發(fā)布時間：2018-03-05 07:16

  本文選題：魯棒關(guān)鍵點定位　切入點：深度學習　出處：《北京交通大學》2017年碩士論文　論文類型：學位論文

【摘要】：隨著計算機技術(shù)的飛速發(fā)展,作為情感計算的一個重要方向,人臉表情識別逐漸成為研究的熱點課題。近幾年,深度學習的研究取得了突破性的進展,為其他研究領域帶來了創(chuàng)新和突破的機遇。本文針對人臉表情識別所涉及的特征點定位技術(shù)進行了深入研究�；谏疃染矸e神經(jīng)網(wǎng)絡的非線性映射能力,實現(xiàn)和對比了三種基于不同網(wǎng)絡結(jié)構(gòu)的面部關(guān)鍵點定位算法,并將其與傳統(tǒng)面部關(guān)鍵點定位算法進行了對比�？紤]到表情關(guān)鍵點在人臉表情運動單元內(nèi)的共生性,提出了一種新的基于多任務深度學習的魯棒表情共生點檢測及強度估計算法。論文的主要內(nèi)容包括以下三個方面:(1)為了與基于深度學習的特征點定位算法對比,本文研究并實現(xiàn)了傳統(tǒng)主動形狀模型(ASM)和魯棒級聯(lián)形狀回歸(RCPR)算法。ASM算法是一種基于統(tǒng)計學的可變形模型,該方法通過訓練建立可形變的模型,利用仿射變換參數(shù)的更新對局部紋理模型的特征點進行匹配,但該算法不具備對姿態(tài)和遮擋變化的魯棒性。魯棒級聯(lián)形狀回歸(RCPR)算法是在級聯(lián)形狀回歸(CPR)算法基礎上的改進算法,該方法使用回歸模型,并引入人臉形狀索引特征和遮擋檢測,算法具有針對面部形變和遮擋的魯棒性。(2)論文采用卷積神經(jīng)網(wǎng)絡(CNN)結(jié)構(gòu)進行特征學習,研究并對比實現(xiàn)了三種具有魯棒性的面部關(guān)鍵點定位算法,分別是級聯(lián)深度卷積神經(jīng)網(wǎng)絡(DCNN)算法,改進的由粗到精的級聯(lián)深度卷積神經(jīng)網(wǎng)絡(CFCNN)算法以及基于多任務深度學習(TCDCN)算法。DCNN算法采用三級卷積神經(jīng)網(wǎng)絡級聯(lián)的結(jié)構(gòu),利用無監(jiān)督學習對每一級網(wǎng)絡進行逐級訓練,后一級在前一級網(wǎng)絡定位的基礎上微調(diào),該算法可以檢測出5個人臉關(guān)鍵點。CFCNN算法可以定位68個面部關(guān)鍵點,采用相互獨立的級聯(lián)網(wǎng)絡結(jié)構(gòu)分別預測51個內(nèi)點和17個輪廓點,該算法定位精度較高,但對姿態(tài)及遮擋的魯棒性弱。TCDCN算法將多任務學習與深度學習相結(jié)合,采用非級聯(lián)的網(wǎng)絡結(jié)構(gòu),把面部特征點定位作為主要任務,頭部姿態(tài)檢測作為輔助任務,對兩者采用深度卷積神經(jīng)網(wǎng)絡聯(lián)合學習,該算法提高了對姿態(tài)的魯棒性,可對68個面部關(guān)鍵點實現(xiàn)更魯棒、更快的檢測。通過對AVEC 2012微表情庫和自建數(shù)據(jù)集的實驗結(jié)果的分析以及LFPW人臉庫統(tǒng)計學結(jié)果的對比得出,在參與對比分析的五種典型算法中,TCDCN算法的面部關(guān)鍵點定位效果較好,其所檢測得到的面部關(guān)鍵點可作為用于描述表情變化的候選點集。(3)考慮到人臉表情運動單元(AU)內(nèi)部面部關(guān)鍵點的共生性,本文提出了一種新的基于多任務深度學習的魯棒表情共生點檢測及強度估計算法。AU是編碼人類表情變化的基本單元,其內(nèi)部的面部關(guān)鍵點是共生的,且其強度是表情所對應的心理指標(激活度、正負、期望度、強度)的重要描述子。因此,本文所提算法首先采用TCDCN準確定位出面部錨點,以此作為描述表情變化的候選點集,然后同時提取面部的幾何特征和表觀特征形成特征描述子,以AU區(qū)域內(nèi)面部錨點的共生性作為約束,利用支持向量機和支持向量回歸對其進行分類和回歸,其中的分類過程即為魯棒表情共生點的檢測過程,而回歸分析過程則可估計出魯棒表情共生點的強度。SEMAINE和DISFA表情庫上的實驗結(jié)果表明,所提算法可以較好的檢測和定位魯棒表情共生點,并對其強度進行估計。
[Abstract]:With the rapid development of computer technology, as an important direction of affective computing, facial expression recognition has become a hot research topic. In recent years, a breakthrough in the study of deep learning, brings innovation and breakthrough opportunities for other research. Feature point positioning technology this paper relates to the facial expression recognition is studied. The nonlinear mapping ability of depth based on convolutional neural network, implementation and comparison of three kinds of facial key points localization algorithm based on different network structure, and compares it with traditional facial point positioning algorithm. Considering the expression of key point symbiosis in facial expression motion unit, put forward a new robust expression of multi task deep learning symbiotic point detection and intensity estimation algorithm based on the main contents of this paper include the following three aspects: (1) for the Comparison of feature location algorithm based on deep learning, this paper studies and implements the traditional active shape model (ASM) and robust regression (RCPR) cascade shape algorithm.ASM algorithm is a statistical deformable model based on the method of deformable model is established through training, feature point matching using affine transformation parameters to update local texture model, but the algorithm does not have the robustness of attitude change and occlusion. Robust cascade shape regression (RCPR) algorithm is a regression in cascade shape (CPR) algorithm based on the improved algorithm, the method uses regression model, and introduces the face shape index and occlusion detection algorithm has to face deformation and occlusion robustness. (2) the convolutional neural network (CNN) structure characteristics of learning, research and comparison of realized three kinds of robust facial key point positioning algorithm, respectively. Is the depth of cascaded convolutional neural network (DCNN) algorithm, an improved coarse to fine depth concatenated convolutional neural network (CFCNN) and multi task learning algorithm based on depth (TCDCN) structure.DCNN algorithm using three cascaded convolutional neural networks, using unsupervised learning step by step training on each level after a network. In the network location of a previous stage on the basis of fine-tuning, the proposed algorithm can detect 5 face key point.CFCNN algorithm can locate 68 facial key points, using cascade network structure independent of the predicted 51 inner points and 17 contour points, the positioning accuracy is higher, but the attitude and occlusion robust weak.TCDCN algorithm to multi task learning and deep learning combined with network structure of the cascade, the facial features location as the main task, head pose detection as an auxiliary task, to the depth of volume Integrated neural network combined with learning, the algorithm improves the robustness of the attitude, the 68 face a key point to achieve a more robust, faster detection is obtained. By comparing the experimental results of the AVEC 2012 micro expression databases data analysis and LFPW database statistical results, in five typical algorithms comparison in the analysis, good facial key points localization effect of TCDCN algorithm, the key points of the face detection as a candidate for the description of expression. (3) considering the facial expression motion unit (AU) symbiosis internal facial key points, this paper proposes a new robust expression deep learning task symbiotic point detection and intensity estimation algorithm is the basic unit of.AU encoding human expression, the key point is the face of symbiosis, and its strength is the psychological index corresponding expression (activation, Positive expectations, the strength of the important descriptors). Therefore, the proposed algorithm uses the TCDCN accurately locate facial anchor, as a candidate point description of expression set, then extracting geometric features of facial features and the apparent formation characteristic descriptor, the symbiosis as a constraint in the AU region using facial anchor point. Regression classification and regression for the support vector machine and support vector classification process, which is a robust facial expression detection process of symbiosis, and regression analysis process can estimate the robust facial expression intensity of.SEMAINE and DISFA co expression database. The experimental results indicate that the proposed algorithm can detect and locate the robust expression of symbiosis good, and the strength is estimated.

【學位授予單位】：北京交通大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前6條

1 楊斌;鐘金英;;卷積神經(jīng)網(wǎng)絡的研究進展綜述[J];南華大學學報(自然科學版);2016年03期

2 劉建偉;劉媛;羅雄麟;;深度學習研究進展[J];計算機應用研究;2014年07期

3 劉建偉;劉媛;羅雄麟;;玻爾茲曼機研究進展[J];計算機研究與發(fā)展;2014年01期

4 王晶;蘇光大;劉炯鑫;任小龍;;融合改進的ASM和AAM的人臉形狀特征點定位算法[J];光電子.激光;2011年08期

5 趙暉;王志良;劉遙峰;;人臉活動單元自動識別研究綜述[J];計算機輔助設計與圖形學學報;2010年05期

6 董軍,胡上序;混沌神經(jīng)網(wǎng)絡研究進展與展望[J];信息與控制;1997年05期

相關(guān)博士學位論文 前1條

1 杜春華;人臉特征點定位及識別的研究[D];上海交通大學;2008年

相關(guān)碩士學位論文 前3條

1 李凱月;魯棒表情關(guān)鍵點定位系統(tǒng)設計與實現(xiàn)[D];北京交通大學;2016年

2 牛新亞;基于深度學習的人臉表情識別研究[D];華南理工大學;2016年

3 陳元琳;基于人工神經(jīng)網(wǎng)絡的動態(tài)系統(tǒng)仿真模型和算法研究[D];大慶石油學院;2006年

，

本文編號：1569259