發(fā)布時(shí)間：2018-06-22 19:52

  本文選題：人臉識(shí)別 + 光照不變量��； 參考：《浙江大學(xué)》2016年博士論文

【摘要】：人臉識(shí)別作為一種非接觸式的生物特征識(shí)別技術(shù),在軍事、經(jīng)濟(jì)、公安等領(lǐng)域具有廣闊的應(yīng)用前景。目前人臉識(shí)別技術(shù)已經(jīng)成為模式識(shí)別、計(jì)算機(jī)視覺、圖像處理、神經(jīng)網(wǎng)絡(luò)等領(lǐng)域的一個(gè)研究熱點(diǎn)。由于人臉圖像容易受到光照、表情等多種變化因素的影響,導(dǎo)致人臉識(shí)別研究復(fù)雜而艱巨,是一項(xiàng)極富挑戰(zhàn)性的研究課題。其中,光照條件的變化對(duì)于人臉圖像的影響更是一個(gè)非常突出的問題。本文以減弱和消除復(fù)雜光照的影響、提高人臉的識(shí)別率為目的,從光照預(yù)處理、特征提取、分類識(shí)別這三個(gè)角度對(duì)人臉識(shí)別系統(tǒng)進(jìn)行優(yōu)化和改進(jìn)。同時(shí),由于目前人類逐步邁入大數(shù)據(jù)時(shí)代,人臉識(shí)別的訓(xùn)練樣本量呈指數(shù)級(jí)增加,本文也對(duì)大數(shù)據(jù)情況下的最優(yōu)化算法進(jìn)行了一定的探討。下面概述本文的主要研究?jī)?nèi)容。1.基于自適應(yīng)導(dǎo)引圖像濾波器的光照不變量提取算法在人臉識(shí)別系統(tǒng)中,對(duì)復(fù)雜光照條件進(jìn)行預(yù)處理的目的是希望將光照的影響去除,得到人臉的本來特征,即人臉圖像的光照不變量。自熵圖像法是一種基于朗伯光照模型的光照不變量提取算法,該算法能夠顯著提高復(fù)雜光照條件下的人臉識(shí)別率,并且具有極低的計(jì)算復(fù)雜度。但是,該方法仍然存在一些缺點(diǎn),例如在低信噪比區(qū)域會(huì)放大高頻噪聲,很難保留良好的邊緣信息等。在本論文中,針對(duì)自熵圖像法的缺陷,提出了基于自適應(yīng)導(dǎo)引圖像濾波器的自熵圖像算法,該算法能夠根據(jù)圖像的內(nèi)容自動(dòng)地改變?yōu)V波器的系數(shù),從而降低高頻噪聲,也能夠更好地保留邊緣信息,對(duì)于關(guān)鍵部位尤其是眼睛、鼻子、嘴巴等對(duì)最終的人臉識(shí)別率有關(guān)鍵影響力的部位,能夠非常有效地強(qiáng)化其光照不變特征,從而提高最終的人臉識(shí)別率。2.基于自學(xué)習(xí)的局部特征提取方法良好的人臉表示是高效人臉識(shí)別算法的關(guān)鍵因素,也是處理光照干擾的重要手段。局部特征提取算法是目前主流的特征提取方法,局部特征描述局部像素點(diǎn)的變化,并對(duì)這些局部模式進(jìn)行統(tǒng)計(jì),這是一種非常簡(jiǎn)潔有效的表示方法,但是該方法在進(jìn)行局部像素點(diǎn)描述的時(shí)候采用的是基于人為經(jīng)驗(yàn)的固定采樣模式。本文提出了一種基于自學(xué)習(xí)的局部特征提取方法,通過自學(xué)習(xí)的方式對(duì)采樣模式進(jìn)行最優(yōu)化的選擇,解決了傳統(tǒng)的局部特征提取方法中需要通過人為經(jīng)驗(yàn)進(jìn)行采樣模式設(shè)置這一問題,進(jìn)一步縮小了來自同一人臉的圖像之間的類內(nèi)差異,增大了不同人臉圖像之間的類間差異,從而提高了最終的人臉識(shí)別率,并且具有更好的對(duì)光照、表情和姿態(tài)的魯棒性。3.基于統(tǒng)一準(zhǔn)則的特征提取和分類方法分類識(shí)別和特征提取是人臉識(shí)別系統(tǒng)中相對(duì)獨(dú)立的兩個(gè)模塊,在很多的研究中,也將兩者分開進(jìn)行優(yōu)化,然而,作為人臉識(shí)別系統(tǒng)的一部分,這兩部分之間仍然具有緊密的聯(lián)系,二者相輔相成,好的特征能夠增強(qiáng)分類器的作用,好的分類器也能夠幫助區(qū)分人臉特征。在本文中,詳細(xì)分析了這兩個(gè)模塊的內(nèi)在原理,并且提出了統(tǒng)一的內(nèi)在衡量標(biāo)準(zhǔn),即點(diǎn)到子空間的距離。并提出了遵循該標(biāo)準(zhǔn)的特征提取和分類識(shí)別方法,實(shí)驗(yàn)結(jié)果表明,基于點(diǎn)到子空間距離的特征提取及分類方法能夠增強(qiáng)人臉識(shí)別系統(tǒng)對(duì)于光照的魯棒性,并能夠有效提高最終的人臉識(shí)別率。4.適用于大樣本量的擬牛頓小批量最優(yōu)化算法在人臉識(shí)別系統(tǒng)中,無論是特征的自學(xué)習(xí)還是分類器的訓(xùn)練,一般都包含著求最優(yōu)解的過程,而隨著科技的發(fā)展,人們逐漸進(jìn)入大數(shù)據(jù)時(shí)代,數(shù)據(jù)量的指數(shù)級(jí)增加給現(xiàn)有的最優(yōu)化算法提出了新的挑戰(zhàn)。本文對(duì)在大數(shù)據(jù)下的最優(yōu)化算法做了一定的探討,提出了一種適用于大數(shù)據(jù)問題的擬牛頓小批量最優(yōu)化算法。該方法隨機(jī)地選取小批量樣本進(jìn)行參數(shù)的計(jì)算,并用迭代的方式訓(xùn)練出最終的分類模型,使用小批量隨機(jī)樣本能夠有效地解決計(jì)算量過大的問題,在保持最終識(shí)別率的情況下大大減少了訓(xùn)練的時(shí)間。
[Abstract]:Face recognition, as a non-contact biological feature recognition technology, has a wide application prospect in military, economic, public security and other fields. Face recognition technology has become a hot spot in the fields of pattern recognition, computer vision, image processing, neural network, etc. because face images are easily exposed to light, expression and so on. The influence of change factors leads to the complexity and arduous research of face recognition, which is a very challenging research topic. Among them, the influence of light conditions on face image is a very prominent problem. In this paper, the aim of reducing and eliminating the influence of complex illumination and improving the recognition rate of human face is to preprocessing from light and feature extraction. At the same time, the training sample size of face recognition is increased exponentially, and the optimization algorithm under large data is also discussed in this paper. The main research content of this paper.1. is based on.1.. In the face recognition system, the aim of preprocessing the complex illumination conditions is to remove the influence of light, and get the original feature of the face, that is the invariant of the illumination of the face image. The self entropy image method is a kind of illumination invariant extraction based on the Lambert light model. The algorithm can significantly improve the face recognition rate under complex illumination conditions and have very low computational complexity. However, this method still has some shortcomings, for example, it can enlarge the high frequency noise in the low signal to noise ratio region, and it is difficult to retain the good edge information. In this paper, the basis for the defects of the self entropy image method is proposed. The self entropy image algorithm of adaptive guided image filter can automatically change the filter's coefficient according to the content of the image, thus reduce the high frequency noise, and can better retain the edge information. For the key parts, especially the eyes, nose, mouth and so on, it has the key influence on the final face recognition rate. It is very effective to strengthen the invariant features of light illumination, thus improving the final face recognition rate,.2. based on self learning local feature extraction method, good face representation is the key factor of efficient face recognition algorithm, and also an important means of processing light interference. Local feature extraction is the main feature extraction method at present, local special feature extraction method is a local special method. This is a very concise and effective representation method, which is a very concise and effective representation. However, this method uses a fixed sampling mode based on artificial experience when the local pixel is described. This paper proposes a local feature extraction method based on self learning, which is self-taught by self-learning. The way to optimize the sampling mode is to solve the problem that the traditional local feature extraction method needs to set this problem through the artificial experience sampling mode, which further reduces the intra class difference between the images from the same face, and increases the difference among the different face images, thus improving the final result. Face recognition rate, and has better robustness to light, expression and attitude..3. based on unified criteria feature extraction and classification recognition and feature extraction are two relatively independent modules in face recognition system. In many studies, the two are also divided into line optimization. However, as one of the face recognition systems, The two parts are still closely related, the two are complementary, the good features can enhance the function of the classifier, and the good classifier can also help to distinguish the face features. In this paper, the internal principles of the two modules are analyzed in detail, and a unified internal measurement standard is proposed, that is, the distance from the point to the subspace. The experimental results show that the feature extraction and classification method based on the point to subspace distance can enhance the robustness of the face recognition system to the illumination, and can effectively improve the final face recognition rate,.4., which is suitable for the large sample size of the quasi Newton small batch optimization algorithm. In the face recognition system, both the self learning of the feature and the training of the classifier generally include the process of finding the optimal solution. With the development of science and technology, people are gradually entering the era of large data. The exponential increase of the amount of data gives a new challenge to the existing optimization algorithms. This paper has done the optimization algorithm under the large data. In a certain way, a quasi Newton small batch optimization algorithm suitable for large data problems is proposed. This method randomly selects small batch samples to calculate the parameters, and trains the final classification model in an iterative way. Using small batch random samples can effectively solve the problem of excessive calculation and keep the final recognition. In the case of rate, the time of training is greatly reduced.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馬少華,高峰,李敏,吳成東;神經(jīng)網(wǎng)絡(luò)分類器的特征提取和優(yōu)選[J];基礎(chǔ)自動(dòng)化;2000年06期

2 管聰慧,宣國(guó)榮;多類問題中的特征提取[J];計(jì)算機(jī)工程;2002年01期

3 胡威;李建華;陳波;;入侵檢測(cè)建模過程中特征提取最優(yōu)化評(píng)估[J];計(jì)算機(jī)工程;2006年12期

4 朱玉蓮;陳松燦;趙國(guó)安;;推廣的矩陣模式特征提取方法及其在人臉識(shí)別中的應(yīng)用[J];小型微型計(jì)算機(jī)系統(tǒng);2007年04期

5 趙振勇;王保華;王力;崔磊;;人臉圖像的特征提取[J];計(jì)算機(jī)技術(shù)與發(fā)展;2007年05期

6 馮海亮;王麗;李見為;;一種新的用于人臉識(shí)別的特征提取方法[J];計(jì)算機(jī)科學(xué);2009年06期

7 朱笑榮;楊德運(yùn);;基于入侵檢測(cè)的特征提取方法[J];計(jì)算機(jī)應(yīng)用與軟件;2010年06期

8 王菲;白潔;;一種基于非線性特征提取的被動(dòng)聲納目標(biāo)識(shí)別方法研究[J];軟件導(dǎo)刊;2010年05期

9 陳偉;瞿曉;葛丁飛;;主觀引導(dǎo)特征提取法在光譜識(shí)別中的應(yīng)用[J];科技通報(bào);2011年04期

10 王華,李介谷;人臉斜視圖象的特征提取與恢復(fù)[J];上海交通大學(xué)學(xué)報(bào);1997年01期

相關(guān)會(huì)議論文 前10條

1 尚修剛;蔣慰孫;;模糊特征提取新算法[A];1997中國(guó)控制與決策學(xué)術(shù)年會(huì)論文集[C];1997年

2 潘榮江;孟祥旭;楊承磊;王銳;;旋轉(zhuǎn)體的幾何特征提取方法[A];第一屆建立和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會(huì)議（HHME2005）論文集[C];2005年

3 薛燕;李建良;朱學(xué)芳;;人臉識(shí)別中特征提取的一種改進(jìn)方法[A];第十三屆全國(guó)圖象圖形學(xué)學(xué)術(shù)會(huì)議論文集[C];2006年

4 杜栓平;曹正良;;時(shí)間—頻率域特征提取及其應(yīng)用[A];2005年全國(guó)水聲學(xué)學(xué)術(shù)會(huì)議論文集[C];2005年

5 黃先鋒;韓傳久;陳旭;周劍軍;;運(yùn)動(dòng)目標(biāo)的分割與特征提取[A];全國(guó)第二屆信號(hào)處理與應(yīng)用學(xué)術(shù)會(huì)議�？痆C];2008年

6 魏明果;;方言比較的特征提取與矩陣分析[A];2009系統(tǒng)仿真技術(shù)及其應(yīng)用學(xué)術(shù)會(huì)議論文集[C];2009年

7 林土勝;賴聲禮;;視網(wǎng)膜血管特征提取的拆支跟蹤法[A];1999年中國(guó)神經(jīng)網(wǎng)絡(luò)與信號(hào)處理學(xué)術(shù)會(huì)議論文集[C];1999年

8 秦建玲;李軍;;基于核的主成分分析的特征提取方法與樣本篩選[A];2005年中國(guó)機(jī)械工程學(xué)會(huì)年會(huì)論文集[C];2005年

9 劉紅;陳光，

本文編號(hào)：2054048