KR101797533B1 - Apparatus and Method for determining iris representative color for standardization of artificial eye - Google Patents

Abstract

The present invention suggests an apparatus and a method for determining a representative color of an iris. The method for determining a representative color of an iris comprises the steps of: extracting an iris area from an eyeball image; quantizing a pixel value of each pixel in the iris area; converting the quantized pixel values into a color space component value according to color coordinates different from color coordinates representing the pixel value, and categorizing the converted color space component value according to a predetermined method; and determining an iris representative color by using one or more component values of the categorized color space component values.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an iris representative color determining apparatus and method for standardizing an iris,

More particularly, the present invention relates to an apparatus and method for recognizing iris information as a biometric marker.

The iris is a round thin film between the cornea and the lens of the eyeball. The iris is expanded and contracted to reduce or enlarge the pupil. In other words, the iris functions to control the amount of light entering the eye. Iris has a unique color depending on the race or individual, and Koreans have various colors ranging from dark brown to light brown.

Since the conventional method of manufacturing the bill is manual, there is a problem that the product is different according to the capability of the maker. Therefore, in order to make a bill using a high-end device such as a 3D printer, a standard regarding the color of the iris should be prepared.

An accurate discrimination technique of the iris color is also required to establish a standard for the iris color. Especially, the technique of discriminating the color of iris may be necessary in order to satisfy the demand for rapid personal identification in a modern society in which human identification is increasingly required.

Conventional methods of identifying individuals in the past have not been able to meet increasing demands for accurate and rapid identification of individuals in modern societies. Existing iris recognition techniques include processing techniques for noise removal of acquired information, It has a non-standardized limit in color judgment.

Korean Patent Publication No. 10-2015-0019393 (Publication date: 2015.02.25)

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and it is an object of the present invention to provide a filtering unit for extracting an iris region from an eye image, quantizing pixel values of each image, and filtering a highlighted portion of the quantized pixel value categorizing unit, An apparatus and method for determining an accurate iris representative color, and a program stored in a computer-readable recording medium for realizing the apparatus and method.

Another object of the present invention is to standardize iris colors using representative criteria. If the representative color of the iris is changed according to the angle of the iris, accurate iris color can not be standardized. The object of the present invention is to determine a reliable iris representative color and to standardize the iris color as a representative judgment criterion.

According to an aspect of the present invention, there is provided an iris recognition method comprising: extracting an iris region from an eye image; Quantizing a pixel value of each pixel of the iris region; Converting the quantized pixel values into color space component values according to a colorimetric system different from the colorimetric system that indicates the pixel value, and categorizing the converted color space component values according to a predetermined method; Determining an iris representative color using one or more component values of the categorized color space component values; The iris representative color determining method according to the present invention includes:

Advantageously, the categorizing comprises: detecting pixel values of a predetermined higher frequency among the quantized pixel values; And categorizes using the detected pixel values.

Advantageously, the categorizing step comprises transforming the detected pixel values into a color space component value of a first color system that represents a color with a brightness and a color distance between predetermined colors; The color space component values of the first color system are converted into color space component values of a second color system represented by at least one component value selected from the group consisting of brightness, color saturation distance at the center of the color space, and hardness of the color space step; And categorizing the color space component values of the second color system using the converted color space component values.

Preferably, the categorization includes filtering the color space component value of the second color system when the brightness value of the converted color space component values of the second color system is equal to or greater than a predetermined threshold value; And the iris representative color is determined using the color space component values of the filtered second color system.

Preferably, the first color system is a CIELAB color system, and the second color system is a CIELCH color system.

Preferably, in the categorization, the other colorimetric system is a CIELCH colorimetric system, and categorizing the converted color space component values according to a predetermined method comprises: converting the color space component values converted according to the CIELCH color system into the color space component values of the CIELCH color system And categorizes the converted color space component values based on the hue angle.

Preferably, categorizing the converted color space component values based on the hue angle of the CIELCH color system comprises: distinguishing the hue angle into a plurality of predetermined intervals, Values are categorized.

Preferably, the step of determining the iris representative color further includes calculating an average value of the categorized color space component values, and the representative color is determined using the average value of the calculated color space component values.

Preferably, the other colorimetric system is a CIELCH colorimetric system, and the average value of the color space component values is calculated by calculating an average value of color angles among color space component values of the CIELCH color system, Next, an average value of hue angles belonging to the category to which the maximum value of the saturation among the color space component values of the CIELCH color system belongs is determined as the representative color.

Preferably, the iris representative color determination method includes a step of determining a pattern pattern of the iris region extracted from the eye image, and the iris representative color is determined with reference to the determined pattern pattern.

Preferably, the pattern pattern is one type selected from the group consisting of a crown type, a flower type, a sunshine type, and a composite type, and the composite type is a combination of the crown type, the flower type and the sunshine type .

The present invention also proposes a computer program stored on a computer-readable medium for executing the iris representative color determination method in a computer.

According to another aspect of the present invention, there is provided an image processing apparatus including an iris region extracting unit for extracting an iris region; A pixel value quantization unit for quantizing the pixel value of each pixel of the iris region; A pixel value categorization unit for converting the quantized pixel values into a color space component value according to a colorimetric system different from a colorimetric system for representing the pixel value and categorizing the converted color space component value according to a predetermined method; An iris representative color determining unit for determining an iris representative color using at least one of the categorized color space components; And an iris representative color determining unit for determining iris representative color.

Preferably, the pixel value categorizing unit includes a pixel value detector for detecting pixel values of a predetermined high frequency among the quantized pixel values; And converts the color space component of the first color system into the color space component using the detected pixel value.

Preferably, the pixel value categorization unit may include a first conversion unit that converts the detected pixel values into a color space component value of a first color system that expresses a color by brightness and a color distance between predetermined colors; And

And converting the color space component values of the first color system into color space component values of a second color system represented by one or more component values selected from the group consisting of brightness, color saturation distance at the center of the color space, 2 conversion unit; Further comprising:

And the pixel value categorization unit categorizes the converted color space component values using the color space component values of the converted second color system.

Preferably, the pixel value categorization unit further includes a pixel value filtering unit for filtering the color space component values of the second color system when the brightness value of the converted color space component values of the second color system is equal to or greater than a preset threshold value And the pixel value categorization unit categorizes the color space component values of the filtered second color system using the filtered color space component values.

Preferably, the iris representative color determining unit further includes calculating an average value of the categorized color space component values, and the representative color is determined using the average value of the calculated color space component values.

Preferably, the other colorimetric system is a CIELCH colorimetric system, and the average value of the color space component values is calculated by calculating an average value of color angles among color space component values of the CIELCH color system, Next, an average value of hue angles belonging to the category to which the maximum value of the saturation among the color space component values of the CIELCH color system belongs is determined as the representative color.

The present invention can achieve the following effects through the configurations for achieving the above object.

First, the correct iris representative color can be determined.

Second, it is possible to standardize iris color by determining reliable iris representative color.

1 is a flowchart of an iris representative color determination method according to an embodiment.
2 is an enlarged flow chart of categorizing pixel values according to one embodiment.
3 is an enlarged flow chart of a step of determining iris representative color according to an embodiment.
4 is a block diagram of an iris representative color determining apparatus according to an embodiment.
5 is an enlarged block diagram of a pixel value categorization unit.
6 is an enlarged block diagram of the iris representative color determining unit.
Fig. 7 is a reference diagram for an ocular structure.
8 is a conceptual diagram for explaining the color space of the CIELAB color system.
9 is a conceptual diagram for explaining the color space of the CIELCH color system.
10 is a conceptual diagram for explaining a highlight portion in which illumination is reflected on the iris.
11 is a conceptual diagram for explaining filtering of the highlight portion.
12 is a conceptual diagram for explaining the representativeness of a color angle of the CIELCH color system.
13 is a reference view for explaining the types of iris patterns.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In the following description with reference to the accompanying drawings, the same or corresponding components are denoted by the same reference numerals, and a duplicate description thereof will be omitted.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope. The singular expressions include plural expressions unless the context clearly dictates otherwise.

Each of the steps described below may be implemented by one or a plurality of software modules, or hardware that is responsible for each function, or a combination of software and hardware.

Specific meanings and examples of the terms will be described below in accordance with the order of each drawing.

FIG. 1 is a flowchart illustrating a method of extracting an iris region from an eye image according to an exemplary embodiment of the present invention to determine an iris representative color. A method of determining iris representative color will be described with reference to FIGS. 4 and 7. FIG.

The iris representative color determination method includes the following steps that are performed in a time-wise manner in the iris representative color determination apparatus.

In step S100, the iris region extracting unit 100 extracts the iris region from the eyeball image. In the eyeball image, the pixel values of the iris and the sclera differ greatly, and the iris region extracting unit 100 extracts the boundary region And the iris region can be extracted based on the detected boundary region.

In S150, the pixel-value quantization unit 150 quantizes the pixel value of each pixel of the iris region extracted in S100. Quantization means to convert continuous analog data into discrete values such as integers.

In S200, the pixel value categorizing unit 200 converts the quantized pixel values into color space component values of a colorimetric system different from the colorimetric system that indicates the pixel values, and categorizes them according to a predetermined method. Here, the color system means a color model and can mean a color system. The color space is an image of a color space in a three-dimensional space. The color system is RGB, and the other color system means a color system other than the RGB color system. For example, the other color system may be the CIELAB color system or the CIELCH color system.

The pixel value categorizing unit 150 categorizes the detected pixel values according to a predetermined method, wherein the predetermined method may be to categorize the converted color space component values based on the hue angle of the CIELCH color coordinate system. The hue angle means the color space hardness of the CIELCH color system, and has a value of 0 to 360 degrees. The color angle of the CIELCH color system satisfies the categorization criterion because the measurement deviation is small even when photographing the same iris with multiple angles.

In S250, the iris representative color determining unit 250 determines the iris representative color using one or more component values of the categorized color space component values.

For example, the iris representative color determining unit 250 can determine the representative color of the iris by using the hue angle of the CIELCH color system. More specifically, the iris representative color determining unit 250 determines the iris representative color using the average of the color space component values and the CIELCH color space spatial component value.

2 is an enlarged flow chart of the step S200 of categorizing the quantized pixel values.

In S202, the pixel value detection unit 202 detects a predetermined high frequency pixel value among the quantized pixel values. For example, the predetermined upper frequency may be 10. The frequency may be larger or smaller than the set frequency, and the larger the frequency is, the more accurate the iris representative color can be determined.

In S204, the first conversion unit 204 converts the detected pixel values into color space component values of the first color system. For example, the detected pixel values may be converted into color space component values of the CIELAB color system. The above process performed by the first conversion unit 204 is expressed by the following equations (1) and (2).

In S206, the second conversion unit 206 converts the color space component values of the first color system into color space component values of the second color system. For example, the color space component values of the CIELAB color system can be converted into the color space component values of the CIELCH color system. The above process performed by the second conversion unit 206 is expressed by Equation (3) below.

In S208, the filtering unit 208 filters the color space component values of the second color system when the brightness value among the color space component values of the second color system among the color space component values of the second color system is equal to or greater than a predetermined threshold value . For example, the predetermined threshold value may be 50, and the filtering unit 208 does not categorize the color space component values of the corresponding category.

3 is an enlarged flow chart of the step S250 of determining iris representative color.

In S252, the average value calculation unit 252 calculates an average value of the categorized color space component values. For example, the average value calculation unit 252 calculates the average value of the hue angle of the CIELCH color system, and determines the iris representative color using the average value.

In step S254, the average value determination unit 254 determines an average value of the hue angles belonging to the category to which the maximum value of the saturation among the color space component values of the CIELCH color system belongs to the iris representative color . The saturation among the color space component values of the CIELCH color system may mean the color saturation at the center of the color space.

In S255, the iris pattern determining unit 255 refers to the iris pattern to determine the iris pattern. The iris representative color determining apparatus 300 refers to the pattern of the iris of the upper iris to determine the iris representative color.

For example, the pattern pattern of the iris is one type selected from the group consisting of a crown type, a flower type, a sunshine type and a complex type, and the complex type is a combination of the crown type, the flower type and the sunshine type .

4 is a block diagram of an iris representative color determining apparatus according to an embodiment of the present invention.

The iris representative color determining apparatus 300 includes an iris region extracting unit 100, a pixel value quantizing unit 150, a pixel value categorizing unit 200, and an iris representative color determining unit 250.

The iris region extracting unit (100) extracts an iris region from an eye image. The extraction method is as described above.

The pixel value quantization unit 150 quantizes pixel values of the extracted iris region. The quantization has the same meaning as described above.

The pixel value categorizing unit 200 categorizes the quantized pixel values according to a predetermined method. The meaning of the predetermined method is the same as described above. More specifically, the pixel value categorizing unit 200 distinguishes the color angle of the CIELCH color system from a plurality of predetermined intervals, and categorizes the converted color space component values according to the intervals.

The iris representative color determining unit 250 determines the iris representative color using one or more component values of the categorized color space component values. The method of using the categorized color space component values is as described above.

FIG. 5 is an enlarged block diagram of the pixel value categorization unit 200. FIG. The configuration of the pixel value categorizing unit 200 will be described with reference to FIGS. 9 and 10. FIG.

The pixel value categorizing unit 200 includes a pixel value detecting unit 202, a first converting unit 204, a second converting unit 206, and a filtering unit 208.

The pixel value detection unit 202 detects a predetermined high frequency pixel value. The predetermined upper frequency may be preferably 10 according to an embodiment. Since the iris color of Korean has a hue between black and brown, the detected pixel values may have directionality in the color space of the colorimetric system.

The first conversion unit 204 converts the detected pixel value into the color space component value of the first color system. The functions performed by the first conversion unit 204 are expressed by the following equations (1) and (2).

For example, the detected pixel values can be converted into brightness 506, saturation 508, and hue angle 510, which are color space components of the CIELAB colorimetric system.

The second conversion unit (206) converts the color space component values of the first color system into color space component values of the second color system different from the first color system. The function performed by the second conversion unit 206 is expressed by Equation (3) below.

The filtering unit 208 filters the color space component values of the second color system when the brightness value among the color space component values of the converted second color system is greater than or equal to a preset threshold value. For example, a highlight indicates a portion illuminated by an iris, and when the brightness value of the CIELCH color system is 50 or more, it is determined as a highlight.

6 is an enlarged block diagram of the iris representative color determining unit 250. As shown in FIG.

The iris representative color determination unit 250 includes an average value calculation unit 252, an average value output unit 254, and an iris pattern determination unit 255.

The average value calculation unit 252 calculates an average value of categorized color space component values.

The average value is a value obtained by dividing the sum of color space component values of each category by the number of color space component values of each category.

The average value output unit 254 calculates the average value of the hue angles belonging to the category to which the maximum value of the saturation among the color space component values of the CIELCH color system belongs, Color.

The iris pattern determining unit 255 refers to the pattern of the iris to determine the pattern of the iris. The iris representative color is determined by referring to the determined iris pattern, and the kind of the pattern pattern is omitted.

Fig. 7 is a reference diagram for an ocular structure.

The physiological characteristics of the iris 302 will be briefly described. The iris 302 has many features as a color of invariance and can obtain a lot of information. It is a thin disc having a width of 4 to 5 mm, a thickness of 0.3 to 0.4 mm and a diameter of 10 to 12 mm, It has a unique color, and Koreans have various colors from dark brown to light brown. A pupil 304 is located in the center of the iris 302 and a portion where the pupil and the iris are in contact with each other is referred to as an inner boundary 308 and a portion where the iris and the sclera 306 are in contact with each other is referred to as an outer boundary 310.

8 is a conceptual diagram for explaining the color space of the CIELAB color system.

CIELAB color space is imaged in three-dimensional space is called color space (400) of CIELAB color system. The color system has the same meaning as the color model or the color system. The CIELAB colorimetric system represents a relative color distance between red and green expressed by brightness L * (402), a * (406), and a relative color distance between yellow and blue expressed by b * (404).

If the brightness L * (402) value is 100, it means white, and if the brightness L * (402) value is 0, it means black.

Here, R, G and B are pixel values, and the constants in front of R, G and B pixel values can be changed according to the definition method of R, G and B color spaces such as CIE RGB, ISO RGB, and Apple RGB . X, Y, and Z represent triplet values of the CIEXYZ color system. That is, it is possible to linearly convert the pixel value to the CIEXYZ colorimetric system. The triplet values of the CIEXYZ color system are all positive numbers.

Where X, Y, and Z are the triplet values of the CIE XYZ color system as described above. And Xw, Yw, and Zw are triplet values of the fully diffusive reflecting surface, and are values obtained by normalizing the CIE XYZ triplet value with respect to the standard white.

Here, L *, a * and b * are the color space components of the CIELAB color system, respectively, and refer to the relative color distance between red and green and the relative color distance between yellow and blue, respectively.

The fully diffusive reflective surface is an ideal surface with one ideal surface that does not transmit light but transmits light.

9 is a conceptual diagram for explaining the color space of the CIELCH color system.

The CIELCH color space is imaged in a three-dimensional space is called a color space 502 of the CIELCH color space. The CIELCH color system is a system that expresses colors with brightness L * (506), saturation C * (508), and hue angle h * (510). The saturation C * (508) means the color saturation distance at the center of the color space. The color angle means the same as the color, and means the hardness of the color space of the CIELCH color system.

Where h is the abbreviation for Hue-angle and means the hue angle. This represents the hardness of the color space of the CIELCH color system. C * ab stands for Chroma, which means saturation. Saturation can also be expressed as C *. CIELCH Color saturation distance in the color space center of the color system. Also, a * and b * are the color space components of the CIELAB color system as described above, respectively, and refer to the relative color distance between yellow and blue and the relative color distance between red and green, respectively.

10 is a conceptual diagram for explaining a highlight portion in which illumination is reflected on the iris.

2 and 7, a highlight portion will be described below.

The highlight 602 indicates a portion illuminated by the iris. In order to determine the accurate iris representative color, it is preferable to place the highlight portion 602 reflecting the illumination on the eye image in the pupil 304 of FIG. 7, but the highlight portion 602 is positioned in the pupil 304 of FIG. 7 The accurate iris representative color can be determined through the filtering of the highlight of FIG. 2 (S208).

11 is a conceptual diagram for explaining filtering of the highlight portion.

As described above, when the L * (612) among the color space component values of the CIELAB and CIELCH color system is 50 or more, it is determined as a highlight part and filtered. Therefore, all of the concept images 614 and 616 are highlighted and subjected to filtering.

12 is a conceptual diagram for explaining the representativeness of a color angle of the CIELCH color system.

The chart 700 is the color space component values of the CIELAB and CIELCH colorimetric system when the iris No. 1 is photographed at different angles.

The chart 720 shows the color space component values of the CIELAB and CIELCH colorimetric systems when the iris No. 2 is photographed at different angles.

The chart 740 shows color space component values of the CIELAB and CIELCH colorimetric system when the iris No. 3 is photographed at different angles.

In order to standardize the iris color through the iris representative color determination device 300, a criterion having a small measurement deviation is required. That is, if the color space component values measured according to the angle of the iris change, the iris color standardization is impossible.

For example, in the chart 700, 720, 740, the color angles h (12, 22, 32) of the CIELCH colorimetric system of each chart have a small variation in photographing from different angles. However, the other color space component values (14, 16, 18, 24, 26, 28, 34, 36, 38) of the chart are not suitable as a reference because the deviation of the measurement value is large at the time of photographing from different angles.

In the charts 700, 720 and 740, the color angle h (12) of the CIELCH colorimetric system of each chart has values of 50.01, 50.35, and 49.81 when the iris 1 is photographed from different angles, Lt; / RTI > Therefore, it is desirable to standardize the color of the iris using the color angle of the CIELCH colorimetric system in which the deviation of the measured value is small.

13 is a reference view for explaining the types of iris patterns.

The pattern pattern is one type selected from the group consisting of a crown type 802, a flower type 804, a sunshine type 806 and a complex type. The complex type is the crown type 802, the flower type 804 ) And the sunshine type (806).

The computer program for executing the iris representative color determination method according to another embodiment of the present invention may be a computer program stored in the medium for executing the iris representative color determination method according to the present invention described above.

It is to be understood that the present invention is not limited to these embodiments, and all elements constituting the embodiment of the present invention described above are described as being combined or operated in one operation. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them.

In addition, although all of the components may be implemented as one independent hardware, some or all of the components may be selectively combined to perform a part or all of the functions in one or a plurality of hardware. As shown in FIG. In addition, such a computer program may be stored in a computer readable medium such as a USB memory, a CD disk, a flash memory, etc., and read and executed by a computer to implement an embodiment of the present invention. As the recording medium of the computer program, a magnetic recording medium, an optical recording medium, or the like can be included.

It will be apparent to those skilled in the art that various modifications, substitutions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. will be. Therefore, the embodiments disclosed in the present invention and the accompanying drawings are intended to illustrate and not to limit the technical spirit of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings . The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

Claims (18)

Extracting an iris region from an eye image;
Quantizing a pixel value of each pixel of the iris region;
Converting the quantized pixel values into color space component values of a colorimetric system different from a colorimetric system that indicates the pixel value, and categorizing the converted color space component values according to a predetermined method; And
Determining an iris representative color using one or more component values of the categorized color space component values; / RTI > a method for determining an iris representative color. The method according to claim 1,
Wherein the categorizing further comprises detecting pixel values of a predetermined high frequency among the quantized pixel values,
And categorizing the iris representative color using the detected pixel values. 3. The method of claim 2,
Converting the detected pixel values into color space component values of a first color system representing a color with a brightness and a color distance between predetermined colors; And
The color space component values of the first color system are converted into color space component values of a second color system represented by at least one component value selected from the group consisting of brightness, color saturation distance at the center of the color space, and hardness of the color space step; Further comprising:
And categorizing the iris representative color using the converted color space component values of the second color system. The method of claim 3,
Wherein the categorization further comprises filtering the color space component values of the second color system when the brightness value among the color space component values of the converted second color system is equal to or greater than a preset threshold value,
Wherein the categorization is performed using categorized color space component values of the filtered second colorimetric system. 5. The method of claim 4,
Wherein the first color system is a CIELAB color system and the second color system is a CIELCH color system. 2. The method of claim 1, wherein in the categorizing step,
The other color system is a CIELCH color system,
Categorizing the transformed color space component values according to a predetermined method,
Wherein the color space component values converted according to the CIELCH color system are categorized into the color space component values based on the color angle of the CIELCH color system. The method according to claim 6,
The categorization of the converted color space component values based on the hue angle of the CIELCH color system may include dividing the hue angle into a plurality of predetermined intervals and categorizing the converted color space component values according to the intervals Wherein the iris representative color determining method comprises: The method according to claim 1,
Wherein the step of determining the iris representative color further comprises calculating an average of the categorized color space component values,
And determining a representative color using an average value of the calculated color space component values. 9. The method of claim 8, wherein the other color system is a CIELCH color system,
Calculating the average value of the color space component values is to calculate an average value of color angles among the color space component values of the CIELCH color system,
Determining an average value of hue angles belonging to a category to which a maximum value of saturation among the color space component values of the CIELCH color system belongs, as a representative color, following the step of calculating the average value. 10. The method of claim 9,
Wherein the iris representative color determination method includes a step of determining a pattern pattern of the iris region extracted from the eye image,
And determining an iris representative color by referring to the determined pattern pattern. 11. The method of claim 10,
Wherein the pattern pattern is one type selected from the group consisting of a crown type, a flower type, a sunshine type and a composite type, and the complex type is a combination of the crown type, the flower type and the sunshine type. Color determination method. An iris region extracting unit for extracting an iris region from an eye image;
A pixel value quantization unit for quantizing pixel values of pixels of the iris region;
A pixel value categorizing unit for converting the quantized pixel values into color space component values according to a colorimetric system different from a colorimetric system for representing the pixel value and categorizing the converted color space component values according to a predetermined method; And
An iris representative color determining unit for determining an iris representative color using one or more component values of the categorized color space components;
And an iris representative color determining unit. 13. The method of claim 12,
Wherein the pixel value categorizing unit further comprises a pixel value detector for detecting pixel values of a predetermined high frequency among the quantized pixel values,
Wherein the pixel value categorizing unit classifies the iris representative color using the detected pixel values. 14. The method of claim 13,
Wherein the pixel value categorizing unit comprises: a first converting unit for converting the detected pixel values into a color space component value of a first color system that expresses a color by brightness and a color distance between predetermined colors; And
And converting the color space component values of the first color system into color space component values of a second color system represented by one or more component values selected from the group consisting of brightness, color saturation distance at the center of the color space, 2 conversion unit; Further comprising:
Wherein the pixel value categorizing unit classifies the iris representative color using the converted color space component values of the second color system. 15. The method of claim 14,
Wherein the pixel value categorizing unit further includes a pixel value filtering unit for filtering the color space component values of the second color system when the brightness value among the color space component values of the converted second color system is equal to or greater than a preset threshold value,
Wherein the pixel value categorizing unit classifies the iris representative color using the filtered color space component values of the second color system. 13. The method of claim 12,
Wherein the iris representative color determining unit further includes an average value calculating unit for calculating an average value of the categorized color space component values,
And a representative color is determined using an average value of the calculated color space component values. 17. The method of claim 16,
The other color system is a CIELCH color system,
Calculating the average value of the color space component values is to calculate an average value of color angles among the color space component values of the CIELCH color system,
And an average value of hue angles belonging to a category to which a maximum value of the chroma saturation among the color space component values of the CIELCH color system belongs is taken as a representative color in consideration of an average value of the calculated hue angle. A program stored in a computer-readable recording medium for realizing the iris representative color determination method according to any one of claims 1 to 11 through being executed by a processor.

Images