本文選題：生物特征識(shí)別 + 眉毛�。� 參考：《安徽工業(yè)大學(xué)》2017年碩士論文

【摘要】：目前,人們普遍認(rèn)為具有高度安全的身份識(shí)別手段就是利用生物本身所具有的獨(dú)特特征(如指紋,人臉等)來進(jìn)行識(shí)別。這種方式已經(jīng)被廣泛應(yīng)用于金融服務(wù)、視頻監(jiān)控、信息安全、人機(jī)交互、刑偵判定、電子商務(wù)、出入境管理等眾多行業(yè)范疇。鑒于人類的眉毛滿足了利用生物特征進(jìn)行識(shí)別而具有的唯一性、普遍性、穩(wěn)定性以及易獲取性的特點(diǎn),所以,可以將眉毛作為身份識(shí)別的一種手段。眉毛具備顯明的輪廓特征和紋理特征,但當(dāng)前對(duì)眉毛的研究主要停留在單眉毛圖像,且缺乏對(duì)眉毛的外部特征展開相關(guān)研究,因此仍然存在局限性,進(jìn)一步展開關(guān)于眉毛的研究工作將會(huì)在生物特征識(shí)別方面具有重要的意義。本文開展的研究工作主要內(nèi)容如下:(1)為了提取眉毛輪廓,本文首先簡(jiǎn)要的敘述了水平集算法的基本原理,然后重點(diǎn)研究了基于偏移場(chǎng)矯正的水平集模型(Li模型)。該模型不僅可以實(shí)現(xiàn)圖像分割,也可以抑制圖像的灰度不均勻性,但往往也因初始曲線設(shè)置不合理,進(jìn)而導(dǎo)致演化時(shí)間過長(zhǎng)。本文特別針對(duì)水平集初始曲線部分進(jìn)行改進(jìn),其中引入基于偽球的邊緣檢測(cè)算子,再結(jié)合形態(tài)學(xué)閉操作和填充操作,將演化的初始曲線(初始輪廓)設(shè)定在靠近感興趣區(qū)域(眉毛邊緣),實(shí)現(xiàn)了對(duì)眉毛輪廓的粗定位,大大減少Li模型的水平集演化時(shí)間。(2)將基于偽球的邊緣檢測(cè)算子與Li模型進(jìn)行結(jié)合,通過水平集演化獲取眉毛圖像中的眉毛輪廓,在此基礎(chǔ)上,利用眉毛的幾何特性,計(jì)算形狀特征和方向特征,然后利用灰度共生矩陣法(GLCM)計(jì)算眉毛紋理特征,以特征向量方式構(gòu)建眉毛的一種外部特征模型。(3)實(shí)驗(yàn)結(jié)果表明,在相同的迭代次數(shù)下,對(duì)比Li模型,本文方法得到的眉毛輪廓更準(zhǔn)確;針對(duì)自建的自然眉毛圖像庫(kù)(100人),本文模型其身份驗(yàn)證的匹配率最高達(dá)90.59%,眉毛外部特征模型的單眉毛識(shí)別率可達(dá)86.1%,與HMM和2DPCA結(jié)果相當(dāng),雙眉毛識(shí)別率略有提高(90.2%),針對(duì)沒有濃淡區(qū)別的眉毛庫(kù),僅靠形狀和方向特征模型,單、雙眉毛識(shí)別率為88.1%和88.7%,說明也能達(dá)到識(shí)別眉毛的作用。
[Abstract]:At present, it is generally believed that a highly secure identification means is to use the unique characteristics of biology (such as fingerprints, faces, etc.) to identify. This method has been widely used in financial services, video surveillance, information security, human-computer interaction, criminal detection, e-commerce, immigration management and many other industries. Since human eyebrows satisfy the unique, universal, stable and easily accessible characteristics of biometric recognition, eyebrow can be used as a means of identity recognition. Eyebrow has obvious contour features and texture features, but the current research on eyebrow is mainly focused on single eyebrow image, and lack of related research on the external features of eyebrow, so there are still limitations. Further research on eyebrows will be of great significance in biometric recognition. The main work of this paper is as follows: (1) in order to extract the contour of eyebrow, the basic principle of level set algorithm is briefly described in this paper, and then the level set model based on offset correction is studied emphatically. The model can not only achieve image segmentation, but also suppress the inhomogeneity of image grayscale. However, the initial curve setting is unreasonable and the evolution time is too long. In this paper, the initial curve of the level set is improved, in which the pseudo-sphere based edge detection operator is introduced, and then the morphological closed operation and the filling operation are combined. The initial curve (initial contour) of evolution is set near the region of interest (eyebrow edge) to achieve the coarse location of the contour of the eyebrow. The level set evolution time of Li model is greatly reduced.) the edge detection operator based on pseudo sphere is combined with Li model, and the contour of eyebrow in eyebrow image is obtained by level set evolution. On this basis, the geometric characteristics of eyebrow are utilized. The shape and direction features are calculated, and then the grayscale co-occurrence matrix method (GLCM) is used to calculate the eyebrow texture features, and an external feature model of eyebrow is constructed by eigenvector. The experimental results show that, under the same iteration times, the Li model is compared. According to the self-built natural eyebrow image database, the matching rate of this model is 90.59, and the single eyebrow recognition rate of the external feature model of eyebrow can reach 86.1, which is similar to that of HMM and 2DPCA. The rate of double eyebrow recognition was slightly increased by 90.2%. The recognition rate of single and double eyebrows was 88. 1% and 88. 7%, which indicated that the eyebrow recognition rate could also be achieved by the shape and direction feature model.
【學(xué)位授予單位】：安徽工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 梁奔香;蔡曉東;朱利偉;華娜;吳迪;;幾何性特征的眉毛模型的研究[J];電視技術(shù);2015年13期

2 葛小鳳;陳亞軍;;經(jīng)典邊緣檢測(cè)算子及其抗噪性能研究[J];數(shù)字技術(shù)與應(yīng)用;2015年02期

3 劉波;;ROC曲線在制定地溝油中鈉離子鑒別指標(biāo)最佳臨界值中的應(yīng)用[J];中國(guó)油脂;2013年06期

4 李玉擰;白潔;;基于分水嶺和K-均值的半自動(dòng)眉毛圖像分割[J];北京工業(yè)大學(xué)學(xué)報(bào);2012年07期

5 李玉擰;謝歡曦;周藝華;;基于2DPCA的眉毛識(shí)別方法研究[J];武漢大學(xué)學(xué)報(bào)(理學(xué)版);2011年06期

6 張家軒;王成儒;;基于邊緣信息和時(shí)空馬爾可夫模型的運(yùn)動(dòng)目標(biāo)檢測(cè)方法[J];燕山大學(xué)學(xué)報(bào);2011年02期

7 李厚君;李玉擰;;基于AdaBoost的眉毛檢測(cè)與定位[J];計(jì)算機(jī)與數(shù)字工程;2010年08期

8 高程程;惠曉威;;基于灰度共生矩陣的紋理特征提取[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2010年06期

9 曹俊彬;李玉擰;黃琰;;基于小波變換和SVM的眉毛身份驗(yàn)證系統(tǒng)研究[J];計(jì)算機(jī)應(yīng)用研究;2009年11期

10 張晨光;李玉擰;;基于半監(jiān)督學(xué)習(xí)的眉毛圖像分割方法[J];計(jì)算機(jī)工程與應(yīng)用;2009年21期

相關(guān)碩士學(xué)位論文 前3條

1 石瑾凌;基于水平集方法的海面SAR溢油檢測(cè)研究[D];西安電子科技大學(xué);2014年

2 吳煒峰;基于水平集的灰度不均勻圖像分割研究[D];華南理工大學(xué);2013年

3 曲滔滔;眉毛在面孔識(shí)別中作用的研究[D];吉林大學(xué);2011年

，

本文編號(hào)：1868721