發(fā)布時(shí)間：2018-05-30 09:43

  本文選題：特征提取 + 手指靜脈識(shí)別��； 參考：《山東大學(xué)》2016年博士論文

【摘要】：生物特征識(shí)別相較于傳統(tǒng)的身份驗(yàn)證具有安全、方便等優(yōu)勢(shì),其研究?jī)r(jià)值和良好的應(yīng)用價(jià)值得到了學(xué)術(shù)界和企業(yè)界的認(rèn)可。血管作為藏匿在人體皮膚下的模態(tài),具有活體識(shí)別、不易被盜用和復(fù)制等特點(diǎn),是更加安全的一類生物特征。血管類的模態(tài)主要包括以手指靜脈為代表的手部血管和眼部視網(wǎng)膜血管等,本文針對(duì)手指靜脈識(shí)別和視網(wǎng)膜血管分割、識(shí)別中存在的一系列問題進(jìn)行了研究。手指靜脈識(shí)別是一種比較新穎的、被業(yè)內(nèi)認(rèn)為是最有前景的身份認(rèn)證技術(shù)之一。相較于其他的生物特征識(shí)別方法,手指靜脈識(shí)別具有安全性高、方便和用戶友好等優(yōu)勢(shì),得到了越來越多同行的關(guān)注。目前對(duì)手指靜脈識(shí)別的研究取得了較大的進(jìn)展,但仍有問題需要解決。例如,手指靜脈圖像存在的圖像質(zhì)量和形變問題,會(huì)對(duì)基于局部特征手指靜脈識(shí)別方法的效果產(chǎn)生較大的影響。改進(jìn)現(xiàn)有的特征,以及設(shè)計(jì)魯棒的特征提取方法是解決這些問題的重要方向。視網(wǎng)膜眼底圖像主要包括眼底血管和感光細(xì)胞等結(jié)構(gòu)。視網(wǎng)膜眼底血管是人體血液循環(huán)系統(tǒng)唯一可以無創(chuàng)傷觀察的較深層微血管。視網(wǎng)膜眼底圖像可以用于身份驗(yàn)證,此外,視網(wǎng)膜眼底血管的特征對(duì)診斷系統(tǒng)疾病和系統(tǒng)性眼病也有重要意義。無論進(jìn)行視網(wǎng)膜識(shí)別還是對(duì)視網(wǎng)膜血管特征進(jìn)行分析,一般都需要對(duì)血管進(jìn)行分割。在視網(wǎng)膜血管分割方面存在大量工作,但在效率和準(zhǔn)確率上很難達(dá)到一個(gè)平衡,如何高效、準(zhǔn)確的進(jìn)行血管分割仍是一個(gè)挑戰(zhàn)。在利用視網(wǎng)膜進(jìn)行身份驗(yàn)證時(shí),不準(zhǔn)確的血管分割易引入錯(cuò)誤,如何在避免血管分割的情況下進(jìn)行視網(wǎng)膜識(shí)別也是一個(gè)重要研究課題。本文針對(duì)手指靜脈識(shí)別中局部特征的表達(dá)能力差和對(duì)形變敏感等問題,以及如何高效、準(zhǔn)確的進(jìn)行視網(wǎng)膜血管分割、如何在避免血管分割的情況下進(jìn)行視網(wǎng)膜識(shí)別進(jìn)行了深入的分析和探討,主要工作和貢獻(xiàn)有：1、基于局部特征的識(shí)別是手指靜脈識(shí)別中一類比較重要的方法。比較常用的局部特征主要有局部二值模式(LBP)、局部導(dǎo)數(shù)模式(LDP)及其變種等�，F(xiàn)存的局部特征主要考慮到了像素鄰域內(nèi)的梯度方向,而忽略了梯度的大小和梯度之間的關(guān)系等,所以特征的表達(dá)能力有限�；诖朔治�,本文設(shè)計(jì)了一種新的局部特征提取方法,稱為局部方向編碼(LDC),該方法不僅考慮了局部梯度變化的大小,且進(jìn)一步考慮了多個(gè)方向的梯度變化關(guān)系。在包含136個(gè)手指的4,080幅圖像上的識(shí)別效果表明了所設(shè)計(jì)特征的區(qū)分能力。本文方法比目前最優(yōu)的基于局部特征的LLBP方法的等錯(cuò)誤下降了50%。2、目前的手指靜脈識(shí)別技術(shù)在處理形變問題時(shí),往往將其視作是一種影響匹配的噪聲信息,并將工作的重點(diǎn)放在如何對(duì)形變信息進(jìn)行恢復(fù)或者怎樣降低形變的影響上,而忽略了形變信息本身的規(guī)律性。經(jīng)分析,在進(jìn)行同源匹配時(shí),雖然兩幅圖像間存在形變,但是由于像素位置關(guān)系的約束,相鄰像素的位移和方向是相似的；而在異源匹配時(shí),相鄰位置的像素由于特征的差異,位移和方向就沒有這種規(guī)律�；诖�,本文提出了基于形變信息的手指靜脈識(shí)別方法,利用匹配中形變矩陣的一致性來衡量?jī)煞鶊D像的相似度。形變矩陣由基于像素級(jí)特征的優(yōu)化匹配算法產(chǎn)生。在公開手指靜脈庫PolyU和SDU-MLA上六折交叉驗(yàn)證的等錯(cuò)誤率分別為0.0010和0.0049,表明了所設(shè)計(jì)特征的區(qū)分能力以及對(duì)識(shí)別的有效性。3、現(xiàn)有的視網(wǎng)膜分割算法主要分為監(jiān)督方法和非監(jiān)督方法兩類。監(jiān)督方法的分割效果較好,但是需要提取像素級(jí)的特征,所以效率較低；而非監(jiān)督方法由于提取的特征較簡(jiǎn)單,得到的效果往往不理想。此外,這兩類方法對(duì)邊緣像素的區(qū)分性都達(dá)不到理想的效果。本文設(shè)計(jì)了一種基于濾波器的非監(jiān)督視網(wǎng)膜血管分割方法,主要思想是增強(qiáng)血管和背景之間的差別,簡(jiǎn)化分割過程。首先,設(shè)計(jì)兩種不同的濾波器,一種增強(qiáng)圖像的細(xì)節(jié),另一種對(duì)整幅圖像的光照進(jìn)行歸一化,然后對(duì)兩種濾波的結(jié)果進(jìn)行加權(quán)得到最終的效果。這樣得到的預(yù)處理圖像只需要一個(gè)閾值就可以將血管分割出來。經(jīng)過簡(jiǎn)單的微調(diào)和后處理之后,在公開數(shù)據(jù)庫DRIVE和STARE庫上的實(shí)驗(yàn)結(jié)果超過了目前的非監(jiān)督方法,且優(yōu)于大多數(shù)監(jiān)督方法,并有較高的效率。4、SIFT描述子以其強(qiáng)大的區(qū)分能力著稱,且在物體識(shí)別和檢測(cè)上得到了廣泛應(yīng)用。經(jīng)驗(yàn)證,SIFT描述子在視網(wǎng)膜識(shí)別的直接應(yīng)用卻得不到理想的效果,在VARIA數(shù)據(jù)庫上的等錯(cuò)誤率為0.0436。本文認(rèn)為找到效果不理想的原因,并提高基于SIFT的視網(wǎng)膜識(shí)別的準(zhǔn)確率是一個(gè)值得研究的問題。經(jīng)分析發(fā)現(xiàn),該類圖像往往存在光照不均勻、模糊和局部對(duì)比度小等問題,這樣的圖像在進(jìn)行SIFT特征提取時(shí),繼續(xù)進(jìn)行高斯子空間變換,會(huì)損失大部分圖像信息,提取的SIFT描述子也會(huì)不穩(wěn)定�；谏鲜龇治�,本文對(duì)視網(wǎng)膜圖像進(jìn)行了去除偏場(chǎng)的增強(qiáng)操作,并進(jìn)一步利用迭代的各向異性擴(kuò)散平滑算法對(duì)圖像進(jìn)行去噪。在經(jīng)過預(yù)處理的圖像上,基于SIFT的識(shí)別準(zhǔn)確率有明顯提高且有較強(qiáng)的魯棒性。
[Abstract]:Compared with traditional identification, biometric identification has the advantages of security, convenience and other advantages. Its research value and good application value have been recognized by the academia and the business community. As a mode hidden under human skin, blood vessels have the characteristics of living identification, not easy to be embezzled and copied, and are a safer biological feature. The mode of the class consists mainly of the hand vessels and retinal vessels represented by the finger vein. In this paper, a series of problems in the recognition of finger veins and retinal vascular segmentation are studied. Finger vein recognition is one of the most promising and most promising identification techniques in the industry. Compared with other methods of biometric identification, finger vein recognition has the advantages of high security, convenient and user friendly. More and more attention has been paid to the research of finger vein recognition. However, some problems still need to be solved. For example, the image quality and deformation of the finger vein image can be solved. It has a great influence on the effect of finger vein recognition based on local characteristics. Improving the existing features and designing a robust feature extraction method are important directions to solve these problems. Retina fundus images mainly include fundus blood vessels and photosensitive cells. Retina fundus blood vessels are the only blood circulation system of the human body The retina fundus images can be used for identification. In addition, the characteristics of retinal fundus vessels are also important for diagnosis of systemic diseases and systemic ophthalmopathy. There is a lot of work in the division of omentum vessels, but it is difficult to achieve a balance in efficiency and accuracy. How to effectively and accurately segment the blood vessels is still a challenge. When using the retina for identification, the inaccurate segmentation of blood vessels is easy to introduce errors, and how to avoid retinal recognition under the condition of avoiding blood vessel segmentation This paper is an important research topic. In this paper, in view of the poor expression of the local characteristics of the finger vein recognition and the sensitivity to deformation, and how to effectively and accurately segment the retinal vessels, how to do retinal recognition in the condition of avoiding blood vessel segmentation is deeply analyzed and discussed. The main work and contribution are as follows: 1, Local feature recognition is one of the most important methods in finger vein recognition. The commonly used local features mainly include local two value mode (LBP), local derivative mode (LDP) and its variant. The existing local features mainly take into account the gradient square in the neighborhood of pixels, but ignore the relationship between the gradient and the gradient. Based on this analysis, this paper designs a new local feature extraction method called local direction coding (LDC). This method not only takes into account the size of local gradient change, but also considers the gradient change of multiple directions. The recognition effect on 4080 images containing 136 fingers. It shows the distinguishing ability of the designed features. This method is less than the 50%.2 of the optimal LLBP method based on the local feature. The current finger vein recognition technology often treats it as a kind of noise information that affects the matching, and puts the focus on how to restore the deformation information. And how to reduce the influence of the deformation, but ignore the regularity of the deformation information itself. After analysis, although the two images are deformed during the homologous match, the displacement and direction of the adjacent pixels are similar because of the pixel position relation, while the pixels in the adjacent position are due to the difference of the features in the source matching. In this paper, a finger vein recognition method based on deformation information is proposed, and the similarity of the two images is measured by the consistency of the deformation matrix in the matching. The deformation matrix is produced by the optimization matching algorithm based on the pixel level features. Forty percent off on the PolyU and SDU-MLA of the finger vein library. The error rates of cross validation are 0.0010 and 0.0049 respectively, indicating the distinguishing ability of the designed features and the validity of the recognition. The existing retinal segmentation algorithms are divided into two categories: supervision method and unsupervised method. The segmentation effect of the supervised method is better, but the feature of pixel level needs to be extracted, so the efficiency is lower than that of the.3. In addition, the two methods are not ideal for the distinction between the edge pixels. In this paper, a non supervised retinal blood vessel segmentation method based on filter is designed. The main idea is to enhance the difference between the blood vessels and the background and simplify the segmentation process. First, two different filters are designed, one is to enhance the details of the image, the other is the normalization of the illumination of the whole image, then the final effect is weighted for the results of the two filtering. The obtained preprocessed image can be divided out of the blood tube with only one threshold. After that, the experimental results on the public database DRIVE and STARE library exceed the current unsupervised methods, and are superior to most supervision methods, and have high efficiency.4. The SIFT descriptor is famous for its powerful distinguishing ability, and has been widely used in object recognition and detection. It is verified that the SIFT descriptor is directly responsible for the retina recognition. It is not ideal for use, and the error rate in the VARIA database is 0.0436.. This paper thinks that it is a problem to find out the reason of unsatisfactory effect and improve the accuracy rate of retina recognition based on SIFT. When SIFT feature extraction is carried out, the Gauss subspace transformation is continued, most of the image information will be lost, and the extracted SIFT descriptor will be unstable. Based on the above analysis, the enhancement operation of removing partial field is carried out on the retina image, and the image is de-noised by the iterative anisotropic diffusion smoothing algorithm. On the preprocessed images, the recognition accuracy based on SIFT has been significantly improved and has strong robustness.
【學(xué)位授予單位】：山東大學(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 趙硯田;;引人注目的靜脈識(shí)別技術(shù)[J];中國(guó)防偽報(bào)道;2009年03期

2 張拓;;手掌靜脈識(shí)別在身份識(shí)別中的應(yīng)用[J];中國(guó)輸血雜志;2010年S1期

3 李沛秦;李貴林;;看不見偷不走的放心鎖——靜脈識(shí)別[J];實(shí)驗(yàn)室研究與探索;2014年03期

4 吉紫娟;包佳祺;;用于手指靜脈識(shí)別的光學(xué)系統(tǒng)[J];湖北教育學(xué)院學(xué)報(bào);2007年02期

5 陳彥德;;淺析靜脈識(shí)別技術(shù)的原理與應(yīng)用[J];中國(guó)高新技術(shù)企業(yè);2008年20期

6 邱英;譚定忠;姚欣;孫暉;顧義華;宋瑞涵;;靜脈識(shí)別技術(shù)研究進(jìn)展[J];機(jī)械工程師;2009年07期

7 左鐵東;張環(huán);胡德文;;手掌靜脈識(shí)別系統(tǒng)的研究與設(shè)計(jì)[J];計(jì)算機(jī)測(cè)量與控制;2009年11期

8 王科俊;劉靖宇;;基于相對(duì)距離和角度的手指靜脈識(shí)別方法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年05期

9 楊穎;楊公平;;手指靜脈識(shí)別技術(shù)[J];計(jì)算機(jī)科學(xué)與探索;2012年04期

10 ;手指靜脈識(shí)別技術(shù)中紅外線的作用分析[J];中國(guó)防偽報(bào)道;2012年04期

相關(guān)會(huì)議論文 前6條

1 肖賓杰;張征;殳偉群;;靜脈識(shí)別研究的進(jìn)展與應(yīng)用展望[A];第七屆全國(guó)信息獲取與處理學(xué)術(shù)會(huì)議論文集[C];2009年

2 張拓;;手掌靜脈識(shí)別在身份識(shí)別中的應(yīng)用[A];中國(guó)輸血協(xié)會(huì)第五屆輸血大會(huì)論文專集（摘要篇）[C];2010年

3 盧飛遠(yuǎn);程國(guó)建;潘華賢;;基于NiBlack的靜脈圖像的應(yīng)用研究[A];第十二屆中國(guó)青年信息與管理學(xué)者大會(huì)論文集[C];2010年

4 王科俊;劉靖宇;楊曉菲;;提取相位和方向特征的手指靜脈識(shí)別方法[A];2011年中國(guó)智能自動(dòng)化學(xué)術(shù)會(huì)議論文集（第一分冊(cè)）[C];2011年

5 康文雄;鄧飛其;;基于特征點(diǎn)角度矩陣的靜脈識(shí)別方法[A];第二十七屆中國(guó)控制會(huì)議論文集[C];2008年

6 許強(qiáng);楊佳;;基于線性加權(quán)的免疫克隆算法的手指靜脈特征提取[A];中國(guó)自動(dòng)化學(xué)會(huì)控制理論專業(yè)委員會(huì)B卷[C];2011年

相關(guān)重要報(bào)紙文章 前6條

1 楊二;上海環(huán)球金融中心啟用指靜脈識(shí)別考勤管理系統(tǒng)[N];中國(guó)質(zhì)量報(bào);2008年

2 王海;峰峰集團(tuán)引入靜脈互保確認(rèn)系統(tǒng)[N];中國(guó)煤炭報(bào);2010年

3 本報(bào)記者 華凌;一“指”當(dāng)關(guān) 萬夫莫開[N];科技日?qǐng)?bào);2008年

4 本報(bào)記者 冰島;非接觸式手掌靜脈認(rèn)證有望終結(jié)密碼時(shí)代[N];國(guó)際商報(bào);2008年

5 張巨睿;《科學(xué)世界》解讀科技奧運(yùn)[N];中國(guó)郵政報(bào);2008年

6 葛林楠 王握文 楊燕群;手指作“密碼” 開啟保險(xiǎn)箱[N];科技日?qǐng)?bào);2013年

相關(guān)博士學(xué)位論文 前10條

1 顏學(xué)葵;掌靜脈識(shí)別算法研究[D];華南理工大學(xué);2015年

2 襲肖明;手指靜脈識(shí)別若干關(guān)鍵問題研究[D];山東大學(xué);2015年

3 王軍;手部靜脈識(shí)別關(guān)鍵技術(shù)研究[D];中國(guó)礦業(yè)大學(xué);2015年

4 孟憲靜;血管類圖像分割與識(shí)別方法研究[D];山東大學(xué);2016年

5 楊璐;手指靜脈識(shí)別方法研究[D];山東大學(xué);2016年

6 李鐵鋼;靜脈識(shí)別算法研究[D];吉林大學(xué);2007年

7 陳劉奎;人體手指靜脈識(shí)別技術(shù)研究[D];武漢大學(xué);2010年

8 宋尚玲;鼻部毛囊識(shí)別和手指靜脈識(shí)別[D];山東大學(xué);2009年

9 秦華鋒;手指靜脈圖像質(zhì)量評(píng)估與特征識(shí)別算法研究[D];重慶大學(xué);2012年

10 賈旭;基于多特性融合的手背靜脈識(shí)別關(guān)鍵算法研究[D];東北大學(xué);2012年

相關(guān)碩士學(xué)位論文 前10條

1 薛琴;手掌靜脈識(shí)別技術(shù)在貴重物品物流中的應(yīng)用研究[D];沈陽大學(xué);2015年

2 孟昭慧;基于二次判別和局部信息及特征融合的手靜脈識(shí)別[D];復(fù)旦大學(xué);2014年

3 董路梅;基于詞袋模型的手指靜脈識(shí)別方法研究[D];山東大學(xué);2015年

4 劉菲;手指靜脈識(shí)別關(guān)鍵問題研究[D];山東大學(xué);2015年

5 高潔睿;手指靜脈特征提取方法研究[D];沈陽工業(yè)大學(xué);2016年

6 耿宏雨;基于手背靜脈的生物特征識(shí)別關(guān)鍵算法研究[D];東北大學(xué);2014年

7 李思遠(yuǎn);手指靜脈識(shí)別關(guān)鍵問題研究[D];東北大學(xué);2014年

8 周雄;手指靜脈識(shí)別技術(shù)的研究與實(shí)現(xiàn)[D];桂林電子科技大學(xué);2010年

9 陳虹;基于指靜脈識(shí)別技術(shù)的社保系統(tǒng)的研究與實(shí)現(xiàn)[D];北京工業(yè)大學(xué);2012年

10 崔菲菲;手指靜脈識(shí)別技術(shù)研究[D];山東大學(xué);2012年

，

本文編號(hào)：1954827