發(fā)布時(shí)間：2018-03-20 13:56

  本文選題：微表情數(shù)據(jù)庫(kù)　切入點(diǎn)：面部行為編碼系統(tǒng)　出處：《山東大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：微表情是一種不受心理控制的面部表情,具有持續(xù)時(shí)間短暫、變化幅度微弱、動(dòng)作區(qū)域較少等明顯區(qū)別于宏表情的特點(diǎn)。當(dāng)前微表情在國(guó)家安全、司法審訊、謊言測(cè)試等領(lǐng)域潛在的應(yīng)用價(jià)值引起了人們極大的關(guān)注。隨著計(jì)算機(jī)模式識(shí)別技術(shù)的發(fā)展微表情相關(guān)研究取得了很多成果,但作為研究基礎(chǔ)的微表情數(shù)據(jù)庫(kù)由于微表情捕捉困難、采集過(guò)程復(fù)雜、人工編碼費(fèi)時(shí)耗力和圖像質(zhì)量評(píng)價(jià)標(biāo)準(zhǔn)缺失等原因?qū)е聰?shù)據(jù)庫(kù)樣本數(shù)量不足,質(zhì)量參差不齊,越來(lái)越無(wú)法滿(mǎn)足微表情研究工作。同時(shí)由于微表情自動(dòng)檢測(cè)技術(shù)發(fā)展滯后,無(wú)法有效的輔助復(fù)雜的人工編碼,在很大程度上也制約了微表情數(shù)據(jù)庫(kù)建立工作的進(jìn)一步發(fā)展。針對(duì)上述問(wèn)題,本文深入分析了現(xiàn)有微表情數(shù)據(jù)庫(kù)的特點(diǎn),通過(guò)合理設(shè)置實(shí)驗(yàn)環(huán)境,改進(jìn)實(shí)驗(yàn)方法等措施,建立了目前樣本數(shù)量最大、種類(lèi)齊全、圖像分辨率較高的SDU微表情數(shù)據(jù)庫(kù);隨后應(yīng)用不同方法從不同角度對(duì)該數(shù)據(jù)庫(kù)樣本進(jìn)行了質(zhì)量評(píng)價(jià);最后結(jié)合微表情的表達(dá)特點(diǎn),提出兩種微表情自動(dòng)檢測(cè)方法:基于特征點(diǎn)集群形變矢量的微表情檢測(cè)法和基于感興趣區(qū)域光流特征矢量的幅值和角度信息的微表情檢測(cè)法。本文的主要工作和創(chuàng)新點(diǎn)包括以下幾個(gè)方面:第一,微表情數(shù)據(jù)庫(kù)建立過(guò)程中,在微表情誘發(fā)素材選擇和環(huán)境設(shè)置上獲得了心理學(xué)博士的專(zhuān)業(yè)指導(dǎo),實(shí)驗(yàn)器材選擇視頻質(zhì)量各項(xiàng)指標(biāo)相對(duì)優(yōu)越的攝像器材,同時(shí)吸收心理學(xué)專(zhuān)業(yè)學(xué)生參與樣本分析處理,最大限度地保證微表情樣本的質(zhì)量,最終建立了包含300個(gè)樣本7種情緒類(lèi)型的SDU微表情數(shù)據(jù)庫(kù)。該數(shù)據(jù)庫(kù)樣本相對(duì)其他數(shù)據(jù)庫(kù)具有分類(lèi)全面、質(zhì)量?jī)?yōu)良、數(shù)量最多的特點(diǎn),可以為微表情檢測(cè)和識(shí)別工作提供良好的實(shí)驗(yàn)素材。第二,針對(duì)當(dāng)前微表情數(shù)據(jù)庫(kù)建立標(biāo)準(zhǔn)缺失,樣本質(zhì)量參差不齊的現(xiàn)狀,首次提出微表情數(shù)據(jù)庫(kù)的質(zhì)量評(píng)估方法。該方法包括主觀(guān)評(píng)價(jià)法、客觀(guān)評(píng)價(jià)法和提取特征值分析法,每種評(píng)價(jià)方法分別從分辨率、幀率和編碼比特率等指標(biāo)分析評(píng)價(jià)了 SDU微表情數(shù)據(jù)庫(kù)質(zhì)量。根據(jù)各種方法的評(píng)價(jià)結(jié)果初步得出微表情數(shù)據(jù)庫(kù)質(zhì)量與各指標(biāo)相關(guān)性大小。第三,針對(duì)當(dāng)前微表情數(shù)據(jù)庫(kù)建立過(guò)程中人工編碼耗時(shí)費(fèi)力的現(xiàn)狀,提出兩種微表情自動(dòng)檢測(cè)方法,一種是基于回歸樹(shù)集合思想提取人臉68個(gè)特征點(diǎn)后將其劃分到不同的特征群,通過(guò)設(shè)置合理的閾值分析對(duì)比特征群形變規(guī)律來(lái)檢測(cè)微表情;一種是應(yīng)用聯(lián)合級(jí)聯(lián)法對(duì)齊人臉并將人臉劃分為幾個(gè)不同感興趣區(qū)域,統(tǒng)計(jì)各各感興趣區(qū)域微表情光流特征矢量分布規(guī)律后設(shè)定閾值,再利用光流法提取樣本各檢測(cè)區(qū)光流特征矢量的幅值和角度信息,通過(guò)與閾值對(duì)比后檢測(cè)是否發(fā)生微表情。最后兩種檢測(cè)方法在SDU微表情數(shù)據(jù)庫(kù)和CASMEII微表情數(shù)據(jù)庫(kù)上進(jìn)行檢測(cè)實(shí)驗(yàn)后均獲得了良好的實(shí)驗(yàn)結(jié)果。
[Abstract]:Microfacial expression is a kind of facial expression which is not controlled by psychology. It has the characteristics of short duration, weak range of change, less movement area and so on, which is obviously different from macro expression. The potential application value of lie testing and other fields has attracted great attention. With the development of computer pattern recognition technology, many achievements have been made in the research of micro-expression correlation. However, the microfacial expression database, which is the basis of the research, is difficult to capture, the process of collecting is complicated, the manual coding is time-consuming and the evaluation standard of image quality is missing and so on, which leads to the lack of sample quantity and the uneven quality of the database. At the same time, because the development of automatic microfacial expression detection technology lags behind, it is unable to effectively assist the complex manual coding. To a great extent, it restricts the further development of the establishment of microfacial expression database. In view of the above problems, this paper deeply analyzes the characteristics of the existing microfacial expression database, through setting up the experimental environment reasonably, improving the experimental method, and so on. The SDU microfacial expression database with the largest sample size, complete variety and high image resolution is established. Then, the quality of the sample is evaluated from different angles by different methods. Finally, the expression characteristics of microemoji are combined. Two automatic microfacial expression detection methods are proposed: one is based on feature point cluster deformation vector and the other is based on amplitude and angle information of optical flow feature vector in the region of interest. Innovations include the following: first, In the process of establishing the microfacial expression database, the professional guidance of PhD in psychology was obtained in the selection of microfacial expression inducing material and the setting of environment, and the experimental equipment was used to select the camera equipment with relatively superior video quality indexes. At the same time, students majoring in psychology are involved in sample analysis to maximize the quality of microfacial expression samples. Finally, a SDU microemoji database containing 300 samples and 7 emotion types was established, which has the characteristics of comprehensive classification, excellent quality and maximum quantity compared with other databases. It can provide good experimental material for microfacial expression detection and recognition. Second, aiming at the current situation of the lack of standards and uneven sample quality in the microfacial expression database, The quality evaluation method of microfacial expression database is proposed for the first time. The method includes subjective evaluation method, objective evaluation method and eigenvalue analysis method. The quality of SDU microfacial expression database is analyzed and evaluated by frame rate and coding bit rate. According to the evaluation results of various methods, the correlation between the quality of microfacial expression database and each index is preliminarily obtained. In view of the time-consuming and laborious manual coding in the establishment of microfacial expression database, two automatic microfacial expression detection methods are proposed. One is to extract 68 facial feature points based on the idea of regression tree set and divide them into different feature groups. The microexpressions are detected by setting a reasonable threshold to analyze and compare the deformation of feature groups. One is to align the faces and divide them into several different regions of interest by using the joint cascade method. The characteristic vector distribution of micro-expression optical flow in each region of interest is analyzed and the threshold is set. Then the amplitude and angle information of the characteristic vector of optical flow are extracted by optical flow method. The last two methods were tested on SDU microfacial expression database and CASMEII microfacial expression database, and good experimental results were obtained.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孫正,郁道銀,陳曉冬,徐智,黃家祥,謝洪波;基于光流法的冠狀動(dòng)脈造影圖像序列中血管運(yùn)動(dòng)的估計(jì)[J];工程圖學(xué)學(xué)報(bào);2003年03期

2 韓雷;王洪慶;林隱靜;;光流法在強(qiáng)對(duì)流天氣臨近預(yù)報(bào)中的應(yīng)用[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年05期

3 龔大墉;汪治華;楊數(shù)強(qiáng);劉巖;;基于目標(biāo)的局部約束光流分析[J];重慶工學(xué)院學(xué)報(bào)(自然科學(xué)版);2009年07期

4 嚴(yán)強(qiáng);黃增喜;曹麗萍;黃蓉剛;;光流法在機(jī)車(chē)安全行駛中的應(yīng)用[J];計(jì)算機(jī)應(yīng)用研究;2013年04期

5 馬鵬飛;楊金孝;;基于光流法的粒子圖像測(cè)速[J];科學(xué)技術(shù)與工程;2012年32期

6 張永亮;盧煥章;賀興華;謝耀華;;基于光流預(yù)測(cè)的直線(xiàn)對(duì)應(yīng)算法[J];信號(hào)處理;2010年05期

7 孫承志;熊田忠;吉順平;張家海;;基于差分的光流法在目標(biāo)檢測(cè)跟蹤中的應(yīng)用[J];機(jī)床與液壓;2010年14期

8 王，

本文編號(hào)：1639371