KR102615698B1 - Device for analyzing pupil and iris for iris recognition in cat, analysis method thereof, program - Google Patents

Abstract

The present disclosure includes a communication unit that communicates with a camera that captures images of the cat's pupil and iris; and a processor that controls operations related to analysis of the pupil and iris for cat iris recognition; It includes, and if the level of the image taken from the camera through the communication unit satisfies the preset standard level, the processor creates an edge map in the area with the darkest average brightness among the masked areas in the image that satisfies the standard level. ) may be used to determine the boundary area of the pupil, the iris area may be determined using the boundary area and the edge map, and iris data for the iris area may be output.

Description

Pupil and iris analysis device for cat iris recognition, analysis method and program {DEVICE FOR ANALYZING PUPIL AND IRIS FOR IRIS RECOGNITION IN CAT, ANALYSIS METHOD THEREOF, PROGRAM}

The present disclosure relates to a pupil and iris analysis device for cat iris recognition, an analysis method, and a program.

The iris is a flat donut-shaped membrane that is located between the ‘cornea’ and the ‘lens’ of the eye. The amount of light entering the eye can be determined by adjusting the size of the pupil in the center of the iris.

Iris recognition is a technology that identifies each animal by using the unique patterns inherent in the iris, which is a part of the body. You can. In addition, iris recognition has a higher recognition rate than other biometric recognition technologies such as inscriptions, fingerprints, and veins, and the iris is less likely to be damaged than other body parts such as inscriptions, fingerprints, etc., so it is considered the most popular method among biometric recognition technologies.

However, there are difficulties in obtaining an iris image of a cat. This is because, unlike humans, cats move a lot, and there is a high possibility that they will feel anxious and cause abnormal reactions during the process of photographing their iris. In particular, it is nearly impossible for a person to manually obtain an accurate image of a cat's iris using a camera. Therefore, in order to apply iris recognition technology to cats, above all, technology that allows easily obtaining iris images at an identifiable level is required.

Republic of Korea Patent Publication No. 10-2019-0088973 (announced on July 29, 2019)

The embodiment disclosed in the present disclosure overcomes the difficulties of iris recognition according to the cat's movements and body characteristics by easily obtaining a cat iris image at a level that can identify the unique characteristics of the individual, and provides a high-accuracy iris recognition technology. can be used to identify individual cats.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

A pupil and iris analysis device for iris recognition of a cat according to an aspect of the present disclosure for achieving the above-described technical problem includes: a communication unit that communicates with a camera that captures images of the cat's pupil and iris; and a processor that controls operations related to analysis of the pupil and iris for iris recognition of the cat. It includes, and the processor, when the level of the image captured from the camera through the communication unit satisfies a preset standard level, in the area with the darkest average brightness among the masked areas in the image that satisfies the standard level. It may be characterized by determining the boundary area of the pupil using an edge map, determining the iris area using the boundary area and the edge map, and outputting iris data for the iris area.

Additionally, the processor may further remove glint within the border area after cutting the border area to a certain size.

In addition, the processor rotates by 1 degree around the darkest pixel of the darkest area, and while rotating the entire 360 degrees, the level of the border edge for determining the border area is a preset strong border edge. When the level is satisfied, the boundary area may be determined by connecting the boundary points of the pupil that satisfies the level of the strong boundary edge.

Additionally, the processor may further calculate the center coordinates of the pupil based on the center of gravity coordinates of the boundary area.

In addition, when determining the iris area using the pupil center coordinates and the edge map, the processor determines whether the level of the iris edge for determining the iris area satisfies a preset strong iris edge level. It can be characterized by judgment.

In addition, the pupil and iris analysis method for iris recognition of a cat performed by an analysis device according to another aspect of the present disclosure includes the level of the image of the cat's pupil and iris captured from a camera through a communication unit of the analysis device. If a preset standard level is satisfied, receiving a corresponding image that satisfies the standard level; determining, through the processor of the analysis device, a boundary area of the pupil using an edge map in an area with the darkest average brightness among the masked areas in the corresponding image; determining, through the processor, an iris area using the border area and the edge map; and outputting iris data for the iris area through the processor. may include.

Additionally, the step of determining the border area may be characterized by cutting the border area to a certain size through the processor and then removing glint within the border area.

In addition, the step of determining the border area includes rotating the darkest pixel of the darkest area by 1 degree through the processor, while rotating the entire 360 degrees, using a border edge for determining the border area. ), the boundary area may be determined by connecting the boundary points of the pupil that satisfy the level of the strong boundary edge.

Additionally, the step of determining the boundary area may further include calculating the center coordinates of the pupil based on the center of gravity coordinates of the boundary area through the processor.

In addition, the step of determining the iris area includes, when determining the iris area using the center coordinates of the pupil and the edge map through the processor, the level of the iris edge for determining the iris area is It may be characterized by determining whether a preset level of strong iris edge is satisfied.

In addition, a computer program stored in a computer-readable recording medium may be further provided in combination with a hardware computer to perform a pupil and iris analysis method for iris recognition of a cat.

In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

According to the means for solving the above-described problem of the present disclosure, it is possible to easily obtain a cat iris image at a level that can identify the unique characteristics of the individual, thereby overcoming the difficulties of iris recognition according to the cat's movement and body characteristics and providing high accuracy. It provides the effect of using iris recognition technology to identify individual cats.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description below.

1 is a diagram illustrating an example of a pupil and iris analysis system for iris recognition of a cat according to the present disclosure.
Figure 2 shows the configuration of the analysis device of Figure 1.
Figure 3 is a flowchart showing a pupil and iris analysis method for cat iris recognition according to the present disclosure.
Figure 4 is a flowchart showing in detail the step of determining the boundary area of the pupil in Figure 3.
FIGS. 5 to 9 are diagrams illustrating a detailed process of determining the boundary area of a pupil through the boundary area determination step of the pupil in FIG. 4 as an example.
FIG. 10 is a flowchart showing the iris area determination step of FIG. 3 in detail.
FIGS. 11 to 13 are diagrams illustrating a detailed process of determining the iris area through the iris area determination step of FIG. 3 as an example.
FIG. 14 is a flowchart showing the iris data output step of FIG. 3 in detail.

Like reference numerals refer to like elements throughout this disclosure. The present disclosure does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present disclosure pertains is omitted. The term 'part, module, member, block' used in the specification may be implemented as software or hardware, and depending on the embodiment, a plurality of 'part, module, member, block' may be implemented as a single component, or It is also possible for one 'part, module, member, or block' to include multiple components.

Throughout the specification, when a part is said to be “connected” to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection through a wireless communication network. do.

Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

Throughout the specification, when a member is said to be located “on” another member, this includes not only cases where a member is in contact with another member, but also cases where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another component, and the components are not limited by the above-mentioned terms.

Singular expressions include plural expressions unless the context clearly makes an exception.

The identification code for each step is used for convenience of explanation. The identification code does not explain the order of each step, and each step may be performed differently from the specified order unless a specific order is clearly stated in the context. there is.

Hereinafter, the operating principle and embodiments of the present disclosure will be described with reference to the attached drawings.

In this specification, the analysis device according to the present disclosure includes all various devices that can perform computational processing and provide results to the user. For example, the analysis device according to the present disclosure may include all of a computer, a server device, and a portable terminal, or may take the form of any one.

Here, the computer may include, for example, a laptop equipped with a web browser, a desktop, a laptop, a tablet PC, a slate PC, etc.

A server device is a server that processes information by communicating with external devices and may include an application server, computing server, database server, file server, mail server, proxy server, and web server.

Portable terminals are, for example, wireless communication devices that ensure portability and mobility, such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), and PDA ( Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, smart phone All types of handheld wireless communication devices, such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted-device (HMD), etc. It can be included.

In the pupil and iris analysis system for cat iris recognition according to the present disclosure, when the level of the image captured from the camera satisfies a preset standard level, the average brightness is the highest among the masked areas in the image that satisfies the standard level. In a dark area, the boundary area of the pupil may be determined using an edge map, the iris area may be determined using the boundary area and the edge map, and iris data for the iris area may be output.

The pupil and iris analysis system for cat iris recognition according to the present disclosure enables easy acquisition of cat iris images at a level that can identify unique characteristics of the individual, thereby recognizing the iris according to the cat's movements and body characteristics. It can overcome the difficulties and provide highly accurate iris recognition technology that can be used to identify individual cats.

Below, we will look in detail at the pupil and iris analysis system for cat iris recognition according to the present disclosure.

1 is a diagram illustrating an example of a pupil and iris analysis system for iris recognition of a cat according to the present disclosure. Figure 2 shows the configuration of the analysis device of Figure 1.

Referring to FIGS. 1 and 2 , system 1000 may include a camera 100 and an analysis device 200.

The camera 100 may obtain a clear image of the cat's pupil and iris and transmit it to the analysis device 200. Here, if the level of the acquired image satisfies a preset standard level, the camera 100 may determine that the image satisfying the standard level is a clear image. At this time, the camera 100 may be an infrared camera.

The analysis device 200 can analyze the pupil and iris for iris recognition of a cat. Here, the analysis device 200 may output iris data for the iris area. At this time, the analysis device 200 may include a communication unit 210 and a control unit 220.

The communication unit 210 may communicate with the camera 100 that captures images of the cat's pupil and iris. The communication unit 210 may receive a clear image of the cat's pupil and iris obtained from the camera 100. The communication unit 210 may include at least one of a wired communication module and a wireless communication module.

Wired communication modules include various wired communication modules such as Local Area Network (LAN) modules, Wide Area Network (WAN) modules, or Value Added Network (VAN) modules, as well as USB (Universal Serial Bus) modules. , may include various cable communication modules such as High Definition Multimedia Interface (HDMI), Digital Visual Interface (DVI), recommended standard 232 (RS-232), power line communication, or plain old telephone service (POTS).

In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, wireless communication modules include GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), and UMTS (universal mobile telecommunications system). ), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, 6G, etc. may include a wireless communication module that supports various wireless communication methods.

The control unit 220 may include a memory 221 and a processor 222.

The memory 221 may store data about an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm. The processor 222 may perform the above-described operations using data stored in the memory 221. Here, the memory 221 and the processor 222 may each be implemented as separate chips. Additionally, the memory 221 and processor 222 may be implemented as a single chip.

The memory 221 can store data supporting various functions of the device, programs for operating components within the device, can store input/output data, and can store a plurality of application programs running on the device ( application program or application), data for operation of the device, and commands can be stored. At least some of these applications may be downloaded from an external server via wireless communication.

The memory 221 may be a flash memory type, a hard disk type, a solid state disk type, an SDD type (Silicon Disk Drive type), or a multimedia card micro type. micro type), card type memory (e.g. SD or XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), EEPROM (electrically erasable) It may include at least one type of storage medium among programmable read-only memory (PROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk.

The memory 221 may store images (P1, P2, P3, ...) of the cat's pupil and iris. The memory 221 may store data related to analysis of the pupil and iris for cat iris recognition.

The processor 222 may control operations related to analysis of the pupil and iris for cat iris recognition. The processor 222 may receive images (P1, P2, P3, ...) of the cat's pupil and iris from the camera 100 through the communication unit 210.

If the level of the image of the cat's pupil and iris captured by the camera 100 satisfies the standard level corresponding to a preset clear image, the processor 222 performs masking within the clear image of the cat's pupil and iris that satisfies the standard level. The boundary area of the pupil can be determined using an edge map in the area with the darkest average brightness among the processed areas. Here, the processor 222 may cut the border area to a certain size and then further remove glint within the border area. In addition, the processor 222 rotates by 1 degree around the darkest pixel of the darkest area, and while rotating 360 degrees, the level of the border edge for determining the border area is set to the level of the preset strong border edge. If is satisfied, the border area can be determined by connecting the border points of the pupil that satisfies the level of a strong border edge. Additionally, the processor 222 may further calculate the center coordinates of the pupil based on the center of gravity coordinates of the border area.

The processor 222 may determine the iris area using the boundary area and the edge map and output iris data for the iris area. Here, when the processor 222 determines the iris area using the pupil's center coordinates and the edge map, it determines whether the level of the iris edge for determining the iris area satisfies the preset strong iris edge level. You may.

Figure 3 is a flowchart showing a pupil and iris analysis method for cat iris recognition according to the present disclosure.

Referring to Figure 3, the pupil and iris analysis method for cat iris recognition includes a reception step (S320), a border area determination step (S340), an iris area determination step (S360), and an iris data output step (S380). can do.

In the receiving step, when the level of the image of the cat's pupil and iris captured from the camera 100 through the communication unit 210 satisfies the standard level corresponding to a preset clear image, the cat's pupil satisfying the standard level And a clear image of the iris can be received (S320).

At this time, the processor 222 may determine whether the cat's pupil and iris are a clear image using an image quality algorithm based on the Laplacian method, and may convert the clear image of the cat's pupil and iris into GrayScale. Additionally, the processor 222 may remove noise in an image converted to GrayScale based on the Gaussian Blur of Equation 1 below.

[Equation 1]

In the boundary area determination step, the processor 222 determines the boundary area of the pupil using an edge map in the area with the darkest average brightness among the masked areas in the image of the cat's pupil and iris. (S340).

Figure 4 is a flowchart showing in detail the step of determining the boundary area of the pupil in Figure 3. FIGS. 5 to 9 are diagrams illustrating a detailed process of determining the boundary area of a pupil through the boundary area determination step of the pupil in FIG. 4 as an example.

4 to 9, the boundary area determination step (S340) includes the first step (S341), the second step (S343), the third step (S345), the fourth step (S347), and the fifth step (S349). ) may include.

In the first step, the processor 222 selects a region (D1) with the darkest average brightness of the mask among the masked regions (D) in the image (I) of the cat's pupil and iris, as shown in FIG. 5. can be found (S341). For example, the processor 222 can use a K-sized mask to find the area D1 with the darkest average brightness of the mask. This is part of the pupil.

In the second step, the processor 222 uses Histogram Equalization for the image (I) of the pupil and iris of the cat to evenly distribute the brightness of the image (I) in the range of 0 to 255, as shown in FIG. It can be adjusted to be distributed (S343).

In the third step, the border area D2 is cut to a certain size as shown in FIG. 7 through the processor 222, and then the glint (G) in the border area D2 can be removed ( S345). For example, the processor 222 may remove glint (LED shadow reflected in the pupil) using a glint removal algorithm. This obscures the border of the pupil.

In the fourth step, the processor 222 rotates the darkest pixel (DP) of the darkest area by 1 degree, as shown in FIG. 8, to determine the boundary area while rotating the entire 360 degrees. If the level of the boundary edge satisfies the preset level of a strong boundary edge, the boundary points of the pupil (BP1, BP2, BP3, ..., BPn) that satisfy the level of the strong boundary edge are connected to establish the boundary of the pupil. can be created (S347). Here, the processor 222 can generate the following [Determinant 1] based on an edge map using the Sobel operator. At this time, the processor 222 may determine the boundary area based on [Determinant 1] below.

[Determinant 1]

In the fifth step, the center coordinates (G3) of the pupil may be further calculated through the processor 222 based on the center of gravity coordinates (G1, G2) of the border area (D2) as shown in FIG. 9 ( S349). For example, the center coordinate of the pupil (G3) may be a position coordinate at a distance that is half of the first center of gravity coordinate (G1) and the second center of gravity coordinate (G2).

In the iris area determination step, the processor 222 may determine the iris area using the border area D2 and the edge map (S360).

FIG. 10 is a flowchart showing the iris area determination step of FIG. 3 in detail. FIGS. 11 to 13 are diagrams illustrating a detailed process of determining the iris area through the iris area determination step of FIG. 3 as an example.

Referring to FIGS. 10 to 13 , the iris area determination step (S360) may include a sixth step (S361) and a seventh step (S363).

In the sixth step, when the processor 222 determines the iris area D3 using the pupil center coordinates G3 and the edge map M as shown in FIG. 11, the iris area D3 It can be determined whether the level of the iris edge for determining satisfies the preset level of a strong iris edge (S361). At this time, if the level of the iris edge satisfies the preset level of the strong iris edge, the processor 222 can find the strongest iris edge in the edge map (M) based on the coordinates of the center of the pupil (G3). . Here, the strongest iris edge may include the area of the eyelid (D4). At this time, the processor 222 can detect the eyelid area D4 because the cat does not have a sclera.

Additionally, as shown in FIG. 12 , the processor 222 may determine half (L /2) of the length (L) of both ends of the iris within the iris area (D3) as the radius (R). At this time, the processor 222 may determine the point corresponding to half (L /2) as the center coordinate (C2) of the iris.

Here, the processor 222 may generate a circle based on the point and radius (R) shifted from the pupil's center coordinates (C1) to the iris's center coordinates (C2). At this time, the processor 222 may find the boundary B based on the iris area D3 and the eyelid area D4 within the generated circular area CA. For example, the processor 222 determines that the distance value between the center coordinates of the iris (C2) and the center coordinates of the pupil (C1) is a preset reference distance value, and the iris area (D3) within the range of the circle area (CA). When the eyelid area (D4) is located, it can be judged as the border (B). For another example, the processor 222 may determine the brightness difference between the iris area D3 and the eyelid area D4 to be boundary B if it is greater than or equal to a preset reference difference value. In order to accurately recognize the iris of a cat that moves a lot, the processor 222 can more efficiently distinguish between the iris area (D3), the eyelid area (D4), and the border (B).

In the seventh step, the processor 222 can expand the iris area D3 into a rectangular shape T using linearPolar as shown in FIG. 13 (S363). At this time, D4 may be the eyelid area, and RD may be iris data for the iris area (D3).

In the iris data output step, iris data RD for the iris region D3 may be output through the processor 222 (S380).

FIG. 14 is a flowchart showing the iris data output step of FIG. 3 in detail.

Referring to FIG. 14, the iris data output step (S380) may include an eighth step (S381) and a ninth step (S383).

In the eighth step (S381), the processor 222 may filter the iris area D3 to extract features. In the ninth step (S383), the processor 222 converts the extracted features of the iris region D3 into binary numbers and outputs iris data RD.

Meanwhile, in the present disclosure, in the iris data output step (S380), in order to more accurately recognize the iris data of various cats, the result of the iris data of the recommended cat by learning based on an artificial intelligence model may be output.

For example, in order to more accurately recognize iris data according to the breed of the cat, the analysis device 200 includes metadata in the artificial intelligence model such as eyelid area data by cat breed, pupil area data by cat breed, and cat breed. By inputting the boundary area data of each pupil and the iris area data by cat breed, you can learn it based on an artificial intelligence model and output the recommended cat's iris data as the result. Here, the artificial intelligence model learns eyelid area data by cat breed, pupil area data by cat breed, pupil boundary area data by cat breed, and iris area data by cat breed using a CNN algorithm or RNN algorithm. It can be constructed and reinforced with data sets. At this time, the analysis device 200 may store the iris data of the recommended cat that has been learned and analyzed based on the artificial intelligence model.

For another example, since the aging rate and damage rate of the iris are different depending on the age of the cat, the analysis device 200 provides the cat's metadata to the artificial intelligence model in order to more accurately recognize iris data depending on the cat's age. Eyelid area data by age group, pupil area data by cat age group, pupil boundary area data by cat age group, and iris area data by cat age group are entered as input values, and the recommended cat data is learned based on an artificial intelligence model. Iris data can be output as a result. Here, the artificial intelligence model learns the cat's eyelid area data by age group, the cat's pupil area data by age group, the cat's pupil boundary area data by age group, and the cat's iris area data by age group using a CNN algorithm or RNN algorithm. It can be constructed and reinforced with data sets. At this time, the analysis device 200 may store the iris data of the recommended cat that has been learned and analyzed based on the artificial intelligence model.

As another example, the analysis device 200 uses an artificial intelligence model to more accurately recognize iris data depending on the breed and age of the cat, since the aging rate and damage rate of the iris are different depending on the breed and age of the cat. Among the metadata, enter eyelid area data by cat breed and age group, pupil area data by cat breed and age group, pupil border area data by cat breed and age group, and iris area data by cat breed and age group as input values. , Based on the artificial intelligence model, the iris data of the recommended cat can be output as a result. Here, the artificial intelligence model combines eyelid area data by cat breed and age group, pupil area data by cat breed and age group, pupil border area data by cat breed and age group, and iris area data by cat breed and age group using CNN. It can be constructed and reinforced as a learning data set using an algorithm or RNN algorithm. At this time, the analysis device 200 may store the iris data of the recommended cat that has been learned and analyzed based on the artificial intelligence model.

In this way, the present disclosure overcomes the difficulties of iris recognition according to the movement and body characteristics of the cat by enabling easy acquisition of cat iris images at a level that can identify the unique characteristics of the individual, and provides highly accurate iris recognition technology for cats. It can be provided for use in object identification.

At least one component may be added or deleted in response to the performance of the components shown in FIGS. 1 and 2. Additionally, it will be easily understood by those skilled in the art that the mutual positions of the components may be changed in response to the performance or structure of the system.

3, 4, 10, and 13 depict a plurality of steps being sequentially executed, but this is merely an illustrative explanation of the technical idea of this embodiment and is based on common knowledge in the technical field to which this embodiment belongs. Anyone who has a can change the order shown in FIGS. 3, 4, 10, and 13 without departing from the essential characteristics of this embodiment, or modify it in various ways by executing one or more of the plurality of steps in parallel. and may be applied with modification, so FIGS. 3, 4, 10, and 13 are not limited to the chronological order.

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. Instructions may be stored in the form of program code, and when executed by a processor, may create program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable recording media include all types of recording media storing instructions that can be decoded by a computer. For example, there may be read only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, etc.

As described above, the disclosed embodiments have been described with reference to the attached drawings. A person skilled in the art to which this disclosure pertains will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical idea or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

1000: System 100: Camera
200: analysis device 210: communication department
220: Control unit 221: Memory
222: processor

Claims (10)

a communication unit that communicates with a camera that takes images of the cat's pupil and iris; and
a processor that receives images of the cat's pupil and iris captured by the camera through the communication unit and controls operations related to analysis of the pupil and iris for iris recognition of the cat; Including,
The processor,
When determining the boundary area of the pupil,
If the level of the image of the pupil and iris satisfies a preset identifiable standard level, the image of the pupil and iris that satisfies the standard level is masked,
Finding the area with the darkest average brightness among the areas containing the masked images of the pupil and iris using an edge map,
After cutting the darkest area to a certain size, the glint in the darkest area is removed,
A strong boundary edge whose brightness is rapidly changed at a preset level for determining the boundary area of the pupil while rotating 1 degree around the darkest pixel of the darkest area and rotating a full 360 degrees. If the level of is satisfied, connect the points of the boundary of the pupil that satisfy the level of the strong boundary edge,
Based on the boundary points of the connected pupil, it is determined to be the boundary area of the pupil,
When analyzing the iris,
If the level of the iris edge for determining the area of the iris satisfies the level of a strong iris edge where the preset brightness changes rapidly, the coordinates of the center of the pupil are determined based on the coordinates of the center of gravity of the boundary area of the pupil. Calculate,
Creating a circle based on a point shifted from the center coordinates of the pupil to the center coordinates of the iris and a radius corresponding to half the length of both ends of the iris,
When the distance value between the center coordinates of the iris and the center coordinates of the pupil is a preset reference distance value, and the iris area and the eyelid area are located within the area range of the circle, the distance between the iris area and the eyelid area is Find the border area,
A pupil and iris analysis device for iris recognition in a cat, characterized in that the iris area, the eyelid area, and a boundary area between the iris area and the eyelid area are distinguished. delete delete delete delete In the pupil and iris analysis method for cat iris recognition performed by an analysis device,
Receiving images of the cat's pupil and iris captured by a camera through the communication unit of the analysis device;
determining a boundary area of the pupil through a processor of the analysis device; and
Analyzing the iris using the processor,
The step of determining the boundary area of the pupil is,
If the level of the image of the pupil and iris satisfies a preset identifiable standard level, the image of the pupil and iris that satisfies the standard level is masked,
Finding the area with the darkest average brightness among the areas containing the masked images of the pupil and iris using an edge map,
After cutting the darkest area to a certain size, the glint in the darkest area is removed,
A strong boundary edge whose brightness is rapidly changed at a preset level for determining the boundary area of the pupil while rotating 1 degree around the darkest pixel of the darkest area and rotating a full 360 degrees. If the level of is satisfied, connect the points of the boundary of the pupil that satisfy the level of the strong boundary edge,
Based on the boundary points of the connected pupil, it is determined to be the boundary area of the pupil,
The step of analyzing the iris is,
If the level of the iris edge for determining the area of the iris satisfies the level of a strong iris edge where the preset brightness changes rapidly, the coordinates of the center of the pupil are determined based on the coordinates of the center of gravity of the boundary area of the pupil. Calculate,
Creating a circle based on a point shifted from the center coordinates of the pupil to the center coordinates of the iris and a radius corresponding to half the length of both ends of the iris,
When the distance value between the center coordinates of the iris and the center coordinates of the pupil is a preset reference distance value, and the iris area and the eyelid area are located within the area range of the circle, the distance between the iris area and the eyelid area is Find the border area,
A method, characterized in that distinguishing an area of the iris, an area of the eyelid, and a border area between the area of the iris and the area of the eyelid. delete delete delete delete

Images