CN101241550B - A method for judging the quality of iris images - Google Patents

A method for judging the quality of iris images Download PDF

Info

Publication number
CN101241550B
CN101241550B CN2008100259896A CN200810025989A CN101241550B CN 101241550 B CN101241550 B CN 101241550B CN 2008100259896 A CN2008100259896 A CN 2008100259896A CN 200810025989 A CN200810025989 A CN 200810025989A CN 101241550 B CN101241550 B CN 101241550B
Authority
CN
China
Prior art keywords
wavelet
image
iris image
resolution
iris
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN2008100259896A
Other languages
Chinese (zh)
Other versions
CN101241550A (en
Inventor
马争
潘力立
解梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Electronic Science and Technology of China Zhongshan Institute
Original Assignee
University of Electronic Science and Technology of China Zhongshan Institute
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by University of Electronic Science and Technology of China Zhongshan Institute filed Critical University of Electronic Science and Technology of China Zhongshan Institute
Priority to CN2008100259896A priority Critical patent/CN101241550B/en
Publication of CN101241550A publication Critical patent/CN101241550A/en
Application granted granted Critical
Publication of CN101241550B publication Critical patent/CN101241550B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

本发明提供的一种虹膜图像质量判断方法,它首先通过定位,归一化操提取出原始的归一化虹膜图像,然后对归一化虹膜图像那个进行4层多分辨率分解,通过统计分辨率2-1下的细节分量的幅值较大点数目,并与预先设定的阈值进行比较,可以判断该图像是否存在眼睑和睫毛遮挡问题,接着计算分辨率2-2下的细节分量的方差,并预先设定的阈值进行比较,可以判断该图像清晰度是否满足系统的要求。采用本发明的虹膜图像质量判断方法,对不同的光照环境都有较为稳定的性能,对虹膜图像质量做出快速准确地的判断。

Figure 200810025989

The present invention provides a method for judging the quality of an iris image. It first extracts the original normalized iris image through positioning and normalization operations, then performs 4-layer multi-resolution decomposition on the normalized iris image, and by counting the number of points with larger amplitudes of detail components at a resolution of 2-1 and comparing them with a preset threshold, it can be judged whether the image has eyelid and eyelash occlusion problems, and then calculates the variance of the detail components at a resolution of 2-2 and compares them with a preset threshold to judge whether the image clarity meets the requirements of the system. The iris image quality judgment method of the present invention has relatively stable performance in different lighting environments, and makes a quick and accurate judgment on the quality of the iris image.

Figure 200810025989

Description

一种虹膜图像质量判断方法 A method for judging the quality of iris images

【技术领域】【Technical field】

本发明属于图像处理技术领域,主要涉及生物特征鉴别中的虹膜身份识别技术。The invention belongs to the technical field of image processing, and mainly relates to iris identification technology in biometric identification.

【背景技术】【Background technique】

随着电脑、ATM机、移动电话、门禁控制系统等电子设备不断地进入我们的日常生活中,对于个人安全、方便的身份认证技术变得越来越紧迫。然而,现有的基于智能卡、身份证号码和口令的系统却只能在安全与方便之间徘徊,充分的安全从来没有实现过,而更好的安全却与不方便同时出现。为了实现较高的安全性,我们必须使用更复杂和更不方便的口令,因为如果对我们身边不同的机器使用一个相同的密码,那我们在得到了方便性的同时也增加了安全性的隐患。为此人们一直在探索一些安全而又方便的解决方案。生物识别技术为此提供了一个全新的领域。生物识别技术是利用人类的生理特性或行为特性进行身份识别和验证。这些生理特性包括指纹,掌纹,声音,签名等来识别个人的身份。因为生理特性既不会像密码一样被遗忘,也不会像钥匙一样被遗失,所以被认为是一种更为可靠的个人身份验证方法。虹膜身份识别是一种新兴的生物识别技术,利用虹膜作为身份识别的依据,具有高独特性、高稳定性、天然防伪性和无侵犯性等优点。详见文献:Anil K.Jain,Arun Ross,Salil Prabhakar,“An Introduction to Biometric Recognition”,IEEE Transaction on Circuits and Systems for Video Technology,Volume 14,No.1,pp.4-20,2004和文献:John G.Daugman,“How Iris Recognition Works,”IEEE Transaction on Circuits and Systems for Video Technology,Volume 14,Issue 1,pp.21-30,2004所述。As computers, ATM machines, mobile phones, access control systems and other electronic devices continue to enter our daily life, it is becoming more and more urgent for personal security and convenient identity authentication technology. However, the existing systems based on smart cards, ID numbers and passwords can only hover between security and convenience. Sufficient security has never been achieved, while better security and inconvenience appear at the same time. In order to achieve higher security, we must use more complex and inconvenient passwords, because if we use the same password for different machines around us, we will increase the security risks while gaining convenience . People have been exploring some safe and convenient solutions for this reason. Biometrics offers a whole new field for this. Biometric technology is the use of human physiological or behavioral characteristics for identification and verification. These physiological characteristics include fingerprints, palm prints, voices, signatures, etc. to identify individuals. Because biological characteristics are neither forgotten like a password nor lost like a key, they are considered a more reliable method of personal identification. Iris identification is an emerging biometric technology that uses the iris as the basis for identification and has the advantages of high uniqueness, high stability, natural anti-counterfeiting and non-invasiveness. See literature for details: Anil K. Jain, Arun Ross, Salil Prabhakar, "An Introduction to Biometric Recognition", IEEE Transaction on Circuits and Systems for Video Technology, Volume 14, No.1, pp.4-20, 2004 and literature: John G. Daugman, "How Iris Recognition Works," IEEE Transaction on Circuits and Systems for Video Technology, Volume 14, Issue 1, pp.21-30, 2004.

虹膜图像质量评估在整个自动虹膜识别技术中是非常重要的一个部分,它保证了进行处理的虹膜图像都满足系统的质量要求。从而,避免了由于虹膜图像本身质量问题而引起的误识和拒识。实际中,由于拍摄时采集设备的焦距问题,拍摄瞬间眼球的转动问题,以及眼睑和睫毛对虹膜的部分遮挡,常常使采集的虹膜图像无法进行后续的特征提取。目前已有的算法中还没有提出一种有效的虹膜图像质量评估模型,因此我们旨在建立一套通用可行的评估模型,详见文献:Chen Ji,Hu Guangshu,“Iris Image Quality Evaluation based on Wavelet Packet Decomposition”,Journal of Tsinghua University(Sci &Tech),Volume 43,No.3,pp.377-380,2003和文献:Li Ma,Tieniu Tan,Yunhong Wang,Dexin Zhang,“Efficient Iris Recognition by Characterizing key Local Variations”,IEEE Transaction on Image Processing,Volume 13,No.6,pp.739-750,2004所述。Iris image quality assessment is a very important part in the whole automatic iris recognition technology, it ensures that the processed iris images meet the quality requirements of the system. Therefore, the misrecognition and refusal of recognition caused by the quality problem of the iris image itself are avoided. In practice, due to the focal length of the acquisition device during shooting, the rotation of the eyeball at the moment of shooting, and the partial occlusion of the iris by the eyelids and eyelashes, it is often impossible to perform subsequent feature extraction on the collected iris image. An effective iris image quality evaluation model has not been proposed in the existing algorithms, so we aim to establish a general and feasible evaluation model, see the literature for details: Chen Ji, Hu Guangshu, "Iris Image Quality Evaluation based on Wavelet Packet Decomposition", Journal of Tsinghua University (Sci & Tech), Volume 43, No.3, pp.377-380, 2003 and literature: Li Ma, Tieniu Tan, Yunhong Wang, Dexin Zhang, "Efficient Iris Recognition by Characterizing key Local Variations”, described in IEEE Transaction on Image Processing, Volume 13, No.6, pp.739-750, 2004.

目前已有虹膜质量判断方法有:At present, the existing iris quality judgment methods are:

(1)基于快速傅立叶变换的方法。它对虹膜区域上的两个矩形块内的象素点进行二维快速傅立叶变换,然后通过对其高频、中频和低频能量的统计,分析图像是否清晰和存在睫毛遮挡。该模型的通用性不强,容易将纹理较少的清晰虹膜图像误判为低质量虹膜图像。详见文献:Li Ma,Tieniu Tan,Yunhong Wang,Dexin Zhang,“Personal Identification based on Iris Texture Analysis,”IEEE Transactions on Pattern Analysis and Machine Intelligence,Volume 25,No.12,pp.1519-1533。(1) Method based on fast Fourier transform. It performs two-dimensional fast Fourier transform on the pixels in two rectangular blocks on the iris area, and then analyzes whether the image is clear and has eyelash occlusion through the statistics of its high-frequency, intermediate-frequency and low-frequency energy. The generality of this model is not strong, and it is easy to misjudge a clear iris image with less texture as a low-quality iris image. See literature for details: Li Ma, Tieniu Tan, Yunhong Wang, Dexin Zhang, "Personal Identification based on Iris Texture Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 25, No.12, pp.1519-1533.

(2)基于小波包分解的方法。它选取纹理高频分量分布最集中的子频带作为特征子频带,以其能量作为判别图像质量的准则。该方法的缺点是无法判断因睫毛遮挡而存在问题的虹膜图像。详见文献:Chen Ji,Hu Guangshu,“Iris Image Quality Evaluation based on Wavelet Packet Decomposition”,Journal of Tsinghua University(Sci & Tech),Volume 43,No.3,pp.377-380,2003。(2) The method based on wavelet packet decomposition. It selects the sub-band with the most concentrated distribution of texture high-frequency components as the characteristic sub-band, and uses its energy as the criterion for judging the image quality. The disadvantage of this method is that it cannot judge iris images which are problematic due to eyelash occlusion. See literature for details: Chen Ji, Hu Guangshu, "Iris Image Quality Evaluation based on Wavelet Packet Decomposition", Journal of Tsinghua University (Sci & Tech), Volume 43, No.3, pp.377-380, 2003.

(3)基于图像清晰度、内外偏心度和虹膜可见度的方法。它建立了图像清晰度、内外偏心度和虹膜可见度三个衡量图像质量的指标,实现了对虹膜图像进行实时质量评价的要求。该方法的缺点是对光照条件较为敏感,稳定性不强。Xing Lei,Shi Pengfei,“A Quality Evaluation Method of Iris Image”,Chinese Journal of Stereology and Image Analysis,Volume.8,No.2,pp.108-113,2003。(3) Methods based on image clarity, inner-outer eccentricity, and iris visibility. It establishes three indicators for measuring image quality, namely, image clarity, internal and external eccentricity, and iris visibility, and realizes the requirement of real-time quality evaluation of iris images. The disadvantage of this method is that it is more sensitive to light conditions and less stable. Xing Lei, Shi Pengfei, "A Quality Evaluation Method of Iris Image", Chinese Journal of Stereology and Image Analysis, Volume.8, No.2, pp.108-113, 2003.

上述的虹膜图像质量判断算法都在一定程度上存在问题,计算量过大、对光照较为敏感、通用性不强等等。The above-mentioned iris image quality judgment algorithms all have problems to a certain extent, such as excessive calculation, sensitivity to light, and poor versatility.

【发明内容】【Content of invention】

本发明的目的是建立一种通用性比较强的虹膜图像质量判断方法,能够准确的检测出眼睑睫毛遮挡的虹膜图像和清晰度不够的虹膜图像,并且使算法适用的光照条件范围较广。The purpose of the present invention is to establish a method for judging the quality of iris images with strong versatility, which can accurately detect iris images blocked by eyelids and eyelashes and iris images with insufficient clarity, and make the algorithm applicable to a wide range of lighting conditions.

本发明的目的是这样实现的:The purpose of the present invention is achieved like this:

1、一种虹膜图像质量判断方法,其特征在于其包含下列步骤:1, a kind of iris image quality judging method is characterized in that it comprises the following steps:

步骤1、通过摄像装置,对人眼中的虹膜进行图像采集,从含有虹膜图像的原始灰度图像中得到尺寸为M×N的归一化虹膜图像f(x,y);(x,y)表示像素点的坐标,f(x,y)表示坐标为(x,y)的像素点的灰度值;Step 1, through the camera device, the iris in the human eye is image-acquired, and the normalized iris image f(x, y) whose size is M×N is obtained from the original grayscale image containing the iris image; (x, y) Represents the coordinates of the pixel, f(x, y) represents the gray value of the pixel whose coordinates are (x, y);

步骤2、对步骤1中得到的归一化虹膜图像,进行4层二维小波变换;具体来说,二维小波变换的公式为:

Figure GSB00000279475500041
Figure GSB00000279475500042
其中,
Figure GSB00000279475500043
是分辨率为2j下的尺度系数,
Figure GSB00000279475500044
是分辨率为2j下小波系数,4层小波变换j的取值范围为{-1,-2,-3,-4},i={H,V,D},附加了水平、垂直和对角方向的细节;
Figure GSB00000279475500045
为尺度函数,
Figure GSB00000279475500046
为小波函数,选取的小波为DMeyer小波;进行二维小波变换的尺度函数
Figure GSB00000279475500047
是两个一维尺度函数的乘积;进行二维小波变换的水平方向敏感的小波函数
Figure GSB000002794755000410
为一维小波函数ψj,m(x)和一维尺度函数
Figure GSB000002794755000411
的乘积;进行二维小波变换的垂直方向敏感的小波函数为一维尺度函数
Figure GSB000002794755000413
和一维小波函数ψj,n(y)的乘积;进行二维小波变换的对角方向敏感的小波函数
Figure GSB000002794755000414
为两个一维小波函数ψj,m(x)与ψj,n(y)的乘积;Step 2, to the normalized iris image that obtains in step 1, carry out 4 layers of two-dimensional wavelet transform; Specifically, the formula of two-dimensional wavelet transform is:
Figure GSB00000279475500041
and
Figure GSB00000279475500042
in,
Figure GSB00000279475500043
is the scale coefficient at a resolution of 2 j ,
Figure GSB00000279475500044
is the wavelet coefficient with a resolution of 2 j , the value range of the 4-layer wavelet transform j is {-1, -2, -3, -4}, i={H, V, D}, and the horizontal, vertical and Diagonal details;
Figure GSB00000279475500045
is a scaling function,
Figure GSB00000279475500046
is a wavelet function, and the selected wavelet is DMeyer wavelet; the scaling function for two-dimensional wavelet transformation
Figure GSB00000279475500047
are two one-dimensional scaling functions and The product of the horizontal direction sensitive wavelet function for two-dimensional wavelet transform
Figure GSB000002794755000410
is the one-dimensional wavelet function ψ j, m (x) and one-dimensional scaling function
Figure GSB000002794755000411
The product of the vertical direction sensitive wavelet function for two-dimensional wavelet transform is a one-dimensional scaling function
Figure GSB000002794755000413
and the product of the one-dimensional wavelet function ψ j, n (y); the diagonal direction-sensitive wavelet function for two-dimensional wavelet transformation
Figure GSB000002794755000414
is the product of two one-dimensional wavelet functions ψ j, m (x) and ψ j, n (y);

步骤3、通过步骤2中得到的分辨率2-1下的水平方向小波系数

Figure GSB000002794755000415
垂直方向小波系数
Figure GSB000002794755000416
和对角方向小波系数
Figure GSB000002794755000417
重构原始归一化虹膜图像在分辨率2-1下的细节分量
Figure GSB000002794755000418
也即是高频细节分量;具体来说,重构公式为:
Figure GSB000002794755000419
Figure GSB00000279475500051
其中
Figure GSB00000279475500052
表示分辨率2j下坐标(x,y)的细节分量的值,
Figure GSB00000279475500053
表示分辨率2j下的小波系数,
Figure GSB00000279475500054
是i方向敏感的二维小波;∑为累加运算符;Step 3, through the horizontal wavelet coefficients obtained in step 2 at a resolution of 2 -1
Figure GSB000002794755000415
Vertical wavelet coefficient
Figure GSB000002794755000416
and the diagonal wavelet coefficients
Figure GSB000002794755000417
Reconstruct the detail component of the original normalized iris image at resolution 2 -1
Figure GSB000002794755000418
That is, the high-frequency detail component; specifically, the reconstruction formula is:
Figure GSB000002794755000419
Figure GSB00000279475500051
in
Figure GSB00000279475500052
represents the value of the detail component of the coordinate (x, y) at resolution 2j ,
Figure GSB00000279475500053
Indicates the wavelet coefficients at resolution 2 j ,
Figure GSB00000279475500054
is a two-dimensional wavelet sensitive to the i direction; ∑ is an accumulation operator;

步骤4、计算步骤3中得到的高频细节分量

Figure GSB00000279475500055
的绝对值
Figure GSB00000279475500056
具体来说,如果
Figure GSB00000279475500057
Figure GSB00000279475500058
如果
Figure GSB00000279475500059
| D 2 - 1 f ( x , y ) | = - D 2 - 1 f ( x , y ) ; Step 4. Calculate the high-frequency detail components obtained in step 3
Figure GSB00000279475500055
absolute value of
Figure GSB00000279475500056
Specifically, if
Figure GSB00000279475500057
Figure GSB00000279475500058
if
Figure GSB00000279475500059
| D. 2 - 1 f ( x , the y ) | = - D. 2 - 1 f ( x , the y ) ;

步骤5、统计步骤4中得到的

Figure GSB000002794755000511
的值大于阈值Vo的像素点的数目,将
Figure GSB000002794755000512
的值大于阈值Vo的点作为眼睑和睫毛的边界点;Vo为判断像素点是否为眼睑和睫毛边界点的阈值,具体计算公式为:其中M和N分别为原始归一化虹膜图像的宽度和高度,
Figure GSB000002794755000514
Step 5, statistics obtained in step 4
Figure GSB000002794755000511
The number of pixels whose value is greater than the threshold V o will be
Figure GSB000002794755000512
The point whose value is greater than the threshold V o is used as the boundary point of the eyelid and eyelashes; V o is the threshold for judging whether the pixel point is the boundary point of the eyelid and eyelashes, and the specific calculation formula is: Where M and N are the width and height of the original normalized iris image respectively,
Figure GSB000002794755000514

步骤6、比较步骤5中计算的

Figure GSB000002794755000515
值与阈值TN作比较;如果
Figure GSB000002794755000516
则认为该图像为眼睑和睫毛遮挡的图像,如果
Figure GSB000002794755000517
则认为该图像为可处理的正常虹膜图像;Step 6, compare the calculated in step 5
Figure GSB000002794755000515
The value is compared with the threshold T N ; if
Figure GSB000002794755000516
The image is considered to be an image occluded by eyelids and eyelashes, if
Figure GSB000002794755000517
Then it is considered that the image is a normal iris image that can be processed;

步骤7、按照与步骤3中的方法,通过步骤2中得到的分辨率2-2下的水平方向小波系数

Figure GSB000002794755000518
垂直方向小波系数
Figure GSB000002794755000519
和对角方向小波系数重构原始归一化虹膜图像在分辨率2-2下的细节分量
Figure GSB000002794755000521
Step 7. According to the method in step 3, pass the horizontal direction wavelet coefficients obtained in step 2 under the resolution 2-2
Figure GSB000002794755000518
Vertical wavelet coefficient
Figure GSB000002794755000519
and the diagonal wavelet coefficients Reconstruct the detail component of the original normalized iris image at resolution 2 -2
Figure GSB000002794755000521

步骤8、计算步骤7中得到的

Figure GSB000002794755000522
的方差;具体的计算公式为:其中,Var为分辨率2-2下细节分量的方差,M和N分别为原始归一化虹膜图像的宽度和高度,m的计算公式为: m = Σ x = 1 M Σ y = 1 N D 2 - 2 f ( x , y ) / M × N ; Step 8, calculate the obtained in step 7
Figure GSB000002794755000522
The variance; the specific calculation formula is: Among them, Var is the variance of the detail component at resolution 2-2 , M and N are the width and height of the original normalized iris image respectively, and the calculation formula of m is: m = Σ x = 1 m Σ the y = 1 N D. 2 - 2 f ( x , the y ) / m × N ;

步骤9、将步骤8中得到的方差Var与判别虹膜清晰度的阈值Tv进行比较,若Var≥Tv,则该虹膜图像清晰度满足系统要求;若Var<Tv,则该虹膜图像清晰度不满足系统要求。Step 9. Compare the variance Var obtained in step 8 with the threshold T v for judging iris clarity, if Var≥T v , then the iris image clarity meets the system requirements; if Var<T v , then the iris image is clear The degree does not meet the system requirements.

如上所述的一种虹膜图像质量判断方法,其特征在于步骤6中提到的阈值TN是用于判断该图像是否是可以处理的无眼睑和睫毛遮挡的图像,TN的确定与后续的匹配算法有关,将其设定为

Figure GSB00000279475500062
的虹膜图像匹配,误识率最低时对应的TN。A kind of iris image quality judging method as above is characterized in that the threshold TN mentioned in the step 6 is used to judge whether the image is an image that can be processed without eyelids and eyelashes, and the determination of TN is related to the subsequent matching algorithm, set it to
Figure GSB00000279475500062
The iris image matches the corresponding T N when the false recognition rate is the lowest.

本发明采用了多分辨率分析的方法,通过分析不同分辨率下的细节分量,正确的评价了虹膜图像的质量。本发明首先对原始虹膜图像进行定位,得到归一化虹膜图像。通过对归一化虹膜图像进行4层小波变换,统计分辨率2-1下的细节分量的较大幅值点的数目并与预先设定的阈值进行比较,判断该虹膜图像是否存在眼睑和睫毛遮挡问题。之后,统计分辨率2-2下的细节分量的方差,并与预先设定的阈值进行比较,判断虹膜图像是否清晰。利用多分辨率的思想进行虹膜图像质量的分析是本发明的一个特色,与一般的虹膜图像质量评估方法相比,本发明的通用性和稳定性很强,不易受光照的影响。The invention adopts a multi-resolution analysis method, and correctly evaluates the quality of the iris image by analyzing the detail components under different resolutions. The invention firstly locates the original iris image to obtain the normalized iris image. By performing 4-layer wavelet transform on the normalized iris image, counting the number of large-amplitude points of the detail component at a resolution of 2 -1 and comparing it with the preset threshold, it is judged whether the iris image is covered by eyelids and eyelashes question. Afterwards, the variance of the detail component under the resolution 2-2 is counted, and compared with the preset threshold to judge whether the iris image is clear or not. It is a characteristic of the present invention to analyze the iris image quality with the idea of multi-resolution. Compared with the general iris image quality evaluation method, the present invention has strong versatility and stability and is not easily affected by light.

【附图说明】【Description of drawings】

图1是含有虹膜的原始图像;Figure 1 is the original image containing the iris;

其中,1表示瞳孔;2表示虹膜;3表示瞳孔中的光斑;4表示虹膜的内缘;5表示虹膜的外缘。Among them, 1 represents the pupil; 2 represents the iris; 3 represents the spot in the pupil; 4 represents the inner edge of the iris; 5 represents the outer edge of the iris.

图2是定位结果图和归一化图;Figure 2 is a positioning result map and a normalized map;

其中,(a)为定位结果图;(b)为虹膜归一化图像。Among them, (a) is the positioning result image; (b) is the iris normalized image.

图3是原始归一化虹膜图像及其高频细节分量;Fig. 3 is the original normalized iris image and its high-frequency detail components;

其中,(a)是有眼睑遮挡的归一化虹膜图像,(b)是(a)的高频细节分量,(c)是有睫毛遮挡的归一化虹膜图像,(d)是(c)的高频细节分量。Among them, (a) is the normalized iris image with eyelid occlusion, (b) is the high-frequency detail component of (a), (c) is the normalized iris image with eyelash occlusion, (d) is (c) high-frequency detail components.

【具体实施方式】【Detailed ways】

为了方便地描述本发明内容,首先对一些术语进行定义。In order to describe the content of the present invention conveniently, some terms are defined first.

定义1:虹膜。眼珠的中心是黑色的瞳孔,瞳孔外缘间的环形组织即为虹膜。其呈现出相互交错的类似与斑点、细丝、条纹、隐窝的纹理特征。同一个人的虹膜在人的一生中几乎不会发生改变,不同人的虹膜是完全不一样的。Definition 1: Iris. The center of the eyeball is the black pupil, and the ring-shaped tissue between the outer edges of the pupil is the iris. It presents interlaced texture features resembling spots, filaments, striations, and crypts. The iris of the same person hardly changes throughout a person's life, and the iris of different people is completely different.

定义2:灰度图像。图像中只包含亮度信息而没有任何其他颜色信息的图像。Definition 2: Grayscale image. An image that contains only luminance information in the image without any other color information.

定义3:归一化虹膜图像。对原始虹膜图像进行定位之后,为消除拍摄时的头部旋转,拍摄距离的远近不一致,瞳孔缩放等问题而进行归一化操作后得到的图像,归一化虹膜图像具有相同的大小。Definition 3: Normalized iris image. After positioning the original iris image, in order to eliminate the head rotation during shooting, the inconsistency of the shooting distance, the pupil scaling and other problems, the image obtained after normalization operation, the normalized iris image has the same size.

定义4:小波变换。时间(空间)频率的局部化分析方法,它通过伸缩平移运算对信号(函数)逐步进行多尺度细化,可聚焦到信号的任意细节。Definition 4: Wavelet transform. A localized analysis method of time (space) frequency, which gradually refines the signal (function) on multiple scales through stretching and translation operations, and can focus on any details of the signal.

定义5:尺度系数。在进行小波变换中,原始信号与尺度函数进行卷积之后得到的系数,用于重构信号的近似分量。对于二维小波变换,尺度系数的具体计算公式为:

Figure GSB00000279475500071
其中,f(x,y)为原始信号,为尺度函数,
Figure GSB00000279475500073
为尺度系数。Definition 5: Scale coefficient. In the wavelet transform, the coefficients obtained after the convolution of the original signal and the scale function are used to reconstruct the approximate components of the signal. For two-dimensional wavelet transform, the specific calculation formula of scale coefficient is:
Figure GSB00000279475500071
Among them, f(x, y) is the original signal, is a scaling function,
Figure GSB00000279475500073
is the scale factor.

定义6:尺度函数。尺度函数是由整数平移和实数二值尺度、平方可积函数

Figure GSB00000279475500081
组成的展开函数集合,即集合
Figure GSB00000279475500082
其中
Figure GSB00000279475500083
j,m∈Z。定义5中的二维小波变换的尺度函数
Figure GSB00000279475500084
是两个一维尺度函数
Figure GSB00000279475500085
Figure GSB00000279475500086
的乘积。Definition 6: Scaling function. The scaling function is composed of integer translation and real binary scale, square integrable function
Figure GSB00000279475500081
The set of expansion functions composed of
Figure GSB00000279475500082
in
Figure GSB00000279475500083
j, m ∈ Z. The scaling function of the 2D wavelet transform in Definition 5
Figure GSB00000279475500084
are two one-dimensional scaling functions
Figure GSB00000279475500085
and
Figure GSB00000279475500086
product of .

定义7:小波系数。在进行小波变换时,原始信号与小波函数进行卷积之后得到的系数,用于重构信号的细节分量。对于二维小波变换,小波系数的具体计算公式为:

Figure GSB00000279475500087
其中,f(x,y)为原始信号,
Figure GSB00000279475500088
为小波函数,
Figure GSB00000279475500089
为小波系数。Definition 7: Wavelet coefficients. When wavelet transform is performed, the coefficients obtained after the convolution of the original signal and the wavelet function are used to reconstruct the detail components of the signal. For two-dimensional wavelet transform, the specific calculation formula of wavelet coefficient is:
Figure GSB00000279475500087
Among them, f(x, y) is the original signal,
Figure GSB00000279475500088
is the wavelet function,
Figure GSB00000279475500089
is the wavelet coefficient.

定义8:小波函数。小波函数是用来描述跨越相邻两尺度空间的差异,是由ψ(x)组成的展开函数集合,即集合{ψj,k(x)}。其中ψj,m(x)=2j/2ψ(2jx-m),j,m∈Z。定义5中的二维小波变换的水平方向敏感的小波函数

Figure GSB000002794755000810
为一维小波函数ψj,m(x)和一维尺度函数的乘积;进行二维小波变换的垂直方向敏感的小波函数
Figure GSB000002794755000812
为一维尺度函数
Figure GSB000002794755000813
和一维小波函数ψj,n(y)的乘积;进行二维小波变换的对角方向敏感的小波函数为两个一维小波函数ψj,m(x)与ψj,n(y)的乘积。Definition 8: Wavelet function. The wavelet function is used to describe the difference across two adjacent scale spaces, and it is a set of expansion functions composed of ψ(x), that is, the set {ψ j, k (x)}. where ψ j, m (x) = 2 j/2 ψ(2 j x m), j, m ∈ Z. The horizontal direction sensitive wavelet function of the two-dimensional wavelet transform in definition 5
Figure GSB000002794755000810
is the one-dimensional wavelet function ψ j, m (x) and one-dimensional scaling function The product of the vertical direction sensitive wavelet function for two-dimensional wavelet transform
Figure GSB000002794755000812
is a one-dimensional scaling function
Figure GSB000002794755000813
and the product of the one-dimensional wavelet function ψ j, n (y); the diagonal direction-sensitive wavelet function for two-dimensional wavelet transformation is the product of two one-dimensional wavelet functions ψ j, m (x) and ψ j, n (y).

定义9:DMeyer小波。离散形式的Meyer小波,是Meyer小波的有效近似,可以看作是离散化的Meyer小波,具有双正交性。它既保持了Meyer小波良好的分频特性,又可以提高数值计算的速度。Definition 9: DMeyer wavelet. Discrete form of Meyer wavelet is an effective approximation of Meyer wavelet, which can be regarded as discretized Meyer wavelet with bioorthogonality. It not only maintains the good frequency division characteristics of Meyer wavelet, but also improves the speed of numerical calculation.

定义10:多分辨率分析。多分辨率分析的思想主要是指将原始图像f(x,y)看作分辨率为20=1下的近似,该近似进一步分解为一粗分辨率2J(J<0)下的近似分量以及一系列高分辨率2j(j>J)下的细节分量渐进逼近之和。Definition 10: Multiresolution analysis. The idea of multi-resolution analysis mainly refers to treating the original image f(x, y) as an approximation at a resolution of 2 0 =1, which is further decomposed into an approximation at a coarse resolution of 2 J (J<0) component and a series of asymptotic approximations of detail components at high resolution 2 j (j>J).

定义11:细节分量。任何一幅图像都可以分解为主体信息和细节纹理信息,根据多分辨率分析的思想,细节分量指不同频段范围内的细节纹理信息。Definition 11: Detail component. Any image can be decomposed into subject information and detail texture information. According to the idea of multi-resolution analysis, the detail component refers to the detail texture information in different frequency bands.

定义12:匹配。将某一具体事物正确地归入某一类别。Definition 12: Matching. Correctly place a specific thing into a category.

定义13。误识率。将同一类的事物归入其他类别的概率,常用FMR表示。Definition 13. False recognition rate. The probability of classifying things of the same class into other classes is often expressed by FMR.

按照本发明的虹膜图像质量判断方法,它包含下列步骤:According to the iris image quality judging method of the present invention, it comprises the following steps:

1、一种虹膜图像质量判断方法,其特征在于其包含下列步骤:1, a kind of iris image quality judging method is characterized in that it comprises the following steps:

步骤1、通过摄像装置,对人眼中的虹膜进行图像采集,从含有虹膜图像的原始灰度图像中得到尺寸为M×N的归一化虹膜图像f(x,y);(x,y)表示像素点的坐标,f(x,y)表示坐标为(x,y)的像素点的灰度值;Step 1, through the camera device, the iris in the human eye is image-acquired, and the normalized iris image f(x, y) whose size is M×N is obtained from the original grayscale image containing the iris image; (x, y) Represents the coordinates of the pixel, f(x, y) represents the gray value of the pixel whose coordinates are (x, y);

步骤2、对步骤1中得到的归一化虹膜图像,进行4层二维小波变换;具体来说,二维小波变换的公式为:其中,

Figure GSB00000279475500093
是分辨率为2j下的尺度系数,
Figure GSB00000279475500094
是分辨率为2j下小波系数,4层小波变换j的取值范围为{-1,-2,-3,-4},i={H,V,D},附加了水平、垂直和对角方向的细节;
Figure GSB00000279475500095
为尺度函数,
Figure GSB00000279475500096
为小波函数,选取的小波为DMeyer小波;Step 2, to the normalized iris image that obtains in step 1, carry out 4 layers of two-dimensional wavelet transform; Specifically, the formula of two-dimensional wavelet transform is: and in,
Figure GSB00000279475500093
is the scale coefficient at a resolution of 2 j ,
Figure GSB00000279475500094
is the wavelet coefficient with a resolution of 2 j , the value range of the 4-layer wavelet transform j is {-1, -2, -3, -4}, i={H, V, D}, and the horizontal, vertical and Diagonal details;
Figure GSB00000279475500095
is a scaling function,
Figure GSB00000279475500096
is a wavelet function, and the selected wavelet is DMeyer wavelet;

步骤3、通过步骤2中得到的分辨率2-1下的水平方向小波系数

Figure GSB00000279475500097
垂直方向小波系数
Figure GSB00000279475500098
和对角方向小波系数重构原始归一化虹膜图像在分辨率2-1下的细节分量
Figure GSB000002794755000910
也即是高频细节分量;具体来说,重构公式为:
Figure GSB000002794755000911
Figure GSB000002794755000912
其中
Figure GSB000002794755000913
表示分辨率2j下坐标(x,y)的细节分量的值,
Figure GSB00000279475500101
表示分辨率2j下的小波系数,
Figure GSB00000279475500102
是i方向敏感的二维小波;∑为累加运算符;Step 3, through the horizontal wavelet coefficients obtained in step 2 at a resolution of 2 -1
Figure GSB00000279475500097
Vertical wavelet coefficient
Figure GSB00000279475500098
and the diagonal wavelet coefficients Reconstruct the detail component of the original normalized iris image at resolution 2 -1
Figure GSB000002794755000910
That is, the high-frequency detail component; specifically, the reconstruction formula is:
Figure GSB000002794755000911
Figure GSB000002794755000912
in
Figure GSB000002794755000913
represents the value of the detail component of the coordinate (x, y) at resolution 2j ,
Figure GSB00000279475500101
Indicates the wavelet coefficients at resolution 2 j ,
Figure GSB00000279475500102
is a two-dimensional wavelet sensitive to the i direction; ∑ is an accumulation operator;

步骤4、计算步骤3中得到的高频细节分量

Figure GSB00000279475500103
的绝对值
Figure GSB00000279475500104
具体来说,如果
Figure GSB00000279475500105
如果
Figure GSB00000279475500107
| D 2 - 1 f ( x , y ) | = - D 2 - 1 f ( x , y ) ; Step 4. Calculate the high-frequency detail components obtained in step 3
Figure GSB00000279475500103
absolute value of
Figure GSB00000279475500104
Specifically, if
Figure GSB00000279475500105
if
Figure GSB00000279475500107
| D. 2 - 1 f ( x , the y ) | = - D. 2 - 1 f ( x , the y ) ;

步骤5、统计步骤4中得到的

Figure GSB00000279475500109
的值大于阈值Vo的像素点的数目,将
Figure GSB000002794755001010
的值大于阈值Vo的点作为眼睑和睫毛的边界点;Vo为判断像素点是否为眼睑和睫毛边界点的阈值,具体计算公式为:
Figure GSB000002794755001011
其中M和N分别为原始归一化虹膜图像的宽度和高度, Step 5, statistics obtained in step 4
Figure GSB00000279475500109
The number of pixels whose value is greater than the threshold V o will be
Figure GSB000002794755001010
The point whose value is greater than the threshold V o is used as the boundary point of the eyelid and eyelashes; V o is the threshold for judging whether the pixel point is the boundary point of the eyelid and eyelashes, and the specific calculation formula is:
Figure GSB000002794755001011
Where M and N are the width and height of the original normalized iris image respectively,

步骤6、比较步骤5中计算的

Figure GSB000002794755001013
值与阈值TN作比较;如果
Figure GSB000002794755001014
则认为该图像为眼睑和睫毛遮挡的图像,如果
Figure GSB000002794755001015
则认为该图像为可处理的正常虹膜图像;Step 6, compare the calculated in step 5
Figure GSB000002794755001013
The value is compared with the threshold T N ; if
Figure GSB000002794755001014
The image is considered to be an image occluded by eyelids and eyelashes, if
Figure GSB000002794755001015
Then it is considered that the image is a normal iris image that can be processed;

步骤7、按照与步骤3中的方法,通过步骤2中得到的分辨率2-2下的水平方向小波系数

Figure GSB000002794755001016
垂直方向小波系数和对角方向小波系数
Figure GSB000002794755001018
重构原始归一化虹膜图像在分辨率2-2下的细节分量
Figure GSB000002794755001019
Step 7. According to the method in step 3, pass the horizontal direction wavelet coefficients obtained in step 2 under the resolution 2-2
Figure GSB000002794755001016
Vertical wavelet coefficient and the diagonal wavelet coefficients
Figure GSB000002794755001018
Reconstruct the detail component of the original normalized iris image at resolution 2 -2
Figure GSB000002794755001019

步骤8、计算步骤7中得到的

Figure GSB000002794755001020
的方差;具体的计算公式为:
Figure GSB000002794755001021
其中,Var为分辨率2-2下细节分量的方差,M和N分别为原始归一化虹膜图像的宽度和高度,m的计算公式为: m = &Sigma; x = 1 M &Sigma; y = 1 N D 2 - 2 f ( x , y ) / M &times; N ; Step 8, calculate the obtained in step 7
Figure GSB000002794755001020
The variance; the specific calculation formula is:
Figure GSB000002794755001021
Among them, Var is the variance of the detail component at resolution 2-2 , M and N are the width and height of the original normalized iris image respectively, and the calculation formula of m is: m = &Sigma; x = 1 m &Sigma; the y = 1 N D. 2 - 2 f ( x , the y ) / m &times; N ;

步骤9、将步骤8中得到的方差Var与判别虹膜清晰度的阈值Tv进行比较,若Var≥Tv,则该虹膜图像清晰度满足系统要求;若Var<Tv,则该虹膜图像清晰度不满足系统要求。Step 9. Compare the variance Var obtained in step 8 with the threshold T v for judging iris clarity, if Var≥T v , then the iris image clarity meets the system requirements; if Var<T v , then the iris image is clear The degree does not meet the system requirements.

通过以上步骤,我们就能通过分析从原始的含有虹膜的图像中提取出归一化的虹膜图像判断出该图像是否满足系统的要求。Through the above steps, we can judge whether the image meets the requirements of the system by analyzing the normalized iris image extracted from the original image containing iris.

需要说明的是:It should be noted:

1.步骤1中的虹膜归一化操作,必须是在虹膜定位之后进行。1. The iris normalization operation in step 1 must be performed after iris positioning.

2.步骤2中进行二维小波变换的尺度函数

Figure GSB00000279475500112
是两个一维尺度函数
Figure GSB00000279475500113
Figure GSB00000279475500114
的乘积。进行二维小波变换的水平方向敏感的小波函数
Figure GSB00000279475500115
为一维小波函数ψj,m(x)和一维尺度函数
Figure GSB00000279475500116
的乘积;进行二维小波变换的垂直方向敏感的小波函数
Figure GSB00000279475500117
为一维尺度函数
Figure GSB00000279475500118
和一维小波函数ψj,n(y)的乘积;进行二维小波变换的对角方向敏感的小波函数
Figure GSB00000279475500119
为两个一维小波函数ψj,m(x)与ψj,n(y)的乘积。2. Scaling function for two-dimensional wavelet transform in step 2
Figure GSB00000279475500112
are two one-dimensional scaling functions
Figure GSB00000279475500113
and
Figure GSB00000279475500114
product of . Horizontal sensitive wavelet function for two-dimensional wavelet transform
Figure GSB00000279475500115
is the one-dimensional wavelet function ψ j, m (x) and one-dimensional scaling function
Figure GSB00000279475500116
The product of the vertical direction sensitive wavelet function for two-dimensional wavelet transform
Figure GSB00000279475500117
is a one-dimensional scaling function
Figure GSB00000279475500118
and the product of the one-dimensional wavelet function ψ j, n (y); the diagonal direction-sensitive wavelet function for two-dimensional wavelet transformation
Figure GSB00000279475500119
is the product of two one-dimensional wavelet functions ψ j, m (x) and ψ j, n (y).

3.步骤3,4,5中选择分辨率2-1下的细节分量进行眼睑和睫毛遮挡的分析,是因为在眼睑和睫毛的边缘,灰度图像上存在明显的灰度变化,根据多分辨率分析的思想,这些位置的点对应着高频细节分量的较大幅值。3. In steps 3, 4, and 5, select the detail component under resolution 2-1 to analyze the occlusion of eyelids and eyelashes, because there are obvious grayscale changes on the grayscale image at the edge of the eyelids and eyelashes, according to the multi-resolution Based on the idea of rate analysis, the points at these positions correspond to the larger magnitudes of the high-frequency detail components.

4.步骤5中的阈值Vo用于判断高频细节分量上的点是否是眼睑和睫毛的边缘点。认为高频细节分量幅值

Figure GSB000002794755001110
大于Vo的点就是眼睑和睫毛的边缘点,是因为在眼睑和睫毛的边缘位置处,存在灰度值的明显跳变,对应着高频细节分量上幅值较大的点;而虹膜的纹理边缘位置处,灰度变换较为缓慢,对应着高频细节分量上幅值较小的点。当高频细节分量幅值
Figure GSB00000279475500121
大于某一值时,该点就是眼睑和睫毛的边缘点。4. The threshold V o in step 5 is used to judge whether the point on the high-frequency detail component is the edge point of the eyelid and eyelashes. The magnitude of the high-frequency detail component
Figure GSB000002794755001110
Points greater than V o are the edge points of the eyelids and eyelashes, because at the edge of the eyelids and eyelashes, there is an obvious jump in the gray value, corresponding to a point with a larger amplitude on the high-frequency detail component; while the iris At the edge of the texture, the grayscale transformation is relatively slow, corresponding to the point with a smaller amplitude on the high-frequency detail component. When the amplitude of high-frequency detail components
Figure GSB00000279475500121
Above a certain value, the point is the edge point of the eyelids and eyelashes.

5.步骤6中提到的阈值TN是用于判断该图像是否是可以处理的无眼睑和睫毛遮挡的图像。TN的确定与后续的匹配算法有关,我们将其设定为

Figure GSB00000279475500122
的虹膜图像匹配,误识率最低时对应的TN。5. The threshold TN mentioned in step 6 is used to judge whether the image is an image without eyelids and eyelashes that can be processed. The determination of T N is related to the subsequent matching algorithm, we set it as
Figure GSB00000279475500122
The iris image matches the corresponding T N when the false recognition rate is the lowest.

6.步骤7,8中选取归一化虹膜图像在分辨率2-2下的细节分量

Figure GSB00000279475500123
进行虹膜清晰度的分析,是因为虹膜纹理在灰度图像上变化较为缓慢,根据多分辨率分析的思想,这一变化多体现在中频细节分量
Figure GSB00000279475500124
虹膜图像越清晰,中频细节分量的方差Var越大;虹膜图像越模糊,中频细节分量的方差Var越小。6. In steps 7 and 8, select the detail component of the normalized iris image at resolution 2-2
Figure GSB00000279475500123
The analysis of iris clarity is because the iris texture changes slowly on the grayscale image. According to the idea of multi-resolution analysis, this change is mostly reflected in the intermediate frequency detail component
Figure GSB00000279475500124
The clearer the iris image, the larger the variance Var of the intermediate frequency detail component; the blurrier the iris image, the smaller the variance Var of the intermediate frequency detail component.

7.步骤9中的阈值Tv是用于判断虹膜图像是否清晰的,Tv的确定与后续的匹配算法有关。7. The threshold T v in step 9 is used to judge whether the iris image is clear, and the determination of T v is related to the subsequent matching algorithm.

本发明采用多分辨率分析的方法,首先通过提取原始灰度图像中的虹膜并进行归一化;然后对归一化虹膜图像进行多分辨率分解,分别得到分辨率2-1和分辨率2-2下的细节分量;最后根据分辨率2-1下的细节分量的较大幅值点的数目判断该图像是否存在眼睑和睫毛遮挡问题,根据分辨率2-2下细节分量的方差判断虹膜图像是否清晰。采用本发明提出的基于多分辨率分析的方法,可以有效的进行虹膜图像质量的评价,避免了传统算法对光照较为敏感的问题。The present invention adopts the method of multi-resolution analysis, first by extracting the iris in the original grayscale image and normalizing it; then performing multi-resolution decomposition on the normalized iris image to obtain resolution 2-1 and resolution 2 respectively The detail component under -2 ; finally judge whether the image has the problem of eyelid and eyelash occlusion according to the number of larger amplitude points of the detail component under resolution 2 -1 , and judge the iris image according to the variance of the detail component under resolution 2 -2 Is it clear. By adopting the method based on multi-resolution analysis proposed by the present invention, the iris image quality can be effectively evaluated, and the problem that traditional algorithms are sensitive to light is avoided.

采用本发明的方法,首先使用C语言编写虹膜图像质量评估程序;然后采用CMOS或者CCD摄像装置自动拍摄虹膜的原始图像;接着把拍摄到的虹膜原始图像作为源数据输入到PC平台上的虹膜图像质量评估程序中进行处理;经过虹膜定位、归一化和图像质量评估后给出图像是否满足系统要求的判断。采用2400张拍摄好的、包括不同人的不同光照条件、不同拍摄姿势的灰度虹膜图像作为源数据,将程序判断的结果与主观判断的结果进行比较,错误概率为1.2%,每幅图像的处理时间<150ms。Adopt the method of the present invention, at first use C language to write the iris image quality evaluation program; Then adopt CMOS or CCD camera to take the original image of iris automatically; Then the iris original image that is taken is input to the iris image on the PC platform as source data It is processed in the quality evaluation program; after iris positioning, normalization and image quality evaluation, it gives the judgment whether the image meets the system requirements. Using 2,400 gray-scale iris images taken by different people, including different lighting conditions and different shooting postures, as source data, the results of the program judgment are compared with the results of subjective judgment. The error probability is 1.2%. Processing time <150ms.

综上所述,本发明的方法充分利用虹膜的纹理信息,结合多分辨率分析的方法,从而实现了快速准确的判断虹膜图像的质量。To sum up, the method of the present invention makes full use of the texture information of the iris, combined with the method of multi-resolution analysis, so as to realize the fast and accurate judgment of the quality of the iris image.

Claims (2)

1.一种虹膜图像质量判断方法,其特征在于其包含下列步骤:1. a method for judging iris image quality, is characterized in that it comprises the following steps: 步骤1、通过摄像装置,对人眼中的虹膜进行图像采集,从含有虹膜图像的原始灰度图像中得到尺寸为M×N的归一化虹膜图像f(x,y);(x,y)表示像素点的坐标,f(x,y)表示坐标为(x,y)的像素点的灰度值;Step 1, through the camera device, the iris in the human eye is image-acquired, and the normalized iris image f(x, y) whose size is M×N is obtained from the original grayscale image containing the iris image; (x, y) Represents the coordinates of the pixel, f(x, y) represents the gray value of the pixel whose coordinates are (x, y); 步骤2、对步骤1中得到的归一化虹膜图像,进行4层二维小波变换;具体来说,二维小波变换的公式为:
Figure FSB00000279475400012
其中,
Figure FSB00000279475400013
是分辨率为2j下的尺度系数,
Figure FSB00000279475400014
是分辨率为2j下小波系数,4层小波变换j的取值范围为{-1,-2,-3,-4},i={H,V,D},附加了水平、垂直和对角方向的细节;
Figure FSB00000279475400015
为尺度函数,
Figure FSB00000279475400016
为小波函数,选取的小波为DMeyer小波;进行二维小波变换的尺度函数是两个一维尺度函数
Figure FSB00000279475400018
的乘积;进行二维小波变换的水平方向敏感的小波函数
Figure FSB000002794754000110
为一维小波函数ψj,m(x)和一维尺度函数的乘积;进行二维小波变换的垂直方向敏感的小波函数
Figure FSB000002794754000112
为一维尺度函数
Figure FSB000002794754000113
和一维小波函数ψj,n(y)的乘积;进行二维小波变换的对角方向敏感的小波函数
Figure FSB000002794754000114
为两个一维小波函数ψj,m(x)与ψj,n(y)的乘积;
Step 2, to the normalized iris image that obtains in step 1, carry out 4 layers of two-dimensional wavelet transform; Specifically, the formula of two-dimensional wavelet transform is: and
Figure FSB00000279475400012
in,
Figure FSB00000279475400013
is the scale coefficient at a resolution of 2 j ,
Figure FSB00000279475400014
is the wavelet coefficient with a resolution of 2 j , the value range of the 4-layer wavelet transform j is {-1, -2, -3, -4}, i={H, V, D}, and the horizontal, vertical and Diagonal details;
Figure FSB00000279475400015
is a scaling function,
Figure FSB00000279475400016
is a wavelet function, and the selected wavelet is DMeyer wavelet; the scaling function for two-dimensional wavelet transformation are two one-dimensional scaling functions
Figure FSB00000279475400018
and The product of the horizontal direction sensitive wavelet function for two-dimensional wavelet transform
Figure FSB000002794754000110
is the one-dimensional wavelet function ψ j, m (x) and one-dimensional scaling function The product of the vertical direction sensitive wavelet function for two-dimensional wavelet transform
Figure FSB000002794754000112
is a one-dimensional scaling function
Figure FSB000002794754000113
and the product of the one-dimensional wavelet function ψ j, n (y); the diagonal direction-sensitive wavelet function for two-dimensional wavelet transformation
Figure FSB000002794754000114
is the product of two one-dimensional wavelet functions ψ j, m (x) and ψ j, n (y);
步骤3、通过步骤2中得到的分辨率2-1下的水平方向小波系数垂直方向小波系数和对角方向小波系数
Figure FSB000002794754000117
重构原始归一化虹膜图像在分辨率2-1下的细节分量也即是高频细节分量;具体来说,重构公式为:
Figure FSB000002794754000119
Figure FSB00000279475400021
其中
Figure FSB00000279475400022
表示分辨率2j下坐标(x,y)的细节分量的值,
Figure FSB00000279475400023
表示分辨率2j下的小波系数,
Figure FSB00000279475400024
是i方向敏感的二维小波;∑为累加运算符;
Step 3, through the horizontal wavelet coefficients obtained in step 2 at a resolution of 2 -1 Vertical wavelet coefficient and the diagonal wavelet coefficients
Figure FSB000002794754000117
Reconstruct the detail component of the original normalized iris image at resolution 2 -1 That is, the high-frequency detail component; specifically, the reconstruction formula is:
Figure FSB000002794754000119
Figure FSB00000279475400021
in
Figure FSB00000279475400022
represents the value of the detail component of the coordinate (x, y) at resolution 2j ,
Figure FSB00000279475400023
Indicates the wavelet coefficients at resolution 2 j ,
Figure FSB00000279475400024
is a two-dimensional wavelet sensitive to the i direction; ∑ is an accumulation operator;
步骤4、计算步骤3中得到的高频细节分量
Figure FSB00000279475400025
的绝对值
Figure FSB00000279475400026
具体来说,如果
Figure FSB00000279475400027
Figure FSB00000279475400028
如果
Figure FSB00000279475400029
| D 2 - 1 f ( x , y ) | = - D 2 - 1 f ( x , y ) ;
Step 4. Calculate the high-frequency detail components obtained in step 3
Figure FSB00000279475400025
absolute value of
Figure FSB00000279475400026
Specifically, if
Figure FSB00000279475400027
Figure FSB00000279475400028
if
Figure FSB00000279475400029
| D. 2 - 1 f ( x , the y ) | = - D. 2 - 1 f ( x , the y ) ;
步骤5、统计步骤4中得到的的值大于阈值Vo的像素点的数目,将
Figure FSB000002794754000212
的值大于阈值Vo的点作为眼睑和睫毛的边界点;Vo为判断像素点是否为眼睑和睫毛边界点的阈值,具体计算公式为:
Figure FSB000002794754000213
其中M和N分别为原始归一化虹膜图像的宽度和高度,步骤6、比较步骤5中计算的
Figure FSB000002794754000215
值与阈值TN作比较;如果
Figure FSB000002794754000216
则认为该图像为眼睑和睫毛遮挡的图像,如果
Figure FSB000002794754000217
则认为该图像为可处理的正常虹膜图像;
Step 5, statistics obtained in step 4 The number of pixels whose value is greater than the threshold V o will be
Figure FSB000002794754000212
The point whose value is greater than the threshold V o is used as the boundary point of the eyelid and eyelashes; V o is the threshold for judging whether the pixel point is the boundary point of the eyelid and eyelashes, and the specific calculation formula is:
Figure FSB000002794754000213
Where M and N are the width and height of the original normalized iris image respectively, Step 6, compare the calculated in step 5
Figure FSB000002794754000215
The value is compared with the threshold T N ; if
Figure FSB000002794754000216
The image is considered to be an image occluded by eyelids and eyelashes, if
Figure FSB000002794754000217
Then it is considered that the image is a normal iris image that can be processed;
步骤7、按照与步骤3中的方法,通过步骤2中得到的分辨率2-2下的水平方向小波系数垂直方向小波系数
Figure FSB000002794754000219
和对角方向小波系数
Figure FSB000002794754000220
重构原始归一化虹膜图像在分辨率2-2下的细节分量
Figure FSB000002794754000221
Step 7. According to the method in step 3, pass the horizontal direction wavelet coefficients obtained in step 2 under the resolution 2-2 Vertical wavelet coefficient
Figure FSB000002794754000219
and the diagonal wavelet coefficients
Figure FSB000002794754000220
Reconstruct the detail component of the original normalized iris image at resolution 2 -2
Figure FSB000002794754000221
步骤8、计算步骤7中得到的
Figure FSB000002794754000222
的方差;具体的计算公式为:
Figure FSB000002794754000223
其中,Var为分辨率2-2下细节分量的方差,M和N分别为原始归一化虹膜图像的宽度和高度,m的计算公式为: m = &Sigma; x = 1 M &Sigma; y = 1 N D 2 - 2 f ( x , y ) / M &times; N ;
Step 8, calculate the obtained in step 7
Figure FSB000002794754000222
The variance; the specific calculation formula is:
Figure FSB000002794754000223
Among them, Var is the variance of the detail component at resolution 2-2 , M and N are the width and height of the original normalized iris image respectively, and the calculation formula of m is: m = &Sigma; x = 1 m &Sigma; the y = 1 N D. 2 - 2 f ( x , the y ) / m &times; N ;
步骤9、将步骤8中得到的方差Var与判别虹膜清晰度的阈值Tv进行比较,若Var≥Tv,则该虹膜图像清晰度满足系统要求;若Var<Tv,则该虹膜图像清晰度不满足系统要求。Step 9: Compare the variance Var obtained in step 8 with the threshold T v for judging iris clarity, if Var≥T v , then the iris image clarity meets the system requirements; if Var<T v , then the iris image is clear The degree does not meet the system requirements.
2.根据权利要求1所述的一种虹膜图像质量判断方法,其特征在于步骤6中提到的阈值TN是用于判断该图像是否是可以处理的无眼睑和睫毛遮挡的图像,TN的确定与后续的匹配算法有关,将其设定为
Figure FSB00000279475400031
的虹膜图像匹配,误识率最低时对应的TN
2. a kind of iris image quality judging method according to claim 1, it is characterized in that the threshold TN mentioned in step 6 is to be used for judging whether this image is the image that can be processed without eyelids and eyelashes blocking, TN The determination of is related to the subsequent matching algorithm, which is set as
Figure FSB00000279475400031
The iris image matches the corresponding T N when the false recognition rate is the lowest.
CN2008100259896A 2008-01-19 2008-01-19 A method for judging the quality of iris images Expired - Fee Related CN101241550B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2008100259896A CN101241550B (en) 2008-01-19 2008-01-19 A method for judging the quality of iris images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2008100259896A CN101241550B (en) 2008-01-19 2008-01-19 A method for judging the quality of iris images

Publications (2)

Publication Number Publication Date
CN101241550A CN101241550A (en) 2008-08-13
CN101241550B true CN101241550B (en) 2011-04-13

Family

ID=39933068

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2008100259896A Expired - Fee Related CN101241550B (en) 2008-01-19 2008-01-19 A method for judging the quality of iris images

Country Status (1)

Country Link
CN (1) CN101241550B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101030652B1 (en) * 2008-12-16 2011-04-20 아이리텍 잉크 Apparatus and method for acquiring high quality eye image for iris recognition
CN102129556B (en) * 2011-04-14 2012-09-12 电子科技大学 Judging method of definition of iris image
CN105447440B (en) * 2015-03-13 2019-03-26 北京眼神智能科技有限公司 Real-time iris image evaluation method and device
CN105574865B (en) * 2015-12-14 2019-11-12 沈阳工业大学 Method of extracting eyelashes based on improved ant colony algorithm
CN107368791A (en) * 2017-06-29 2017-11-21 广东欧珀移动通信有限公司 Living iris detection method and Related product
CN110363753B (en) * 2019-07-11 2021-06-22 北京字节跳动网络技术有限公司 Image quality evaluation method and device and electronic equipment
CN110781747B (en) * 2019-09-23 2022-03-01 杭州电子科技大学 A pre-detection method of eyelash occlusion area based on coefficient of variation
CN112712550A (en) * 2019-10-24 2021-04-27 马上消费金融股份有限公司 Image quality evaluation method and device
CN111553880B (en) * 2020-03-26 2024-11-08 北京中科虹霸科技有限公司 Model generation method, label marking method, iris image quality evaluation method and device

Also Published As

Publication number Publication date
CN101241550A (en) 2008-08-13

Similar Documents

Publication Publication Date Title
Chen et al. Liveness detection for iris recognition using multispectral images
CN101241550B (en) A method for judging the quality of iris images
CN101266645B (en) A method of iris localization based on multi-resolution analysis
Ng et al. A review of iris recognition algorithms
CN100373397C (en) A kind of iris image preprocessing method
Jan Segmentation and localization schemes for non-ideal iris biometric systems
Barpanda et al. Iris feature extraction through wavelet mel-frequency cepstrum coefficients
CN111523344B (en) Human body living body detection system and method
Huang et al. A novel iris segmentation using radial-suppression edge detection
CN109934118A (en) A method for identifying veins on the back of the hand
Ahamed et al. Low complexity iris recognition using curvelet transform
Abidin et al. Iris segmentation analysis using integro-differential and hough transform in biometric system
Barpanda et al. Region based feature extraction from non-cooperative iris images using triplet half-band filter bank
Chang et al. Using empirical mode decomposition for iris recognition
Zhou et al. Multimodal eye recognition
Ramsoful et al. Feature extraction techniques for dorsal hand vein pattern
Kahlil et al. Generation of iris codes using 1d log-gabor filter
Sharma et al. Improved human identification using finger vein images
Chowdhary Analysis of Unimodal and Multimodal Biometric System
Subbarayudu et al. A novel iris recognition system
Bremananth et al. New methodology for a person identification system
Ekinci et al. Kernel Fisher discriminant analysis of Gabor features for online palmprint verification
Chawla et al. A robust segmentation method for iris recognition
Sharma et al. Iris Recognition-An Effective Human Identification
Tajbakhsh et al. Feature fusion as a practical solution toward noncooperative iris recognition

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20110413

Termination date: 20170119

CF01 Termination of patent right due to non-payment of annual fee