a国产,中文字幕久久波多野结衣AV,欧美粗大猛烈老熟妇,女人av天堂

當(dāng)前位置:主頁 > 碩博論文 > 信息類碩士論文 >

基于人臉子區(qū)域加權(quán)和LDA的表情識別算法

發(fā)布時間:2018-12-07 10:56
【摘要】:人臉表情是人們?nèi)粘贤ㄖ凶钪匾囊环N表現(xiàn)特征,對于情感計算的研究發(fā)展具有重要意義。針對靜態(tài)表情圖像,單一的整體模版匹配方法特征維數(shù)較高,含有較多無關(guān)區(qū)域特征,因此很難獲得較好的識別效果。本文從幾何置信區(qū)域角度出發(fā),采用本文給出的基于幾何先驗的加權(quán)策略進(jìn)行特征融合,結(jié)合線性判別分析算法進(jìn)行研究,獲得了較好的效果。本論文的主要工作如下:(1)給出一種基于子區(qū)域(置信區(qū)域)和多特征的加權(quán)融合特征提取算法。針對檢測區(qū)域存在較多與人臉部分不相關(guān)的區(qū)域,通過給出基于幾何先驗的裁剪策略作用于檢測區(qū)域,得到更加精確的人臉及其子區(qū)域。針對人臉圖像存在表情無關(guān)區(qū)域并且單一特征描繪不準(zhǔn)確的特點(diǎn),采用Gabor小波對人臉區(qū)域進(jìn)行特征提取,HOG對置信區(qū)域進(jìn)行特征提取,通過研究置信區(qū)域在人臉表情中的先驗信息(敏感度)并且實(shí)驗加以論證,最終給不同的置信區(qū)域設(shè)置相應(yīng)權(quán)值,得到加權(quán)融合特征。在多個數(shù)據(jù)集上進(jìn)行實(shí)驗,驗證了本文算法的有效性。(2)給出一種基于類內(nèi)散度矩陣修正的改進(jìn)LDA算法。針對初步降維特征缺少判別特性的缺點(diǎn),通過在類內(nèi)散度矩陣中引入余弦相似度信息,將每類樣本向量與其均值向量之間的夾角余弦值通過線性變換加權(quán)乘到對應(yīng)協(xié)方差矩陣中,獲得更好的類內(nèi)聚合度和類間離散度。在多個數(shù)據(jù)集上進(jìn)行實(shí)驗,驗證了本文改進(jìn)算法的有效性。(3)構(gòu)造一種GRNN神經(jīng)網(wǎng)絡(luò)分類器首次應(yīng)用于人臉表情識別領(lǐng)域。針對傳統(tǒng)分類器對小樣本非線性數(shù)據(jù)擬合的局限性,通過對人臉表情數(shù)據(jù)特點(diǎn)的分析,構(gòu)造一種GRNN分類器嵌入表情識別算法中,將融合特征作為網(wǎng)絡(luò)的輸入,經(jīng)過模式層和求和層之后完成訓(xùn)練。在多個數(shù)據(jù)集上進(jìn)行實(shí)驗,驗證了本文算法的有效性。
[Abstract]:Facial expression is one of the most important expression features in people's daily communication, which is of great significance to the research and development of emotional computing. For the static facial expression image, the single integral template matching method has higher feature dimension and more independent region features, so it is difficult to obtain a better recognition effect. In this paper, from the point of view of geometric confidence region, the feature fusion based on geometric priori weighting strategy is adopted, and the linear discriminant analysis (LDA) algorithm is used to study the feature fusion, and good results are obtained. The main work of this paper is as follows: (1) A weighted fusion feature extraction algorithm based on sub-region (confidence region) and multi-feature is proposed. Because there are many regions which are not related to the face part in the detection region, a geometric priori based clipping strategy is given to the detection region to obtain more accurate face and its sub-regions. In view of the feature of facial expression independent region and inaccurate description of single feature in face image, Gabor wavelet is used to extract the feature of face region, and HOG is used to extract the feature of confidence region. By studying the priori information (sensitivity) of the confidence region in the facial expression and proving it experimentally, the weighted fusion feature is obtained by setting the corresponding weights for the different confidence regions. Experiments on multiple datasets show the effectiveness of the proposed algorithm. (2) an improved LDA algorithm based on the correction of the intra-class divergence matrix is proposed. In view of the lack of discriminant characteristics in the preliminary dimensionality reduction feature, the cosine similarity information is introduced into the intra-class divergence matrix. The angle cosine value between each class of sample vector and its mean vector is weighted by linear transformation to the corresponding covariance matrix to obtain a better degree of intra-class aggregation and inter-class dispersion. Experiments on multiple datasets show the effectiveness of the improved algorithm. (3) A GRNN neural network classifier is first applied to facial expression recognition. Aiming at the limitation of the traditional classifier to fit the small sample nonlinear data, a GRNN classifier embedded in the facial expression recognition algorithm is constructed by analyzing the features of the facial expression data, and the fusion feature is taken as the input of the network. After the mode layer and summation layer completed the training. Experiments on multiple datasets show the effectiveness of the proposed algorithm.
【學(xué)位授予單位】:大連海事大學(xué)
【學(xué)位級別】:碩士
【學(xué)位授予年份】:2017
【分類號】:TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 薛雨麗;毛峽;張帆;;BHU人臉表情數(shù)據(jù)庫的設(shè)計與實(shí)現(xiàn)[J];北京航空航天大學(xué)學(xué)報;2007年02期

2 ;Person-independent expression recognition based on person-similarity weighted expression feature[J];Journal of Systems Engineering and Electronics;2010年01期

3 王大偉;周軍;梅紅巖;張素娥;;人臉表情識別綜述[J];計算機(jī)工程與應(yīng)用;2014年20期

相關(guān)博士學(xué)位論文 前1條

1 楊章靜;基于鄰域結(jié)構(gòu)的特征提取及其在人臉識別中的應(yīng)用研究[D];南京理工大學(xué);2014年



本文編號:2367089

資料下載
論文發(fā)表

本文鏈接:http://www.wukwdryxk.cn/shoufeilunwen/xixikjs/2367089.html


Copyright(c)文論論文網(wǎng)All Rights Reserved | 網(wǎng)站地圖 |

版權(quán)申明:資料由用戶fafb4***提供,本站僅收錄摘要或目錄,作者需要刪除請E-mail郵箱bigeng88@qq.com
131美女爱做视频免费 | 久久综合丝袜日本网| 久久精品中文无码资源站| 影音先锋女人av女色资源| 鄂托克前旗| 日韩免费电影| 日韩综合在线| 在线成人小视频| 被男友按住猛啪好爽| 亚洲欧美熟女| 快播色图| 亚洲色图p| 9久9久9久女女女九九九一九| 波多野结衣AV一区二区全免费观看| 久久久精品国产亚洲AV网10| 精品福利一区二区视频| 久久东京热人妻无码人AV| 亚洲色图15p| 国产av影视| 亚洲成人免费| 精品无码一区二区三区亚洲| 97av| 一级做a爱久久久久久久| 欧美h视频| 国产av自拍一区| 夜夜嗨网站| 欧美一本| 日韩中文一区| 亚洲爱情小岛1号线和2号线入口| 先锋影音在线资源| 黄色午夜| 精品欧美一区二区三区| av高清在线| 综合一区| 九色国产精品入口| 排列组合中的c和a怎么理解| 内射少妇视频| 国产一区二区欧美| 麻豆亚洲| 野花论坛高清| 亚洲精品国产一二三无码AV |