本文選題：表情識(shí)別 + 隨機(jī)森林��； 參考：《電子科技大學(xué)》2013年碩士論文

【摘要】：人臉表情是人際溝通過(guò)程中一種非常重要的信息表達(dá)方式，能夠傳遞很多文字和聲音所不能表達(dá)的信息。人臉表情識(shí)別研究有非常重要的社會(huì)和經(jīng)濟(jì)意義，目前，表情識(shí)別在電子游戲、智能廣告投放、智能人機(jī)交互、遠(yuǎn)程教育、安全駕駛、臨床醫(yī)學(xué)、幼兒教育與護(hù)理、心理學(xué)研究、智能監(jiān)控、圖像合成、動(dòng)漫等方面都有廣泛的應(yīng)用，，且前景非�？捎^。近年來(lái)，隨著表情識(shí)別的應(yīng)用場(chǎng)景日漸推廣和人們對(duì)表情識(shí)別領(lǐng)域的認(rèn)識(shí)加深，表情識(shí)別技術(shù)已成為多個(gè)領(lǐng)域的熱點(diǎn)研究課題。 目前人臉表情識(shí)別的研究主要集中在表情特征提取和表情分類算法研究方面。本文針對(duì)表情圖像序列，提出了基于AAM(ActiveAppearance Model)模型結(jié)合LK(Lucas-Kanade)光流跟蹤算法的序列表情特征提取方法和基于隨機(jī)森林的表情分類方法：首先，采用AAM模型對(duì)中性表情圖像進(jìn)行特征點(diǎn)定位，在后續(xù)圖像幀間采用LK光流跟蹤算法跟蹤AAM人臉特征點(diǎn)；其次，將劇烈表情和中性表情圖像中相應(yīng)的AAM特征點(diǎn)的位移作為表情特征，采用SVM算法訓(xùn)練分類器，進(jìn)行人臉表情運(yùn)動(dòng)單元分類；最后將人臉表情運(yùn)動(dòng)單元作為隨機(jī)森林的輸入進(jìn)行訓(xùn)練得到表情識(shí)別分類器，進(jìn)而對(duì)七種基本表情進(jìn)行識(shí)別。 本課題在Extended Cohn-Kanade人臉圖像序列數(shù)據(jù)庫(kù)進(jìn)行了大量實(shí)驗(yàn)，實(shí)驗(yàn)結(jié)果表明：AAM模型結(jié)合LK跟蹤算法的人臉序列特征提取算法較單純的AAM人臉表特征提取更加精確高效；將圖像序列中終止幀和起始幀之間AAM特征點(diǎn)的位移作為輸入，采用SVM進(jìn)行表情運(yùn)動(dòng)單元(Action Unit，簡(jiǎn)稱AU)識(shí)別的識(shí)別率高達(dá)98%以上；采用人臉表情運(yùn)動(dòng)單元作為表情特征，隨機(jī)森林算法的表情識(shí)別率是97.10%，而相同條件下貝葉斯網(wǎng)絡(luò)的表情識(shí)別率為89.37%。另外，隨機(jī)森林算法在訓(xùn)練和檢測(cè)過(guò)程中都比貝葉斯網(wǎng)絡(luò)快速高效。隨機(jī)森林算法相比目前廣為采用的貝葉斯表情分類算法，在表情識(shí)別率和算法效率方面都有很大提高。
[Abstract]:Facial expression is a very important way to express information in the process of interpersonal communication. It can convey many messages that can not be expressed by words and sounds.The research of facial expression recognition has very important social and economic significance. At present, facial expression recognition is used in video games, intelligent advertising, intelligent human-computer interaction, distance education, safe driving, clinical medicine, early childhood education and nursing.Psychological research, intelligent monitoring, image synthesis, animation and other aspects have a wide range of applications, and the prospects are very impressive.In recent years, expression recognition technology has become a hot research topic in many fields with the increasing application of expression recognition scene and the deepening of people's understanding of the expression recognition field.At present, the research of facial expression recognition mainly focuses on facial expression feature extraction and facial expression classification algorithm.In this paper, an expression feature extraction method based on AAM(ActiveAppearance Model model combined with LKG Lucas-Kanade-based optical flow tracking algorithm and an expression classification method based on random forest are proposed.AAM model is used to locate the neutral facial expression image, and LK optical flow tracking algorithm is used to track the AAM facial feature points between the subsequent image frames. Secondly, the LK optical flow tracking algorithm is used to track the AAM facial feature points.The displacement of the corresponding AAM feature points in the violent expression and neutral facial expression image is taken as the expression feature, and the classifier is trained by SVM algorithm to classify the facial expression motion unit.Finally, the facial expression motion unit is trained as the input of the random forest to obtain the facial expression recognition classifier, and then the seven basic expressions are recognized.A lot of experiments have been done in the Extended Cohn-Kanade face image sequence database. The experimental results show that the feature extraction algorithm based on the Extended Cohn-Kanade model combined with LK tracking algorithm is more accurate and efficient than the simple AAM face table feature extraction algorithm.The displacement of the AAM feature points between the termination frame and the start frame in the image sequence is taken as input, and the recognition rate of the facial expression motion unit (AAM) is up to 98% by using SVM, and the facial expression motion unit is used as the facial expression feature.The expression recognition rate of stochastic forest algorithm is 97.10, while that of Bayesian network is 89.37 under the same conditions.In addition, stochastic forest algorithm is faster and more efficient than Bayesian network in training and detection.Compared with Bayesian expression classification algorithm, stochastic forest algorithm has a great improvement in expression recognition rate and algorithm efficiency.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 于勇;王兆其;夏時(shí)洪;毛天露;;一種姿態(tài)無(wú)關(guān)的人體模型骨骼提取方法[J];計(jì)算機(jī)研究與發(fā)展;2008年07期

2 王tbtb;邱顯杰;王文中;王兆其;;一種視頻驅(qū)動(dòng)的三維人體動(dòng)畫合成方法[J];系統(tǒng)仿真學(xué)報(bào);2007年08期

3 梁路宏,艾海舟,何克忠;基于多模板匹配的單人臉檢測(cè)[J];中國(guó)圖象圖形學(xué)報(bào);1999年10期

本文編號(hào)：1763221