KR101769741B1 - Method and apparatus for recognizing iris through pupil detection - Google Patents

Abstract

The present invention provides a method and a device to recognize an iris through pupil detection capable of improving accuracy of extracting an iris image. According to an embodiment of the present invention, the device to recognize the iris comprises: an image conversion unit converting an original image of a subject being photographed obtained by an image capturing part into a grayscale image; an image binarization unit performing binarization with respect to the image converted into the grayscale; a pixel grouping unit having a same pixel value in the binary image, classifying an interconnected region into a same group; a pupil detection unit determining a region where a physical value belongs within a reference range among the regions grouped by the pixel grouping unit as a pupil region; and an iris image extraction unit specifying an iris region on an original image based on a location of the pupil region.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an iris recognition method and an iris recognition method,

The present invention relates to an iris recognition method and an iris recognition method using pupil detection, and more particularly, to an iris recognition method and an iris recognition method using pupil detection, and more particularly, To a method and apparatus for enabling iris image acquisition.

However, since these methods are easily exposed to the risk of theft or loss, recently, a more stable and accurate personal identification method has been required.

Biometrics and authentication methods have been developed to overcome the disadvantages of traditional personal identification methods such as fingerprint, face, and iris.

In particular, the iris authentication method is known to be the most excellent in terms of uniqueness, invariance, and stability in personal identification, and is being applied to fields requiring high security.

The iris authentication is performed through a process of extracting an iris image of a subject and comparing the iris image with a previously registered iris image. In order to do this, an area corresponding to the eye of the photographee should be detected in a photographed image of the photographee. Generally, an algorithm such as OpenCV, which is an open source, is utilized.

OpenCV is an algorithm that detects feature regions in the image of a photographer and iris recognition and authentication. It can detect the eye region with high probability by using such an algorithm, There is a problem in that a part of iris image necessary for iris recognition is cut off or the size of the image is not constantly acquired when extracting the iris image after extracting only the eye image from the whole image.

Therefore, there is a need for a method capable of obtaining iris images of uniform size for iris recognition and authentication.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems of the conventional art, and it is an object of the present invention to always obtain a constant iris image at the time of iris recognition.

Another object of the present invention is to improve the accuracy of iris image extraction by acquiring an iris image using features that do not vary greatly from person to person.

According to an aspect of the present invention, there is provided an image processing apparatus comprising: an image conversion unit that converts an original image of a person to be imaged acquired by an image photographing unit into gray scale; An image binarization unit for binarizing the image converted to gray scale; A pixel grouping unit having the same pixel value in the binarized image and classifying the interconnected areas into the same group; A pupil detection unit which determines a pupil region in which a physical value among the regions grouped by the pixel grouping unit falls within a reference range; And an iris image extracting unit for specifying an iris region on the original image based on the position of the pupil region.

The image conversion unit may further perform an operation of reducing the size of the image converted to gray scale.

The operation of reducing the size of the image may be performed by dividing the image converted into the gray scale into a plurality of blocks and generating an image composed of an average of pixel values of each block.

The binarization can be performed by expressing a point having a pixel value equal to or larger than a reference value in the grayscale-converted image as "1 ", and a point having a pixel value smaller than the reference value as" 0 ".

The pixel grouping unit may perform grouping for each of the regions through an 8-way recursive flood fill algorithm.

The physical value may be at least one of a width, a vertical length, a ratio between a horizontal length and a vertical length of the grouped area, and a standard deviation between distances from the center of gravity to the outermost pixels of the area.

Wherein the pupil detection unit detects an area where a ratio between a horizontal length and a vertical length of the grouped areas is equal to or less than a first reference value and a standard deviation between distances from the center of gravity to the outermost pixels is equal to or less than a second reference value as a pupil area can do.

The iris image extracting unit measures a pixel value of pixels existing within a predetermined distance centered on a pupil area on the original image and calculates a point at which a pixel value change in a direction toward the pupil area indicates a threshold value or more, As shown in FIG.

The iris image extracting unit may extract an image between the boundary regions on the original image as an iris image.

Meanwhile, according to another embodiment of the present invention, there is provided a method of converting an original image of a photographee into a grayscale; Performing binarization on the grayscale-converted image; Classifying interconnected regions having the same pixel value in the binarized image into the same group; Determining a region of the grouped regions to be within a reference range as a pupil region; And specifying an iris region on the original image based on the position of the pupil region.

According to the present invention, an iris image is extracted based on an area having a predetermined feature point, that is, a pupil area, in an image taken by a photographer, so that a constant iris image can always be obtained.

In addition, according to the present invention, a pupil region that does not show a large difference for each person compared to other body regions is detected, and an iris image is extracted through the pupil region. Therefore, even if a user attempts iris recognition, It is possible to extract an accurate iris image through the above-described method.

1 is a diagram showing an example of an electronic apparatus to which an iris recognition apparatus according to an embodiment of the present invention is mounted.
2 is a diagram showing in detail the configuration of an iris recognition unit included in an electronic device according to an embodiment of the present invention.
3 to 9 show an example of an image utilized or generated in operation of the iris recognition unit according to an embodiment of the present invention.
10 is a flowchart illustrating an iris recognition process using pupil detection according to an embodiment of the present invention.
Fig. 11 shows an example of an image utilized or generated in each step shown in Fig.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "indirectly connected" . Also, when an element is referred to as "comprising ", it means that it can include other elements, not excluding other elements unless specifically stated otherwise.

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

1 is a diagram showing an example of an electronic apparatus to which an iris recognition apparatus according to an embodiment of the present invention is mounted.

Referring to FIG. 1, an electronic apparatus according to an exemplary embodiment includes an image capturing unit 100, an iris recognition unit 200, and a display unit 300.

The image capturing unit 100 is formed in a partial area of the electronic device and performs a function of acquiring an image of a person to be photographed. The image capturing unit 100 according to an exemplary embodiment may be implemented as a camera capable of capturing infrared rays for iris recognition. The iris recognition unit 200 according to an exemplary embodiment detects a pupil in an image of a person to be imaged acquired by the image capturing unit 100 and extracts an iris image based on a pupil detection result. The display unit 300 performs a function of previously displaying an image to be photographed by the image photographing unit 100, a function of displaying iris recognition and authentication processing, and the like.

Hereinafter, the process of detecting the pupil and acquiring the iris image based on the image of the person to be imaged acquired by the image capturing unit 100 will be described in detail.

2 is a diagram showing in detail the configuration of an iris recognition unit included in an electronic device according to an embodiment of the present invention.

2, an iris recognition unit 200 according to an embodiment includes an image conversion unit 210, an image binarization unit 220, a pixel grouping unit 230, a pupil detection unit 240, (250).

An image binarization unit 220, a pixel grouping unit 230, a pupil detection unit 240 and an iris image extraction unit 250 are embedded in an electronic device, Program modules or hardware to be installed. Such a program module or hardware may be included in an electronic device or other device capable of communicating with it in the form of an operating system, an application program module, and other program modules, and may be physically stored on various known memory devices. Such program modules or hardware, on the other hand, encompass but are not limited to routines, subroutines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types in accordance with the invention.

The iris recognition unit 200 according to an embodiment receives the image of the photographee photographed by the image photographing unit 100.

The image conversion unit 210 according to an embodiment converts the infrared photographing image of the to-be-photographed person obtained by the image photographing unit 100 mounted on the electronic apparatus into a grayscale image. The process of converting to a grayscale image can be performed by at least one of various well-known conversion schemes. As an example, an image converted to grayscale can be obtained by reconstructing an image based on a value obtained by dividing a red value (R), a green value (G), and a blue value (B) extracted from an infrared radiographic image by three, But is not limited thereto. 3 (a) and 3 (b) show an example of an image converted to gray scale.

The image converting unit 210 converts the original image captured by the image capturing unit 100 into a grayscale image, and then reduces the image size. According to one embodiment, an image that has been converted into a gray scale image is divided into a plurality of blocks having a predetermined size (for example, 4x4 pixels), and then pixel values The average is obtained. Then, an image composed of averages of pixel values for each block is obtained. That is, each pixel value of an image obtained here is an average of pixel values of each block. Thus, each block is converted into one pixel to obtain a reconstructed image. 4 (a) and 4 (b) show an example of an image composed of images obtained through the above process, that is, pixel average values for each block. If the size of each block is defined as 4.times.4 pixels, the size of the entire image is reduced to 1/4, and the time required for image processing at a later stage may be reduced as the size of the image decreases. In addition, since the above-described process is similar to the blurring process for an image, it is possible to obtain the effect of removing noise that may be introduced by an external environment or the like.

The image binarization unit 220 according to an embodiment performs an operation of binarizing the image processed by the image transform unit 210 into a dark region and a bright region. The binarization reference value can be specified by multiplying the pixel value average of the entire image by a positive rational number. Here, the positive number of the positive number is preferably 1 or 0.5. A point having a pixel value equal to or larger than the reference value may be represented by "1 ", i.e.," white ", and a point having a pixel value lower than the binarization reference value may be represented by "0" Accordingly, an image binarized into a dark region and a bright region can be obtained, and FIGS. 5A and 5B show an example of a binarized image according to this process.

The pixel grouping unit 230 according to an embodiment performs operations of grouping the dark regions present in the rendered image by binarization by the image binarization unit 200. [ Flood Fill algorithms may be used for grouping, but are not limited thereto.

The flood fill algorithm is an algorithm that determines the part of a multidimensional array that is connected to a specified location. The four-way recursive flood fill algorithm and the eight-way recursive flood fill algorithm are typically used as the flood fill algorithm. FIG. 6 is a diagram for explaining each flood fill algorithm.

First, referring to FIG. 6 (a), a four-direction recursive flood fill algorithm will be described. In the case of designating the area (1), according to the 4-way recursive flood fill algorithm, if an area having the same pixel value exists in any one of the up, down, left, and right directions, it is determined as an interconnected area. Therefore, even though the areas (1) and (2), and the areas (1) and (3) have the same pixel value, they are not connected to any one of the upper, lower, left, and right directions. .

Next, an 8-way recursive flood fill algorithm will be described with reference to FIG. 6 (b). In the case of designating the region (1) in the same way as the above example, according to the 8-way recursive flood fill algorithm, a pixel having the same pixel value in any one of the upper, lower, left, right, upper left, lower left, right lower, If a region exists, it is determined as an interconnected portion. Therefore, since the (1) and (2) regions, (1) and (3) regions have the same pixel value and are connected in the upper left or lower right directions, the regions (1), .

The image processed by the image binarization unit 220 may have a certain portion of noise or may be divided into a plurality of regions on the binarized image even if the portion is connected to one portion of the actual body.

In an embodiment, in order to classify the portions classified into the same region in the actual body into at most one group even on the binarized image, regions having the same pixel values are classified into upper, lower, left, right, upper left, lower left, lower right, If they are connected in at least one direction, they are classified into the same group. That is, the pixel grouping unit 230 according to an embodiment performs grouping on the binarized image using an 8-direction recursive flood fill algorithm. 7 shows the result of grouping based on the binarized image. Referring to FIG. 7, it can be seen that the region corresponding to the eyebrows of the actual body is divided into two groups (B1 and B2), and the portion corresponding to the pupil of the actual body is determined as one group (P).

The pupil detection unit 240 according to one embodiment measures the value of each of the grouped regions based on the image processed by the pixel grouping unit 230. [ The measured value may be at least one of a width, a length, a ratio between the width and the width, and a standard deviation between the distances from the center of gravity to the outermost pixels of the area.

If the numerical value of each grouped area is within the range of the preset pupil, that is, the reference value, the pupil is detected as the pupil.

For example, a region where the ratio between the horizontal length and the vertical length does not exceed 1.8 and the standard deviation between the distances from the center of gravity to the outermost pixels is 2.0 or less can be detected as a pupil.

The iris image extracting unit 250 according to an embodiment of the present invention includes a pupil position P1 sensed by the pupil detection unit 240 in an original image photographed by the image photographing unit 100, Is recognized as a final pupil region (P2), and only the iris image is extracted from the original image based on the recognized pupil region (P2).

Specifically, as shown in FIG. 9A, an X-axis is defined as an axis passing through the center of the pupil region P2 on the original image, and a pixel value of each pixel existing on the X- Y-axis value, a graph as shown in FIG. 9 (b) is obtained. Since the iris will be located in the vicinity of the pupil region, a region corresponding to N times, for example, five times, the pupil region diameter around the pupil region is specified as the pixel value calculation target region, It is sufficient to calculate the pixel value of the pixels existing in the pixel.

9 (b), the iris image extracting unit 250 extracts a point at which the pixel value falls to a threshold value, for example, 20 or more toward the pupil region from both ends of the pixel value calculation target region as an origin, (I) between the boundary points is determined as an iris image, and then the corresponding image is extracted.

The iris recognition unit 200 according to the embodiment may additionally perform iris authentication based on the iris image extracted by the iris image extraction unit 250, May be performed by a device.

According to the embodiment of the present invention, since the iris image is extracted based on the region having a predetermined feature point, that is, the pupil region, in the image taken by the photographer, a constant iris image can always be obtained. Further, since the characteristics of the pupil region are not significantly different from those of other body regions, accuracy of pupil region detection can be improved, and accuracy of iris image extraction can be improved.

FIG. 10 is a flowchart illustrating an iris recognition process using pupil detection according to an exemplary embodiment of the present invention, and FIG. 11 illustrates an example of an image used or acquired at each step. Hereinafter, a pupil detection process according to an embodiment of the present invention will be described with reference to FIGS. 10 and 11. FIG. The operation described below can be performed by a program module or hardware embedded in an electronic apparatus equipped with an image pickup section. For example, the operation performed by the iris recognition section 200 described with reference to Figs. 2 to 9 .

First, the image pickup unit mounted on the electronic apparatus and having the infrared ray photographing function is initialized and then set to a photographing standby state (S110).

Thereafter, the image capturing unit infrared-photographs the face of the person to be imaged to obtain an image as shown in FIG. 11 (a) (S120).

After the image acquisition, the acquired original image is converted into a grayscale image, and an image as shown in FIG. 11 (b) is obtained (S130). The obtained grayscale image is reconstructed into a reduced-size noise canceled image (S140). As described above, the size reduction process and the noise reduction process are performed by dividing the gray scale image into a plurality of blocks having a predetermined size, and then obtaining the pixel value average of the pixels constituting the corresponding block for each block, ≪ / RTI >

When the size-reduced image is generated, each pixel is binarized into "1" and "0" (S150). The binarization process can be performed by comparing the pixel value of each pixel with the reference value and expressing the pixel showing the pixel value equal to or larger than the reference value as "1" ("white") and the other pixel as "0" have. 11 (c) shows an image after the binarization process is performed.

After image binarization, as shown in FIG. 11 (d), at least one of the predetermined pixel values and the predetermined direction, for example, up, down, left, right, upper left, lower left, lower right, (S160). In step S160, it is determined whether or not the regions are connected to one another.

Thereafter, in step S160, it is determined whether there exists a region having a similarity to the physical characteristics of the pupil among the regions classified into the same group (S170).

If there is no area having similarity to the pupil's characteristic, the process returns to step S120 and an image acquisition may be attempted again.

On the contrary, if there is a region having a high similarity to the characteristic of the pupil, the pupil region P is detected on the original image as shown in FIG. 11 (e) based on the coordinates of the region (S180).

If the pupil region P is sensed on the original image, the pixel value change in the direction toward the pupil region P is greater than or equal to the threshold value, based on the pixel value of pixels existing within a certain distance about the corresponding region After the point is specified as the boundary region of the iris image, the image between the specified boundary regions is extracted as the iris image (S190).

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included within the scope of the present invention.

100: Image shooting unit
200: iris recognition unit
300:
210: image conversion unit
220: Image binarization unit
230: pixel grouping unit
240: pupil detection unit
250: iris image extracting unit

Claims (10)

An original image of a person to be photographed obtained by the image photographing unit is converted into gray scale, the converted image is divided into a plurality of blocks, an image composed of an average of pixel values of each block is generated, A conversion unit;
An image binarization unit for binarizing the image reduced by the image transform unit;
A pixel grouping unit having the same pixel value in the binarized image and classifying the interconnected areas into the same group;
A pupil detection unit which determines a pupil region in which a physical value among the regions grouped by the pixel grouping unit falls within a reference range; And
Measuring a pixel value of pixels existing within a predetermined distance around a pupil region on the original image and specifying a point at which a pixel value change in a direction toward the pupil region indicates a threshold value or more as a boundary region of the iris image, And an iris image extracting unit for specifying an area. delete delete The method according to claim 1,
Wherein the binarization is performed by expressing a point having a pixel value greater than or equal to a reference value as "1" in an image converted to the gray scale, and a point having a pixel value smaller than the reference value as "0 ". The method according to claim 1,
Wherein the pixel grouping unit performs grouping for each of the regions through an 8-way recursive flood fill algorithm. The method according to claim 1,
Wherein the physical value is at least one of a width, a vertical length, a ratio between a width and a width of the grouped area, and a standard deviation between distances from the center of gravity to the outermost pixels of the area, iris recognition Device. The method according to claim 6,
Wherein the pupil detection unit detects an area where a ratio between a horizontal length and a vertical length of the grouped areas is equal to or less than a first reference value and a standard deviation between distances from the center of gravity to the outermost pixels is equal to or less than a second reference value as a pupil area Iris recognition device. delete The method according to claim 1,
Wherein the iris image extracting unit extracts an image between the boundary areas on the original image as an iris image. Converting an original image of a person to be photographed into grayscale, dividing the converted image into a plurality of blocks, and reducing an image size by generating an image composed of pixel value averages for each block;
Performing binarization on the reduced-size image;
Classifying interconnected regions having the same pixel value in the binarized image into the same group;
Determining a region of the grouped regions to be within a reference range as a pupil region; And
Measuring a pixel value of pixels existing within a predetermined distance around a pupil region on the original image and specifying a point at which a pixel value change in a direction toward the pupil region indicates a threshold value or more as a boundary region of the iris image, And identifying a region of interest.

Images