發(fā)布時間：2018-01-10 14:03

  本文關(guān)鍵詞：復(fù)雜場景下的多視角人臉檢測方法研究　出處：《江蘇大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 多視角人臉檢測 聚合通道特征 判別權(quán)重池化特征 判別投影HAAR特征 局部模塊字典

【摘要】：復(fù)雜場景下的人臉分析和理解是計算機(jī)視覺與模式識別領(lǐng)域的一個重要研究問題,在視頻人物檢索、智能視頻監(jiān)控、人機(jī)交互和智能安防等領(lǐng)域有廣泛的應(yīng)用前景和巨大的市場需求。人臉檢測是人臉分析的核心技術(shù)和應(yīng)用基礎(chǔ),然而由于視角、形變、光照和遮擋等外部因素,使得人臉檢測成為一個極具挑戰(zhàn)性的研究課題。本文針對真實場景中的人臉視角變化問題,著重研究基于多通道圖特征的多視角人臉檢測算法,該方法可以有效抑制圖像背景中噪聲信息,提高人臉檢測精度和速度。本文的主要工作如下:(1)針對復(fù)雜環(huán)境下的人臉受外界多種復(fù)雜因素影響,導(dǎo)致聚合通道特征檢測率不高的問題,提出一種判別權(quán)重池化特征用于多視角人臉檢測。該方法以多通道圖特征為基礎(chǔ),引入了具有強(qiáng)判別性的中間層矩形濾波器,從而提高了特征的判別能力。該濾波器基于平均人臉形狀統(tǒng)計信息,并利用線性判別分析及其改進(jìn)的不平衡嵌入算法學(xué)習(xí)正負(fù)訓(xùn)練樣本的分布信息。在FDDB數(shù)據(jù)庫上通過與原始多通道特征和一些主流算法的對比,驗證了本文方法的有效性。(2)針對傳統(tǒng)HAAR特征檢測率不高,以及正負(fù)訓(xùn)練樣本分布的不平衡問題,提出一種基于多通道圖的判別投影HAAR特征(PHF)的多視角人臉檢測算法。該方法首先計算人臉訓(xùn)練樣本的底層多通道圖,其次基于正負(fù)訓(xùn)練樣本利用線性判別投影學(xué)習(xí)增強(qiáng)型HAAR特征對底層ACF特征圖進(jìn)行濾波,并利用非對稱AdaBoost算法選出具有強(qiáng)判別性的PHF特征,有效的抑制了正負(fù)樣本空間的不平衡問題。實驗結(jié)果表明,本文方法和當(dāng)前已有主流方法相比,有更高的檢測精度和更快的檢測速度。(3)針對不同人臉視角下部分臉部局部結(jié)構(gòu)相對穩(wěn)定的特點(diǎn),提出一種基于人臉局部模塊字典的多視角人臉檢測算法。該方法首先把人臉局部結(jié)構(gòu)用方向梯度直方圖(HOG)特征來表示,然后通過聚類算法得到具有相似語義類別的顯著臉部局部模塊,再用支持向量機(jī)分別訓(xùn)練不同的人臉局部模塊的多個分類器。在檢測階段用霍夫投票處理各模塊分類器的檢測結(jié)果,得出人臉位置。實驗結(jié)果表明,該方法可以有效提高檢測率。
[Abstract]:Face analysis and understanding in complex scenes is an important research problem in the field of computer vision and pattern recognition, in video character retrieval, intelligent video surveillance. Face detection is the core technology and application foundation of face analysis, but due to external factors such as angle of view, deformation, illumination and occlusion. Face detection has become a very challenging research topic. This paper focuses on multi-view face detection algorithm based on multi-channel graph features. This method can effectively suppress the noise information in the image background and improve the accuracy and speed of face detection. The main work of this paper is as follows: (1) face in complex environment is affected by many external complex factors. Due to the problem of low detection rate of aggregate channel features, a new method based on multi-channel image features is proposed for multi-view face detection. A strong discriminant middle layer rectangular filter is introduced to improve the discriminant ability of the feature. The filter is based on the average face shape statistics. We use linear discriminant analysis and its improved unbalanced embedding algorithm to study the distribution information of positive and negative training samples, and compare with the original multi-channel features and some mainstream algorithms in FDDB database. Verify the effectiveness of this method. 2) aiming at the traditional HAAR feature detection rate is not high, and the distribution of positive and negative training samples is not balanced. A multi-view face detection algorithm based on multi-channel graph based discriminant projection HAAR feature is proposed. Firstly, the bottom multi-channel graph of face training sample is calculated. Secondly, based on the positive and negative training samples, the bottom ACF feature map is filtered by linear discriminant projection learning enhanced HAAR feature. The asymmetric AdaBoost algorithm is used to select the strong discriminant PHF features, which can effectively suppress the imbalance problem in the positive and negative sample space. The experimental results show that. Compared with the current mainstream methods, this method has higher detection accuracy and faster detection speed. A multi-view face detection algorithm based on face local module dictionary is proposed. Firstly, the local structure of the face is represented by the direction gradient histogram (hog) feature. Then the significant facial local modules with similar semantic categories are obtained by clustering algorithm. Then support vector machine is used to train multiple classifiers of different face local modules. In the detection stage, Hough votes are used to deal with the detection results of each module classifier, and the face position is obtained. The experimental results show that. This method can effectively improve the detection rate.
【學(xué)位授予單位】：江蘇大學(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 何春;;人臉識別技術(shù)綜述[J];智能計算機(jī)與應(yīng)用;2016年05期

2 楊恒;張再軍;楊東;張儒良;;融合YCbCr膚色模型與區(qū)域標(biāo)記的人臉檢測算法研究[J];軟件導(dǎo)刊;2016年02期

3 葉繼華;萬葉晶;劉長紅;李漢曦;王仕民;;基于多子空間直和特征融合的人臉識別算法[J];數(shù)據(jù)采集與處理;2016年01期

4 胡昭華;趙孝磊;徐玉偉;何軍;;一種新的低秩分塊稀疏表示的人臉識別算法[J];數(shù)據(jù)采集與處理;2015年05期

5 楊軍;袁紅照;劉妍麗;;基于樣本擴(kuò)張和雙子空間決策融合的單樣本人臉識別算法[J];數(shù)據(jù)采集與處理;2015年01期

6 邱姍姍;;決策樹分類算法分析課程成績——促進(jìn)《計算機(jī)基本操作技術(shù)》課程體系改革[J];數(shù)字技術(shù)與應(yīng)用;2014年09期

7 李理;李偉生;;一種基于改進(jìn)樣本選取的快速人臉檢測方法[J];計算機(jī)應(yīng)用與軟件;2010年07期

8 董立新;;基于先驗知識的人臉檢測算法研究與應(yīng)用[J];數(shù)字技術(shù)與應(yīng)用;2010年01期

9 鄧亞峰;蘇光大;傅博;;一種基于AdaBoost的快速動態(tài)人臉檢測算法[J];計算機(jī)工程;2006年11期

10 江珂;王玲;;運(yùn)用膚色信息和模板匹配的彩色人臉檢測[J];中國測試技術(shù);2006年01期

相關(guān)博士學(xué)位論文 前1條

1 王瓊;人臉與人臉特征檢測技術(shù)研究[D];南京理工大學(xué);2008年

相關(guān)碩士學(xué)位論文 前3條

1 年雪潔;面向靜態(tài)圖片行人檢測的局部特征學(xué)習(xí)方法應(yīng)用研究[D];東南大學(xué);2016年

2 許倩茹;多視人臉檢測技術(shù)研究[D];東南大學(xué);2015年

3 馬穎哲;多視角人臉檢測技術(shù)的研究[D];遼寧工程技術(shù)大學(xué);2010年

，

本文編號：1405523