KR20220114150A - Method and device for detecting animol biometric information - Google Patents

Abstract

The present invention relates to a method of identifying companion animal biometric information. An object of the present invention is to detect the companion animal biometric information. To this end, the present invention includes the steps of: receiving an image of the companion animal; setting a region of interest including the region of interest in the image, and identifying hair color distribution information of the companion animal in the region of interest; extracting a biometric information area based on the color distribution information; and identifying a type of the biometric information area.

Description

Companion animal biometric information detection method and device

The present invention relates to a method and apparatus for detecting biometric information of a companion animal, and more particularly, to a method and apparatus for detecting biometric information of a companion animal from an image.

As information and communication technology develops, technologies for identifying an object included in an image including a plurality of frames are being developed. In particular, by applying a recognition method possessed by a human, techniques for identifying an object in an image or identifying a predetermined object in advance have been developed.

In addition, based on the recent image recognition technology, the development of a technology using the biometric authentication method as an authentication method for banking, shopping, and unlocking using the obtained biometric information obtained by obtaining biometric information of a person from an image is actively progressing is becoming For example, as a representative biometric authentication method, iris recognition through an image of an eye region detected in an image, face recognition through an image of a face region detected in an image, and a hand fingerprint image detected in an image are analyzed, and the result of the analysis Techniques for performing fingerprint recognition are being developed based on

However, since the authentication technology using biometric information requires high accuracy due to the characteristics of authentication, there is still a need to develop a technology for accurately authenticating an object through biometric information. In addition, development of biometric authentication technology for animals as well as biometric authentication technology for humans is required.

An object of the present invention is to solve the above-described problem, and one object is to recognize biometric information for a companion animal.

In addition, the present invention applies a dynamic pre-processing method according to the color distribution information near the biometric information so that the input image is dark or the detection performance shows a difference depending on the color of the companion animal, so that it can respond to various environments and objects. One object is to improve the detection performance of information.

In order to achieve this object, the present invention provides a step A of receiving an image including a region of interest, at least one first region including biometric information (partial object) in the region of interest, and the first region in the region of interest. Step B of extracting the second restricted area to identify the color distribution information of the companion animal included in the twelfth area, step C of preprocessing the image based on the color distribution information, and the companion animal from the preprocessed image It is characterized in that it comprises a D step of detecting the biometric information of the animal and identifying the type.

According to the present invention as described above, the present invention is to solve the above-described problem, and it is possible to recognize biometric information for a companion animal.

In addition, the present invention applies a dynamic pre-processing method according to the color distribution information near the biometric information so that the input image is dark or the detection performance shows a difference depending on the color of the companion animal, so that it can respond to various environments and objects. It is possible to improve the detection performance of information.

1 is a view for explaining an example in which a biometric information detection device according to an embodiment of the present invention recognizes biometric information of a companion animal included in an image;
2 is a flowchart illustrating a method for a biometric information detecting apparatus to identify a companion animal's biometric information in an image according to an embodiment of the present invention;
3 is a view for explaining a second area according to an embodiment of the present invention;
4 is a view for explaining a color histogram according to an embodiment of the present invention;
5 is a flowchart illustrating a method for detecting biometric information of a companion animal according to an embodiment of the present invention;
6 is a flowchart for explaining a method of constructing a biometric information database according to an embodiment of the present invention;
7 is a diagram schematically illustrating a process of determining registered biometric information data in constructing a biometric information database according to an embodiment of the present invention;
8 is a diagram illustrating a configuration of a biometric information detection device for identifying biometric information of a companion animal according to an embodiment of the present invention.

The above-described objects, features and advantages will be described below in detail with reference to the accompanying drawings, and accordingly, those skilled in the art to which the present invention pertains will be able to easily implement the technical idea of the present invention. In describing the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

In the drawings, the same reference numerals are used to refer to the same or similar elements, and all combinations described in the specification and claims may be combined in any manner. And unless otherwise specified, it is to be understood that references to the singular may include one or more, and references to the singular may also include the plural.

The terminology used herein is for the purpose of describing specific exemplary embodiments only and is not intended to be limiting. As used herein, singular expressions may also be intended to include plural meanings unless the sentence clearly indicates otherwise. The term “and/or,” “and/or” includes any and all combinations of the items listed therewith. The terms "comprises", "comprising", "comprising", "comprising", "having", "having" and the like have an implicit meaning, so that these terms refer to their described features, integers, It specifies steps, operations, elements, and/or components and does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The steps, processes, and acts of the method described herein should not be construed as necessarily performing their performance in such a specific order as discussed or exemplified, unless specifically determined to be an order of performance thereof. . It should also be understood that additional or alternative steps may be used.

In addition, each component may be implemented as a hardware processor, respectively, the above components may be integrated into one hardware processor, or the above components may be combined with each other and implemented as a plurality of hardware processors.

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

1 is a diagram for explaining an example of recognizing the biometric information of a companion animal included in an image in an apparatus for detecting biometric information of a companion animal according to an embodiment of the present invention.

Referring to FIG. 1 , the biometric information detecting apparatus 10 may extract biometric information from an image of a companion animal. The apparatus for detecting biometric information may be exemplified by a mobile device such as a smart phone or a tablet, but the present invention is not limited thereto and includes a system including a camera module and a processor.

To this end, the biometric information detection apparatus 10 may acquire an image through a camera. In more detail, the biometric information detecting apparatus 10 may acquire an image of a companion animal based on a user's image input, and display the acquired image of the companion animal. Also, according to an embodiment, the biometric information detecting apparatus 10 may further provide a guide message such as 'Please take a picture of the dog's face' for the user's convenience while the user is shooting the image of the companion animal.

The bioinformation detecting apparatus 10 may set a region including a region of interest among body parts of the companion animal as the region of interest 101 in the image of the companion animal obtained through the camera.

The biometric information detecting apparatus 101 according to an embodiment of the present invention may display a guide for the ROI 101 on the screen in the process of acquiring an image of the companion animal. For example, the biometric information detecting apparatus 10 may set a region including at least one partial object related to a nose or eyes, which is biometric information of a companion animal, as the region of interest 101 in the image. The partial object according to an embodiment of the present invention may include at least one of eyebrows, pupils, whites, and hairs of animals located around the eye area related to the eyes of the animals, and the nostrils and nostrils related to the nose of the animal. It may include at least one of a pharynx positioned between the holes and a nose hair positioned around the nose.

The biometric information detecting apparatus 10 may pre-process the acquired image or extract the ROI 101 from the image and pre-process only the ROI.

For example, the bioinformation detecting apparatus 10 may remove noise in the ROI 101 and normalize a histogram of an image pixel. For example, the biometric information detecting apparatus 10 classifies the color and/or brightness values of pixels in the image into bins in which color and/or brightness information is classified into predetermined levels for each image pixel in the region of interest. By generating a histogram of a pixel and normalizing it, the contrast of the entire image can be improved.

The biometric information detecting apparatus 10 may extract the biometric information region 102 such as an eye or a nose from the pre-processed image. For example, the eye region may include eyebrows, pupils, and whites related to the eyes, and the nose region may include nostrils, pharynx, and nose hairs positioned around the nose.

To this end, the biometric information detecting apparatus 10 may detect an object identifiable in the ROI 101 . For example, the biometric information detecting apparatus 101 may detect an object by applying a Histogram of Oriented Gradients (HOG) algorithm to the image of the region of interest 101 .

As another example, the biometric information detecting apparatus 10 may detect a contour corresponding to an arbitrary object in the ROI 101 . According to an embodiment, the biometric information detecting apparatus 10 may detect a plurality of contours corresponding to an object included in the ROI 101 , and may determine outermost contours among the detected contours.

According to an embodiment, the biometric information detecting apparatus 10 may detect a max contour among the contours detected in the image by using a convex hull algorithm. Also, according to an embodiment, the biometric information detecting apparatus 10 detects a contour from at least one binarized guide region, and then applies an intermediate value filter to the detected contour, thereby smoothing the boundary of the contour. You may be able to carry out the process further. The biometric information detecting apparatus 10 may detect the flattened candidate outline as an outline of an object for each guide area.

The biometric information detecting apparatus 10 may determine whether the object extracted from the ROI 101 corresponds to the biometric information region 102 .

For example, the biometric information detecting apparatus 10 may probabilistically determine whether the extracted first object corresponds to the eye area using a machine learning model that has previously learned a large amount of images for the eye area. To this end, the biometric information detection device 10 includes information on the shape, shape, and color of the first object, location information occupied by the first object in the region of interest 101, information on the relationship between the first object and other objects, and the like. A vector for the first object may be created. Thereafter, the biometric information detecting apparatus 10 may embed the first object vector in a machine learning model that has previously learned a large amount of image of the eye area of the companion animal, and may calculate a probability that the first object corresponds to the eye area.

As another example, the biometric information detecting apparatus 10 may determine whether the extracted second object corresponds to the nose area using an algorithm for determining the nose area. For example, by checking whether the size difference between the two nostrils included in the second object is within the threshold value, the height difference between the two nostrils is within the threshold value, and whether the position of the pharynx is located between both nostrils, the second You can check whether the object corresponds to the nose area.

2 is a flowchart illustrating a method of detecting, by an apparatus for detecting biometric information, biometric information of a companion animal from an image according to an embodiment of the present invention.

Referring to FIG. 2 , the biometric information detecting apparatus 10 may acquire an image including at least one region of interest including at least one partial object that is biometric information of a companion animal ( S100 ). For example, the biometric information detecting apparatus 10 may acquire an image captured by at least one camera. After acquiring the first image through the camera, the biometric information detecting apparatus 10 may acquire the second image of the next frame. That is, the biometric information detecting apparatus 10 may acquire an image including a plurality of images including partial objects.

The bioinformation detecting apparatus 10 may set a region including the region of interest among the body parts of the companion animal in the acquired image as the region of interest. (S110) For example, the bio-information detecting apparatus 10 may set a region including at least one partial object related to the nose or eyes, which is the bio-information of the companion animal, in the image as the region of interest. The partial object according to an embodiment of the present invention may include at least one of eyebrows, pupils, whites, and hairs of animals located around the eye area related to the eyes of the animals, and the nostrils and nostrils related to the nose of the animal. It may include at least one of a pharynx positioned between the holes and a nose hair positioned around the nose.

Thereafter, the bioinformation detecting apparatus 10 may pre-process the ROI.

For example, the bioinformation detecting apparatus 10 may remove noise in the ROI and generate a color histogram of the ROI. For example, the biometric information detecting apparatus 10 classifies the color and/or brightness values of pixels in the image into bins in which color and/or brightness information is classified into predetermined levels for each image pixel in the region of interest. By creating a color histogram for each pixel and normalizing it, the contrast of the image as a whole can be improved. (S120)

According to an additional embodiment of the present invention, the biometric information detecting apparatus 10 may set a region of interest in the image of the companion animal and determine at least one first and second region corresponding to the region of interest. The first region is the region of interest in which biometric information objects such as eyes and nose are included, and the second region is a region that limits the first region in the region of interest and divides the region determined by the color of the companion animal included in the image. This is to understand the color distribution information. The second region may be a rectangular region, a triangular region including each corner, or more suitably, an region outside the outline of the biometric information object. The size of the second region will be based on a preset size value. According to an embodiment of the present invention, the second region may be 104 in FIG. 3 , and the first region may be 103 in FIG. 3 .

The bioinformation detecting apparatus 10 may perform texture analysis on the ROI. The bioinformation detecting apparatus 10 may perform texture analysis in order to check the color distribution of the color of the companion animal included in the region of interest and to determine the distribution pattern of the color of the color of the companion animal. (S130)

According to an additional embodiment of the present invention, the biometric information detecting apparatus can better recognize partial objects (eyes and nose) in the first area 103 by checking a pattern according to the color distribution of the color of the second area 104 . there is an effect For example, in the case of a companion animal having a spot pattern, a black spot pattern may exist in the second region 104 , and the spot pattern is easily confused with the eyes. In order to prevent this, according to the embodiment of the present invention, it is possible to identify the eye more accurately by determining the color distribution of the hair color in the second region 104 and determining that there is a pattern having a characteristic similar to that of the eye.

The apparatus 10 for detecting biometric information according to an embodiment of the present invention may further use a color histogram to perform texture analysis. A histogram is a graph representing a distribution of pixel values of an image image, and the biometric information detecting apparatus 10 may generate a color histogram for each RGB color included in the ROI. The biometric information detection device 10 will follow a conventional technique in generating a color histogram.

An example of the generated color histogram is shown in FIG. 4 . Looking at the color histogram shown in FIG. 4 , it can be seen that the same number of pixels appears at a low pixel value due to the color of the biometric information (eyes and nose) of the companion animal even when the color of the color is different from each other.

The bio-information detecting apparatus 10 may extract hair color distribution information of the companion animal based on the color histogram corresponding to the second region 104 . Color distribution information according to an embodiment of the present invention may include black, white, mixed color (brown color), spots, and the like. As an example of the color distribution information for the second region 104 of the companion animal having the spotted pattern, there may be 'there is brown hair in a circle just above the left eye, and has the color of black hair as a whole'.

The biometric information detection apparatus 10 may extract the color distribution information of the companion animal based on the color histogram. Referring to FIG. 4A , in the R, G, and B color histograms, the number of pixels is large only at low pixel values. When it appears, the color distribution information of the second region 104 may be determined to be a uniform black color.

Referring to (b) of FIG. 4 , when the color distribution information of the companion animal is a mixed color (brown color), the color histogram shows the second area 104 as the number of pixels appears in pixel values having different R, G, and B colors. ), it can be determined that the color distribution information is a uniform mixed color (brown).

Meanwhile, referring to FIG. 4C , when the color distribution information of the companion animal is white, the color histogram shows the color of the second region 104 as many pixels appear at the pixel values of R, G, and B colors all high. The distribution information may be determined to be a uniform white color.

The biometric information detecting apparatus 10 may pre-process the image ( S140 ) by applying different parameters according to the color distribution information identified in the second region 104 . The bio-information detecting apparatus 10 may make the outline of the bio-information included in the first region 103 well be revealed irrespective of the color of the companion animal by changing parameters according to the color distribution information.

Specifically, the pre-processing process is described, the bioinformation detection device 10 equalizes the image by converting the pixel values concentrated in a narrow range to be evenly distributed in the range of 0 to 255 through histogram equalization, and the RGB color and by correcting the contrast, the color of the image may be corrected.

Furthermore, in order to better extract the outline of the biometric information from the first region 103 , the biometric information detection device 10 analyzes the texture of the first region and adjusts the Blur_rate to remove edges, etc. that interfere with the outline extraction. have. In this case, a conventional technique such as Gaussian blur may be used.

The bio-information detecting apparatus 10 may detect the bio-information of the companion animal based on the ROI included in the pre-processed image ( S150 ). The biometric information detecting apparatus 10 according to an embodiment of the present invention may utilize the brightness value of a pixel of an image to detect a partial object corresponding to the biometric information of the companion animal. This is because, due to the image preprocessing by applying different parameters according to the color distribution information of the companion animal, the partial object becomes more prominent and its brightness is low when compared with the color distribution information, so that it is easy to distinguish between the fur and the partial object.

When step S150 is specifically described with reference to FIG. 5 , the biometric information detecting apparatus 10 may identify the edge of the partial object in the ROI of the pre-processed image ( S151 ).

The biometric information detecting apparatus 10 identifies a first pixel having a brightness value less than or equal to a preset threshold value at the edge of the partial object (S153), and extracts the outline of the partial object based on the number of first pixels (S155) can do. In this case, the apparatus for detecting biometric information may dynamically set the threshold value according to color distribution information including brightness, saturation, and hue of the boundary region of the partial object.

5 illustrates an embodiment of extracting an object from a region of interest, but the present invention is not limited thereto. There are many algorithms that can quickly and robustly extract an object identifiable from an image, and the object can be extracted by applying such a conventional algorithm.

Returning to the description of FIG. 2 again, the biometric information detecting apparatus 10 may identify the type of the detected partial object ( S160 ).

For example, the biometric information detecting apparatus 10 may probabilistically determine whether the extracted first object corresponds to the eye area using a machine learning model that has previously learned a large amount of images for the eye area. To this end, the bioinformation detecting apparatus 10 includes a first object including shape, shape, and color information of the first object, location information occupied by the first object in the region of interest, information on the relationship between the first object and other objects, and the like. You can create a vector for . Thereafter, the biometric information detecting apparatus 10 may embed the first object vector in a machine learning model that has previously learned a large amount of image of the eye area of the companion animal, and may calculate a probability that the first object corresponds to the eye area.

As another example, the biometric information detecting apparatus 10 may determine whether the extracted second object corresponds to the nose area using an algorithm for determining the nose area. For example, by checking whether the size difference between the two nostrils included in the second object is within the threshold value, the height difference between the two nostrils is within the threshold value, and whether the position of the pharynx is located between both nostrils, the second You can check whether the object corresponds to the nose area.

In operation 160 , the biometric information detecting apparatus 10 may use the biometric information database in identifying the type of the partial object. The biometric information database, in which first biometric data corresponding to each type of biometric information is input in advance, has an important role in recognizing the biometric information of a companion animal. Accordingly, the process of building a biometric information database is also very important. Hereinafter, a method of constructing a biometric information database will be described with reference to FIG. 5 .

6 is a flowchart illustrating a method of constructing a biometric information database according to an embodiment of the present invention.

In order to build the biometric information database, the biometric information detection apparatus 10 may first receive an image including at least one biometric information ( S200 ). An image according to an embodiment of the present invention may include more than a preset number of biometric information for each of the nose and eyes of the companion animal.

The bio-information detecting apparatus 10 may extract temporary bio-information data for a partial object corresponding to the bio-information from the input image ( S210 ). The process of extracting the temporary bioinformation data in step 210 may be the same as the process in which the biometric information detecting apparatus 10 according to an embodiment of the present invention detects biometric information from the image performed in steps 100 to 150 .

The biometric information detection apparatus 10 may calculate the authentication accuracy of the extracted at least one temporary biometric information data ( S220 ).

The biometric information detection device 10 authenticates the second biometric data when the temporary biometric data includes second biometric data corresponding to any first biometric region and having an authentication accuracy greater than or equal to a preset first threshold value. By giving different weights according to the accuracy, the average authentication accuracy may be calculated ( S230 ).

When the average authentication accuracy is equal to or greater than a preset second threshold value, the biometric information detecting apparatus 10 may set the second biometric information data of step 230 as the registered biometric information data of the first biometric region ( S240 ). The biometric information detection apparatus 10 will not store the second biometric information data as registered biometric information data of the first biometric region when the authentication accuracy of the second biometric information data is equal to or less than the second threshold value.

On the other hand, the biometric information detecting apparatus 10 according to an embodiment of the present invention may include, among the second biometric data, when the second biometric data having an authentication accuracy equal to or greater than the third threshold value is included in a preset number or more, the second biometric data When the authentication accuracy of the information data is equal to or greater than the fourth threshold value, the second biometric data may be stored as registered biometric data of the first biometric region.

More specifically, the biometric information detection device 10 according to the embodiment of the present invention accesses the biometric information database to identify the type of partial object included in the temporary biometric information data, and stores the temporary biometric information data and the biometric information database. Compare and calculate the authentication accuracy.

At this time, if the authentication accuracy for any one of the first biometric data included in the temporary biometric data is greater than or equal to a certain threshold, the image and/or the biometric data included in the image are stored in the biometric data database (S165) to update the biometric information database.

According to an embodiment of the present invention, when the authentication accuracy of an image included in the authentication request image is equal to or greater than a threshold value, the image may be reflected in the biometric information database. In this way, it is possible to maintain the authentication accuracy of the biometric information database despite changes in biometric information according to the growth of the companion animal. Furthermore, it is possible to increase the authentication accuracy of the biometric information database despite the characteristics of the companion animal, which is difficult to obtain an image, which is the standard for authentication.

The threshold value of authentication accuracy according to an embodiment of the present invention may be set differently depending on the type of biometric information, the first and second threshold values may be 70%, and the third threshold value is 85%. greater than the first threshold, and the fourth threshold will be 50% less than the first threshold. The values of the first to fourth threshold values are not limited to the above values and may be set differently according to an administrator.

The process of updating the biometric information database using the authentication request image generated by the biometric information detecting apparatus 10 may refer to FIG. 7 .

Referring to FIG. 7 , when the authentication accuracy for the six temporary biometric data data is 50%, 55%, 70%, 85%, 10%, and 60%, respectively, the fifth temporary biometric data data has a lower authentication accuracy. Because it is less than all of the first to fourth thresholds at 10%, it will not be reflected in the biometric information database, and the authentication accuracy of the fourth temporary biometric data among the 4th to 6th temporary biometric data whose type of biometric information is the eye is lower. Since it is 85% higher than the third threshold value, even if the sixth temporary biometric data is lower than the first threshold value, since it is higher than the third threshold value, the fourth and sixth temporary biometric data data will be reflected in the biometric data database.

Returning to the description of FIG. 6 , the biometric information database of the present invention generated through the steps 200 to 240 can have an optimal ERR, so that the biometric information of the companion animal can be more accurately recognized.

8 is a diagram illustrating a configuration of a biometric information detection device for detecting biometric information of a companion animal according to an embodiment of the present invention. Referring to FIG. 8 , the apparatus for detecting biometric information may include a processor 11 , a memory 12 , and a display unit 13 . However, not all of the illustrated components are essential components, and the biometric information detecting device 10 may be implemented by more components than the illustrated components, and the biometric information detecting device 10 may be implemented with fewer components. may be implemented. For example, the apparatus 10 for detecting biometric information according to an embodiment of the present invention may further include an output unit 15 and the like in addition to the processor 11 , the memory 12 , and the display unit 13 .

The output unit 15 may output an audio signal, a video signal, or a vibration signal, and the output unit 15 may include a display unit 14 , a sound output unit 16 , and the like. The display unit 14 includes a screen for displaying and outputting information processed by the processor 11 . In addition, the screen may provide the user with a guide message for allowing the user to photograph the companion animal image.

The processor 11 may control the overall operation of the biometric information detection apparatus 10 , and the processor 11 executes programs stored in the memory 12 to perform the function of the biometric information detection apparatus 10 described above. can

In more detail, the processor 11 may acquire an image including at least one ROI including a partial object from the user. The processor 11 may determine at least one first and second regions corresponding to the ROI in the acquired image. The first region may be a region in the region of interest including partial objects (biometric information), and the second region may be a region limited by the first region in the region of interest, and may be a rectangular region including each side of the region of interest. It may be a triangular-shaped area including each corner. The second area may be set to determine the color distribution information of the companion animal.

The processor 11 may perform texture analysis on the second region. The processor 110 may improve the recognition accuracy of the partial object in the first area by checking the color distribution of the color of the second area and checking the pattern based thereon.

The processor 11 according to an embodiment of the present invention may use a color histogram to perform texture analysis on the second region. A histogram is a graph representing a distribution of pixel values of an image image, and a color histogram for each RGB color included in the second region may be generated. The processor 11 may extract hair color distribution information of the companion animal based on the color histogram corresponding to the second region.

The processor 11 may pre-process the image by applying different parameters according to the color distribution information identified in the second region. The processor 11 may make the outline of the biometric information well revealed regardless of the color pattern of the companion animal by varying the parameter according to the color distribution information.

The processor 11 may detect the biometric information of the companion animal based on the region of interest included in the pre-processed image. The processor 11 according to an embodiment of the present invention may utilize a brightness value of a pixel of an image to detect biometric information of a companion animal. This is because the image is preprocessed by applying different parameters according to the color pattern information of the companion animal, so the biometric information of the companion animal is more prominent and the brightness is low when compared with the color pattern information of the companion animal, so it is easy to distinguish the fur from the biometric information because it does

The processor 11 may identify the type of biometric information of the companion animal based on the identified biometric information. Specifically, the processor 11 may identify the type of biometric information of the companion animal by comparing the first biometric data previously input to the biometric information database of the memory 12 with the identified biometric information of the companion animal.

Furthermore, as the processor 11 accesses the biometric information database of the memory 12 in identifying the identified type of biometric information, the authentication accuracy for any one of the biometric data stored in the biometric information database is the second. If it exceeds the threshold, the image can be stored in the biometric information database.

Embodiments of the present invention disclosed in the present specification and drawings are merely provided for specific examples in order to easily explain the technical contents of the present invention and help the understanding of the present invention, and are not intended to limit the scope of the present invention. It will be apparent to those of ordinary skill in the art to which the present invention pertains that other modifications based on the technical spirit of the present invention can be implemented in addition to the embodiments disclosed herein.

Claims (7)

A method for an electronic device to detect biometric information of a companion animal, the method comprising:
Step A of receiving an image of a companion animal;
a B step of setting a region of interest including the region of interest in the image, and identifying hair color distribution information of the companion animal in the region of interest;
Step C of extracting a biometric information area based on the color distribution information; and
and step D of identifying a type of the biometric information area.
According to claim 1, wherein the B step,
generating hair color distribution information of the companion animal by performing texture analysis of the region of interest;
and processing an outline of an object included in the region of interest by applying a parameter corresponding to the color distribution information.
3. The method of claim 2,
The parameter is a companion animal biometric information detection method, characterized in that it is set differently according to the color distribution information of the companion animal.
4. The method of claim 3,
setting a boundary region of a partial object in the region of interest,
identifying a first pixel having a value in a range dynamically set according to color distribution information in the boundary region; and
and detecting the biometric information based on the number of the first pixels.
A method for an electronic device to identify a type of biometric information of a companion animal, the method comprising:
storing the biometric information of the companion animal in a database;
detecting biometric information of the companion animal from an image including a region of interest;
Comprising the step of comparing the detected biometric information with the biometric information stored in the database, and when the comparison value is equal to or greater than a preset threshold, updating the database by reflecting the image and/or biometric information detected from the image Companion animal biometric information detection method characterized.
6. The method of claim 5,
The detecting step is
receiving an image including the region of interest;
At least one first region including biometric information (partial object) and a second region limiting the first region are extracted from the region of interest, and hair color distribution of the companion animal included in the second region is extracted from the region of interest. identifying information;
pre-processing the image based on the color distribution information; and
and detecting the biometric information of the companion animal from the pre-processed image and identifying the type based on the biometric data stored in a biometric information database.
The method of claim 6, wherein the step of identifying the type comprises:
The type of biometric information of the companion animal is identified through comparison of the biometric information with the biometric data stored in the biometric information database,
Companion animal biometric information detection method for varying a threshold value of authentication accuracy according to the type of biometric information of the companion animal.

Images