【摘要】：人臉檢測及特征點(diǎn)定位在計算機(jī)視覺研究中有著重要地位,在生活中應(yīng)用也極其廣泛。人臉檢測是指在輸入圖像中檢測是否存在人臉,如果存在,則標(biāo)識出人臉區(qū)域的位置。特征點(diǎn)定位則是在人臉檢測的基礎(chǔ)上,更精確地尋找到臉部的特征點(diǎn)位置。人臉檢測及特征點(diǎn)定位是很多人臉相關(guān)應(yīng)用如表情識別、姿態(tài)估計、人臉動畫合成中的關(guān)鍵步驟,這兩個步驟的性能對其后續(xù)人臉相關(guān)應(yīng)用有重要影響。傳統(tǒng)的人臉檢測及特征點(diǎn)定位方法在訓(xùn)練階段需要進(jìn)行復(fù)雜的特征提取,且魯棒性不佳。本論文致力于簡化特征提取環(huán)節(jié),并構(gòu)造新的特征點(diǎn)定位優(yōu)化方法,進(jìn)一步提高檢測和定位的準(zhǔn)確性和速度。本文對人臉檢測及特征點(diǎn)定位方法進(jìn)行了深入研究。首先,將膚色模型和用深度學(xué)習(xí)方法訓(xùn)練的人臉分類器結(jié)合用于人臉的檢測,在人臉檢測的基礎(chǔ)上,再利用回歸網(wǎng)絡(luò)對檢測結(jié)果不精確的人臉區(qū)域做回歸處理,以獲得更精準(zhǔn)的人臉檢測定位。接下來,根據(jù)回歸后的人臉檢測結(jié)果進(jìn)行特征點(diǎn)定位。特征點(diǎn)定位是采用隨機(jī)森林方法,通過對人臉特征點(diǎn)建立全局約束模型進(jìn)行整體優(yōu)化,利用級聯(lián)回歸結(jié)構(gòu)迭代獲得人臉特征點(diǎn)的精確位置。論文主要研究內(nèi)容如下:1、而本文中通過深度學(xué)習(xí)方法設(shè)計并訓(xùn)練一個人臉分類器網(wǎng)絡(luò),將其與膚色模型相結(jié)合,能夠更有效地檢測出復(fù)雜場景下的人臉,且避免了顯式的特征設(shè)計和提取環(huán)節(jié)。2、針對前一步驟人臉檢測環(huán)節(jié)中可能出現(xiàn)的檢測精度不高的情況,設(shè)計了一個回歸網(wǎng)絡(luò),利用回歸網(wǎng)絡(luò)對檢測結(jié)果進(jìn)行回歸校正以獲得更精確的檢測定位。3、特征點(diǎn)定位初始階段將根據(jù)人臉檢測結(jié)果給特征點(diǎn)賦予初始坐標(biāo),因此,一個精確的人臉檢測結(jié)果對于提升特征點(diǎn)定位的速度和精度有重要作用。本文首先訓(xùn)練隨機(jī)森林模型實(shí)現(xiàn)對特征點(diǎn)定位重要特征的篩選,之后對人臉特征點(diǎn)建立全局約束模型,用最小二乘方法對全局模型參數(shù)進(jìn)行整體優(yōu)化,最后利用級聯(lián)回歸結(jié)構(gòu)進(jìn)行迭代獲得人臉特征點(diǎn)的精準(zhǔn)定位。實(shí)驗(yàn)結(jié)果表明,改進(jìn)的人臉檢測及特征點(diǎn)定位系統(tǒng)能夠有效提高復(fù)雜環(huán)境下人臉檢測及特征點(diǎn)定位的性能,在保證魯棒性及較高定位精度的前提下,還擁有接近實(shí)時的較高檢測及定位速度。
[Abstract]:Face detection and feature location play an important role in computer vision research and are widely used in daily life. Face detection is to detect the presence of a face in an input image and, if so, to identify the location of the face region. On the basis of face detection, feature point location is more accurately located. Face detection and feature location are the key steps in many human face related applications such as facial expression recognition, pose estimation and face animation synthesis. The performance of these two steps plays an important role in the subsequent face related applications. The traditional face detection and feature point localization methods need complex feature extraction in the training stage, and the robustness is not good. This paper is devoted to simplify feature extraction and construct a new method of feature location optimization to further improve the accuracy and speed of detection and location. In this paper, the methods of face detection and feature point location are studied. Firstly, the skin color model and the face classifier trained by the depth learning method are combined for face detection. Then, based on the face detection, the regression network is used to deal with the face region with inaccurate detection results. In order to obtain more accurate face detection location. Then, the feature points are located according to the result of face detection after regression. The feature point location is based on the stochastic forest method. The global constraint model is established for the face feature points and the exact location of the face feature points is obtained by cascading regression structure iterations. The main contents of this paper are as follows: 1. In this paper, a human face classifier network is designed and trained by the deep learning method, which is combined with the skin color model to detect the human face in the complex scene more effectively. And avoid the explicit feature design and extraction link. 2. Aiming at the situation that the detection accuracy may not be high in the previous step face detection link, a regression network is designed. Regression network is used to correct the detection results to obtain more accurate detection location. The initial phase of feature point location will be assigned to the initial coordinates of feature points according to the face detection results, so, An accurate face detection result plays an important role in improving the speed and accuracy of feature point location. In this paper, we first train the stochastic forest model to select important features for feature point location, and then establish a global constraint model for facial feature points, and optimize the global model parameters by using the least square method. Finally, a cascade regression structure is used to iterate to obtain accurate location of face feature points. The experimental results show that the improved face detection and feature point location system can effectively improve the performance of face detection and feature point location in complex environments, while ensuring robustness and high positioning accuracy. It also has high detection and positioning speed near real time.
【學(xué)位授予單位】：重慶理工大學(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10條

1 李昕昕;龔勛;;三維人臉建模及在跨姿態(tài)人臉匹配中的有效性驗(yàn)證[J];計算機(jī)應(yīng)用;2017年01期

2 傅栩雨;葉健東;王鵬;曾穎森;;人臉面部表情識別[J];計算機(jī)與網(wǎng)絡(luò);2015年10期

3 張振海;李士寧;李志剛;陳昊;;一類基于信息熵的多標(biāo)簽特征選擇算法[J];計算機(jī)研究與發(fā)展;2013年06期

4 杜杏菁;王曉菊;;人臉識別中局部遮擋處理技術(shù)研究[J];微電子學(xué)與計算機(jī);2012年07期

5 汪寶彬;汪玉霞;;隨機(jī)梯度下降法的一些性質(zhì)(英文)[J];數(shù)學(xué)雜志;2011年06期

6 曹健;劉瓊昕;高春曉;劉玉樹;;角點(diǎn)特征在目標(biāo)識別中的應(yīng)用[J];北京理工大學(xué)學(xué)報;2011年03期

7 者昊;馬若飛;馬義德;;基于高斯模型的人臉檢測算法[J];微計算機(jī)信息;2010年32期

8 丁克良;沈云中;歐吉坤;;整體最小二乘法直線擬合[J];遼寧工程技術(shù)大學(xué)學(xué)報(自然科學(xué)版);2010年01期

9 孟祥萍;武增光;趙玉蘭;;基于紋理結(jié)構(gòu)的指紋識別算法[J];計算機(jī)工程與設(shè)計;2009年13期

10 寧凡;厲星星;;基于人臉幾何結(jié)構(gòu)的表情識別[J];計算機(jī)應(yīng)用與軟件;2009年06期

相關(guān)博士學(xué)位論文 前1條

1 陸麗;基于人臉圖像的性別識別與年齡估計研究[D];上海交通大學(xué);2010年

，

本文編號：2239317