CN102663372A - Iris texture normalization method based on dual-spring model - Google Patents

Abstract

The iris texture normalization method based on the double spring model of the present invention includes setting the ratio of the pupil radius to the iris radius under the iris standard state and the ratio of the near pupil area width to the (near pupil area+far pupil area) width under the iris standard state ; Set the number of rows to be sampled in the near pupil area and the far pupil area; model the near pupil area and the far pupil area as a series of springs with different elastic coefficients; calculate the pupil radius, near pupil area width and The width of the far pupil area; divide the inner and outer circumferences of the iris into equal parts, calculate the coordinates of a point on the edge of the pupil and the coordinates of the corresponding point on the edge of the iris, and calculate the distance between the two points; determine that the iris is in a non-standard state, and calculate the near pupil area in this state and the width of the far pupil area and perform linear sampling on the near pupil area and the far pupil area; normalize the sampling points into a rectangular image; this method is more convenient and practical than the existing nonlinear normalization method, and can reduce the pupil scaling The error can improve the recognition rate of iris recognition.

Description

A Normalization Method of Iris Texture Based on Double Spring Model

technical field

The invention relates to the technical field of eye iris recognition, in particular to an iris texture normalization method.

Background technique

With the development of network and information technology, personal identification has received unprecedented attention and is facing more and more severe tests. Biometrics is an emerging research discipline that uses various physiological and morphological characteristics inherent in the human body as the identification medium to uniquely identify individuals and conduct personal identity authentication. Compared with traditional identification methods, identification technology based on biometric identification has the advantages of not being easily forgotten or lost, good anti-counterfeiting performance, and portable.

As an important biological feature, the iris has the advantages of natural protected characteristics, high complexity, high stability, and high anti-counterfeiting when used for identification. Iris recognition is one of the most accurate methods compared to other biometric technologies. Therefore, the identity authentication technology based on iris has been paid more and more attention by academic circles and business circles. The iris is located in the ring-shaped part between the black pupil and the white sclera of the human eye, which presents a radial structure from the inside out, including many interlaced subtle features similar to spots, fine lines, crowns, crypts, etc. Texture information called iris.

As shown in Figure 1, the existing iris recognition authentication method includes the following steps: iris image acquisition step, image preprocessing step, iris location step, iris normalization step, feature extraction step and feature matching step. Wherein, the iris image acquisition step is used to collect an iris image that can be identified and contains rich detailed information; the image preprocessing step is used to judge whether there is an iris in the iris image collected, whether the image is clear and whether it is a live collection; iris positioning The step is used to locate the inner and outer circles of the iris and the eyelids; the iris normalization step is used to normalize the iris image into a fixed-resolution rectangular image, wherein the rectangular image contains all available iris texture information; the feature extraction step is responsible for The iris texture information is encoded into appropriate pattern information that can be used for identification; the feature matching step is used to compare the two iris feature codes to determine whether they are from the same eye.

At present, the iris normalization method in most iris recognition and authentication methods is a linear normalization method of iris texture, that is, the iris is mapped from a ring to a fixed-scale rectangle in a linear mapping manner. This type of method linearly divides the corresponding points on the inner and outer circumferences of the iris. However, when the iris image is taken, changes in the external light will cause the pupil to scale, and the pupil scale will cause the iris texture to scale accordingly. This scaling is non-uniform and non-linear. Therefore, the linear normalization method of iris texture cannot eliminate this uneven scaling, which will reduce the accuracy of subsequent iris recognition. Among them, the uneven scaling of the iris texture is determined by the physiological characteristics of the iris. Ophthalmological studies have shown that the contraction and enlargement of the pupil is mainly the result of the joint action of the circular muscle fibers and radial muscle fibers of the iris. The circular muscle fibers are distributed near the inner edge of the iris, and the radial muscle fibers are distributed near the outer edge of the iris. Among them, the circular muscle fibers constitute the main part of the iris texture. When the pupil is stimulated by light to contract and dilate, the circular muscle fibers close to the inner edge of the iris expand and contract greatly, while the radial muscle fibers at the periphery expand and contract only slightly. At this time, the texture of the inner edge of the iris will be significantly compressed Or stretch, with little change in the texture of the outer edge of the iris. Therefore, the contraction and expansion of the iris texture is not uniform linear, but nonlinear, and does not have affine invariance. As shown in Figure 2, you can clearly see the different expansion and contraction conditions of the near pupil area and the far pupil area.

Due to the deficiency of the linear normalization method of iris texture, a non-linear normalization method of iris texture is proposed. For example, the patent titled "Nonlinear Normalization Method of Human Iris Texture", the patent publication number of which is CN1776710A discloses a non-linear iris texture normalization method. The method first uses the arc structure to perform radial non-linear normalization. The circular iris region is optimized such that all iris images have the same degree of pupil scaling. Another example is the patent whose title is "iris texture normalization processing method" publication number CN1445714A. Correct for uneven scaling. The above two nonlinear normalization methods are improved compared with the traditional linear normalization method, and both use relevant mathematical models to correct the nonlinear compression of the iris, but the above two calculation methods are relatively complicated and the amount of calculation Large, difficult to engineer, and the actual effect is not accurate enough.

Contents of the invention

In order to solve one of the problems of the above-mentioned existing methods, the present invention provides a spring model-based iris texture normalization method, which is more accurate and reliable than the existing linear normalization method, and more accurate and reliable than the existing nonlinear normalization method. The integrated method is more convenient and practical, and can well reduce the error caused by the zooming of the pupil, which provides convenience for the subsequent iris feature extraction, and improves the overall recognition rate of iris recognition.

The present invention is a kind of iris texture normalization method based on double spring model, comprises the following steps:

Step 1, the ratio dRPTol of pupil radius and iris radius under the iris standard state and the ratio dRNToall of the near pupil area width and (near pupil area+far pupil area) width under the iris standard state; Set the near pupil area and the far pupil area The number of rows m ₁ and m ₂ to be sampled, where m ₁ and m ₂ are integers greater than 0, and m ₁ +m ₂ =m; the near pupil area and the far pupil area are modeled as having unit elastic coefficients k1 and k2 respectively The springs are connected in series, where k ₁ <k ₂ ;

Step 2, obtain the iris radius R _I of the collected iris image, and calculate the pupil radius R _TO , the width dA0 of the near pupil area and the width of the far pupil area in the standard state according to the dRPTol, dRNToall and iris radius R _I dB0;

Step 3, divide the iris inner and outer circumferences of the collected iris image into n equal parts, calculate the coordinates (x _pi , y _pi ) of a point on the edge of the pupil and the coordinates (x _Ij , y _Ij ), calculate the distance dI between the pupil edge point and the iris edge point according to (x _pi , y _pi ) and (x _Ij , y _Ij ), wherein, n is an integer greater than 0;

Step 4, when dI≠dA0+dB0, determine that the iris image collected is in the iris non-standard state, calculate the width dA1 of the near pupil area and the width dB1 of the far pupil area under the iris non-standard state according to the following formula:

$\frac{\mathrm{<span\; class="notranslate">\; k</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; D</span>}\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; D</span>}\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; D</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; k</span>}\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; dB</span>}\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; dB</span>}\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; dB</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

dA1+dB1=dI;

Step 5, according to the calculated dA1 and dB1, respectively carry out m ₁ line and m ₂ line linear sampling to the near pupil area and the far pupil area under the iris non-standard state to obtain sampling points;

In step 6, the sampling points are normalized into a rectangular image with a resolution of m×n through bilinear interpolation.

Preferably, in step 1, the number of lines m ₁ =m×dRPTol to be sampled in the near-pupil area, and m ₂ =mm ₁ to be sampled in the far-pupil area.

Preferably, in step 2, the width of the near pupil area dA0=dRNToall×(1-dRPTol)×R _I , and the width of the far pupil area dB0=(1-dRPTol)× _RI −dA0.

Preferably, in step 3,

${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; pupil</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; cos</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span><span\; class="notranslate">\; ;</span>$

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; pupil</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; sin</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span><span\; class="notranslate">\; ;</span>$

Among them, (x _pI , y _pI ) is the coordinate point of the center of the pupil, and R _pupil is the radius of the pupil.

${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; I</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; cos</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span><span\; class="notranslate">\; ;</span>$

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; I</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; sin</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span>$

Among them, (x _pI , y _pI ) is the coordinate point of the center of the pupil, and R _I is the radius of the iris.

The distance between the pupil edge point and the iris edge point:

$\mathrm{<span\; class="notranslate">\; iGO</span>}<span\; class="notranslate">\; =</span>\sqrt[\mathrm{<span\; class="notranslate">\; 2</span>}]{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

The iris texture normalization method based on the spring model provided by the present invention can be more accurate and reliable than the existing linear normalization method, more convenient and practical than the existing nonlinear normalization method, and can reduce The error caused by the zooming of the pupil provides convenience for subsequent iris feature extraction, and improves the overall recognition rate of iris recognition.

Description of drawings

The above and/or additional aspects and advantages of the present invention will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

Figure 1 is a schematic diagram of the system structure of the iris recognition method.

Fig. 2 is a schematic diagram of the change of the near-pupil area and the far-pupil area under different external conditions and different zooming degrees of the pupil.

Fig. 3 is a flow chart of the iris texture normalization method based on the spring model of the present invention.

FIG. 4A is a schematic diagram of the iris radius of the acquired iris image obtained in the present invention.

FIG. 4B is a schematic diagram of the inner and outer circumferences of the iris of the collected iris image of the present invention.

FIG. 4C is a schematic diagram of a rectangular image normalized to m×n according to the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

Fig. 3 is a flow chart of the iris texture normalization method based on the spring model of the present invention. Referring to Fig. 3, the present invention is a kind of iris texture normalization method based on double spring model, comprises the steps: Step 1, the ratio dRPTol of pupil radius and iris radius under setting iris standard state and iris near pupil area under iris standard state Ratio dRNToall of the width to the width of (near pupil area + far pupil area); set the number of lines m ₁ and m ₂ to be sampled in the near pupil area and the far pupil area, where m ₁ and m ₂ are integers greater than 0, and m ₁ +m ₂ =m; the near pupil area and the far pupil area are modeled as a series of springs with unit elastic coefficients k1 and k2 respectively, where k ₁ <k ₂ ; step 2, obtain the iris radius R _I of the collected iris image , according to the dRPTol, dRNToall and iris radius R _I , calculate the pupil radius R _TO under the standard state, the width dA0 of the near pupil area and the width dB0 of the far pupil area; step 3, the iris inside and outside of the iris image collected The circumference is divided into n equal parts respectively, and the coordinates (x _pi , y _pi ) of a point on the edge of the pupil and the coordinates (x _Ij , y _Ij ) of the corresponding point on the edge of the iris are calculated according to (x _pi , y _pi ) and (x _Ij , y _Ij ) calculate the distance dI between the pupil edge point and the iris edge point, wherein, n is an integer greater than 0; step 4, when dI≠dA0+dB0, determine the collected iris The image is in a non-standard iris state, and the width dA1 of the near pupil area and the width dB1 of the far pupil area in the iris non-standard state are calculated according to the following formula:

$\frac{\mathrm{<span\; class="notranslate">\; k</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; D</span>}\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; D</span>}\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; D</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; k</span>}\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; dB</span>}\mathrm{<span\; class="notranslate">\; 0</span>}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; dB</span>}\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; dB</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

dA1+dB1=dI; Step 5, according to calculated dA1 and dB1, the near pupil area and the far pupil area under the iris non-standard state are respectively carried out m ₁ line and m ₂ line linear sampling to obtain sampling points; Step 6, The sampling points are normalized into a rectangular image with a resolution of m×n through bilinear interpolation.

Through the iris texture normalization method based on the double spring model of the present invention, the linear method can still be used for sampling, but it is more accurate and reliable than the existing linear normalization method, and more convenient and practical than the nonlinear normalization method, The error caused by pupil scaling can be well reduced, which provides convenience for subsequent iris feature extraction, and improves the overall recognition rate of iris recognition.

Wherein, in step 1, the number of lines m ₁ =m×dRPTol to be sampled in the near-pupil area, and m ₂ =mm ₁ to be sampled in the far-pupil area.

In step 2, referring to Fig. 4A, the iris radius R ₁ of the collected iris image is obtained by the iris positioning link, and the width dA0 of the near pupil area and the width dB0 of the far pupil area can be obtained by the following formula Calculation: dA0=dRNToall×(1-dRPTol)× _RI , the width of the far pupil area dB0=(1-dRPTol)× _RI -dA0.

In step 3, referring to Fig. 4B, the iris inner and outer circumferences of the collected iris image are respectively divided into n equal parts, firstly, the coordinates (x _pi , y _pi ) of a point on the edge of the pupil can be calculated by the following formula And the coordinates (x _Ij , y _Ij ) corresponding to the point on the edge of the iris:

${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; pupil</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; cos</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span><span\; class="notranslate">\; ;</span>$

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; pupil</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; sin</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span><span\; class="notranslate">\; ;</span>$

Among them, (x _pI , y _pI ) is the coordinate point of the center of the pupil, and R _pupil is the radius of the pupil.

${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; I</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; cos</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span><span\; class="notranslate">\; ;</span>$

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; pI</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; I</span>}}<span\; class="notranslate">\; *</span>\mathrm{<span\; class="notranslate">\; sin</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; *</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&PartialD;</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; \&pi;</span>}}{\mathrm{<span\; class="notranslate">\; 256</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; \&Element;</span><span\; class="notranslate">\; [</span>\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ]</span>$

Among them, (x _pI , y _pI ) is the coordinate point of the center of the pupil, and R _I is the radius of the iris.

Calculate the distance dI between the pupil edge point and the iris edge point according to (x _pi , y _pi ) and (x _Ij , y _Ij ),

$\mathrm{<span\; class="notranslate">\; iGO</span>}<span\; class="notranslate">\; =</span>\sqrt[\mathrm{<span\; class="notranslate">\; 2</span>}]{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; Ij</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

In step 4, it can be deduced that the width dA1 of the near pupil area and the width dB1 of the far pupil area in the non-standard state are respectively:

$D1=\frac{\mathrm{dB}0(\mathrm{\&Delta;}-1)+d1}{1+\mathrm{\&Delta;}*\frac{\mathrm{dB}0}{D0}},$ dB1=dI-dA1,

in $\mathrm{\&Delta;}=\frac{k_1}{k_2}.$

In a preferred embodiment of the present invention, dRPTol is 0.37, and dRNToall is 0.375, and the normalization effect in this ratio state is the best, and m=64, n=512. In this preferred embodiment, in step 1, the number of lines m ₁ =24 to be sampled for the near-pupil area, and m ₂ =40 lines to be sampled for the far-pupil area. In step 3, the collected iris image is equally divided into n=512 parts corresponding to the inner and outer circumferences of the iris respectively. In step 5, m ₁ =24 lines and m ₂ =40 lines of linear sampling are respectively performed on the near pupil area and the far pupil area in the non-standard state of the iris. In step 6, referring to FIG. 4C , the sampling points are normalized into a rectangular image with a resolution of 512×64 through bilinear interpolation.

Through the iris texture normalization method based on the double spring model of the present invention, the linear method can still be used for sampling, but it is more accurate and reliable than the existing linear normalization method, and more convenient and practical than the nonlinear normalization method, The error caused by pupil scaling can be well reduced, which provides convenience for subsequent iris feature extraction, and improves the overall recognition rate of iris recognition.

The above is only a preferred embodiment of the present invention, it should be pointed out that for those skilled in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications are also It should be regarded as the protection scope of the present invention.

Claims (10)

1. the iris texture method for normalizing based on the dual spring model is characterized in that, comprises the steps:

Step 1 is set the ratio dRNToall of nearly pupil sector width under ratio dRPTol and the iris standard state of pupil radius and iris radius under the iris standard state and (nearly pupil district+far pupil district) width; Set the line number m that nearly pupil district and pupil district far away need sample ₁And m ₂, m wherein ₁, m ₂For greater than 0 integer, and m ₁+ m ₂=m; Nearly the pupil district is modeled as the spring series connection with unit elasticity coefficient k 1 and k2, wherein k respectively with pupil district far away ₁＜k ₂

Step 2 is obtained the iris radius R of the iris image of being gathered _I, according to said dRPTol, dRNToall and iris radius R _I, calculate the pupil radius R under the standard state _TO, the width dA0 in nearly pupil district and the width dB0 in pupil district far away;

Step 3, with the iris internal and external circumference of the iris image of being gathered corresponding respectively be divided into n part, calculate the coordinate (x of certain point on the pupil edge _Pi, y _Pi) and the iris edge on coordinate (x to putting _Ij, y _Ij), according to (x _Pi, y _Pi) and (x _Ij, y _Ij) calculate between said pupil edge point and the iris marginal point apart from dI, wherein, n is the integer greater than 0;

Step 4 when dI ≠ dA0+dB0, judges that the iris image of being gathered is in the iris off-rating, calculates the width dA1 in the nearly pupil district the iris off-rating under and the width dB1 in pupil district far away according to following formula:

$\frac{k1}{\mathrm{dA}0}(\mathrm{dA}0-\mathrm{dA}1)=\frac{k2}{\mathrm{dB}0}(\mathrm{dB}0-\mathrm{dB}1)$

dA1+dB1＝dI；

Step 5 according to dA1 that calculates and dB1, is carried out m respectively to nearly pupil district under the iris off-rating and pupil district far away ₁Row and m ₂Line linearity is sampled and is obtained sampled point;

Step 6 is normalized into the rectangular image that resolution is m * n with said sampled point through bilinear interpolation.

2. the method for claim 1 is characterized in that, in step 1, and the line number m that said nearly pupil district need sample ₁=m * dRPTol, the line number m that said pupil far away district need sample ₂=m-m ₁

3. the method for claim 1 is characterized in that, in step 2,

The width dA0=dRNToall in said nearly pupil district * (1-dRPTol) * R _IWidth dB0=(the 1-dRPTol) * R in said pupil far away district _I-dA0.

4. in the method for claim 1, it is characterized in that, in step 3,

$x_{\mathrm{pi}}=x_{\mathrm{pI}}+R_{\mathrm{pupil}}*\cos (i*\&PartialD;),\&PartialD;=\frac{\mathrm{\&pi;}}{256},i\&Element;[0,n-1];$

$y_{\mathrm{pi}}=y_{\mathrm{pI}}+R_{\mathrm{pupil}}*\sin (i*\&PartialD;),\&PartialD;=\frac{\mathrm{\&pi;}}{256},i\&Element;[0,n-1];$

Wherein, (x _PI, y _PI) be pupil center's coordinate points, R _PupilBe the pupil radius.

5. in the method as claimed in claim 4, it is characterized in that, in step 3,

$x_{\mathrm{Ij}}=x_{\mathrm{pI}}+R_I*\cos (i*\&PartialD;),\&PartialD;=\frac{\mathrm{\&pi;}}{256},i\&Element;[0,n-1];$

$y_{\mathrm{Ij}}=y_{\mathrm{pI}}+R_I*\sin (i*\&PartialD;),\&PartialD;=\frac{\mathrm{\&pi;}}{256},i\&Element;[0,n-1]$

Wherein, (x _PI, y _PI) be pupil center's coordinate points, R _IBe iris radius.

6. in the method as claimed in claim 5, it is characterized in that, in step 3, the distance between said pupil edge point and the iris marginal point:

$\mathrm{dI}=\sqrt[2]{{(x_{\mathrm{Ij}}-x_{\mathrm{pi}})}^2+{(y_{\mathrm{Ij}}-y_{\mathrm{pi}})}^2}.$

7. in the method for claim 1, it is characterized in that in step 4, the width dA1 in the nearly pupil district under the said off-rating and the width dB1 in pupil district far away are respectively:

$\mathrm{DA}1=\frac{\mathrm{DB}0(\mathrm{\&Delta;}-1)+d1}{1+\mathrm{\&Delta;}*\frac{\mathrm{DB}0}{\mathrm{DA}0}},$ DB1=dI-dA1, wherein $\mathrm{\&Delta;}=\frac{k_1}{k_2}.$

8. like each described method in the claim 1 to 7, it is characterized in that said dRPTol is 0.37, said dRNToall is 0.375.

9. like each described method in the claim 1 to 7, it is characterized in that said m is 64.

10. like each described method in the claim 1 to 7, it is characterized in that said n is 512.

Images