.net/11296/ndltd/56621011000286413896
Notes:	106年10月31日公開
Notes:	參考書目：葉40-43
Summary:	近年來，自動化地人臉表情辨識在建構人機互動系統上已獲得了極大的關注。從影像中擷取重要並具辨識能力的特徵是人臉表情辨識中最重要的一環。本論文提出一個以特定區域進行特徵擷取之人臉表情辨識方法。我們先將人臉表情影像透過加速穩健特徵計算出特徵點，並根據特徵點分布選出特定區域，接著使用結合中心對稱區域三元圖樣及區域符號方向圖樣之特徵擷取方法擷取出這些特定區域內之特徵，最後將這些特徵以支持向量機分類器進行表情辨識。實驗結果證實，我們提出的方法在Cohn-Kanade、Extended Cohn-Kanade、TFEID及JAFFE表情資料庫中，都能提取出表情影像中較具有鑑別度的特徵，進而得到良好的辨識效果。 Automatic facial expression recognition has gained an increasing interest in recent years in building natural human-computer interaction systems. Extracting the discriminative features from facial images is the most important part of facial expression recognition. In this paper, we propose a facial expression recognition approach based on salient local texture-based features. We use Speeded Up Robust Features to find interest points and to generate salient regions from facial images, and then the associated features based on Center-Symmetric Local Ternary Pattern and Local Sign Directional Pattern in these regions are extracted. These features are classified by using the Support Vector Machine. Experimental results show that our approach can achieve higher recognition rate on the Cohn-Kanade, Extended Cohn-Kanade, TFEID, and JAFFE facial expression databases.

基於特定區域紋理特徵之人臉表情辨識 = Facial Expression Recognition Based on Salient Local Texture-based Features
謝, 鴻瑲

基於特定區域紋理特徵之人臉表情辨識 = Facial Expression Recognition Based on Salient Local Texture-based Features / 謝鴻瑲撰 - [高雄市] : 撰者, 民103[2014]. - 43葉 ; 部分彩圖，表格 ; 30公分.
106年10月31日公開參考書目：葉40-43.
人臉表情辨識Facial expression recognition

基於特定區域紋理特徵之人臉表情辨識 = Facial Expression Recognition Based on Salient Local Texture-based Features
LDR:02983nam0 2200277 450 001 430227
005 20171103092806.0
010 0 $b 精裝
010 0 $b 平裝
100 $a 20141027y2014 k y0chiy50 e
101 0 $a chi $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 基於特定區域紋理特徵之人臉表情辨識 $d Facial Expression Recognition Based on Salient Local Texture-based Features $z eng $f 謝鴻瑲撰
210 $a [高雄市] $c 撰者 $d 民103[2014]
215 0 $a 43葉 $c 部分彩圖，表格 $d 30公分
300 $a 106年10月31日公開
300 $a 參考書目：葉40-43
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 近年來，自動化地人臉表情辨識在建構人機互動系統上已獲得了極大的關注。從影像中擷取重要並具辨識能力的特徵是人臉表情辨識中最重要的一環。本論文提出一個以特定區域進行特徵擷取之人臉表情辨識方法。我們先將人臉表情影像透過加速穩健特徵計算出特徵點，並根據特徵點分布選出特定區域，接著使用結合中心對稱區域三元圖樣及區域符號方向圖樣之特徵擷取方法擷取出這些特定區域內之特徵，最後將這些特徵以支持向量機分類器進行表情辨識。實驗結果證實，我們提出的方法在Cohn-Kanade、Extended Cohn-Kanade、TFEID及JAFFE表情資料庫中，都能提取出表情影像中較具有鑑別度的特徵，進而得到良好的辨識效果。 Automatic facial expression recognition has gained an increasing interest in recent years in building natural human-computer interaction systems. Extracting the discriminative features from facial images is the most important part of facial expression recognition. In this paper, we propose a facial expression recognition approach based on salient local texture-based features. We use Speeded Up Robust Features to find interest points and to generate salient regions from facial images, and then the associated features based on Center-Symmetric Local Ternary Pattern and Local Sign Directional Pattern in these regions are extracted. These features are classified by using the Support Vector Machine. Experimental results show that our approach can achieve higher recognition rate on the Cohn-Kanade, Extended Cohn-Kanade, TFEID, and JAFFE facial expression databases.
510 1 $a Facial Expression Recognition Based on Salient Local Texture-based Features $z eng
610 # 0 $a 人臉表情辨識 $a 加速穩健特徵 $a 中心對稱區域三元圖樣 $a 區域符號方向圖樣 $a 支持向量機
610 # 1 $a Facial expression recognition $a Speeded up robust features $a Center-symmetric local ternary pattern $a Local sign directional pattern $a Support vector machine
681 $a 008M/0019 $b 542201 0431 $v 2007年版
700 1 $a 謝 $b 鴻瑲 $4 撰 $3 673443
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 20171026 $g CCR
856 7 # $u http://hdl.handle.net/11296/ndltd/56621011000286413896 $2 http $z 電子資源