JP2022164589A - Determination system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a determination system capable of determining the breed, coat color, and sex of an animal from a picture of the animal in a simple way and a method thereof, or a determination system comprising means of identifying an individual animal using a picture of the animal in a simple way and a method thereof.

SOLUTION: A determination system is provided, comprising reception means configured to receive input of a facial image of a non-human animal, and determination means configured to determine the breed of the animal from the facial image of the animal entered to the reception means using a trained model, the trained model being designed to perform learning using facial images of non-human animals and corresponding breeds as teacher data and to function using a facial image of an animal as input to output a determined breed of the animal.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2023,JPO&INPIT

Description

TECHNICAL FIELD The present invention relates to a determination system and determination method, and more particularly, a system and method for identifying an individual animal, a system and method for determining an animal's breed, and a system and method for determining an animal's fur color from an animal's facial image. , to systems and methods for determining the sex of animals.

Pet animals such as dogs, cats, rabbits, and livestock such as cows and pigs are irreplaceable to humans. In recent years, pet animals, so-called pets, are increasingly treated in the same way as humans, and there is a growing need for individual identification of pets.

For example, pet-friendly stores and services such as trimming salons for pets, pet cafes where pets can accompany pets, dog runs, and lodging facilities where pets can stay together are becoming more familiar. When trying to operate a store or service that can be used by pets, it may be necessary to collect a fee for each individual pet, or to register an individual pet and provide services while referring to past service provision history. There is a need for identifying and identifying pet individuals.

In addition, when a pet goes missing, a pet search service may be requested. When searching for a missing pet, the pet is searched for based on the photo of the pet provided by the owner. Since it is a problem to determine the identity between the individual in the photograph and the individual suspected to be the animal to be searched, individual identification from the photograph of the pet is required.

Also, when providing pet insurance, there is a need to distinguish between insured and non-insured pets. For example, in order to provide a policyholder with an insurance card for pet insurance so that the policyholder can receive insurance payment by presenting the insurance card at the window of a veterinary hospital, The individual pet being treated must be the same as the individual pet actually undergoing medical care. Currently, when trying to provide such pet insurance, the pet insurance management company issues an insurance card with a photo of the pet's face to the policyholder, and the policyholder presents the insurance card at the reception of the animal hospital. However, veterinary hospitals have no choice but to visually compare the photograph of the pet on the insurance card with the pet that has undergone a medical examination to determine the identity of the individual.

Therefore, there is a demand for means for identifying individual pets by a simple method.

Patent Document 1 discloses a network camera, a presence detection sensor that detects whether or not a wild animal photographed by the camera still exists inside a capture facility, and a smartphone capable of viewing e-mails received from the network camera. Equipped with a user information terminal such as a tablet terminal, a personal computer, etc., a still image of an e-mail received only once or only once from the above network camera can be viewed by a remote observer who is far away from the installation site of the capture equipment. Disclosed is an individual identification wild animal capture system that allows remote control of network cameras and capture equipment while browsing.

Further, in Japanese Patent Laid-Open No. 2002-200003, a user terminal has a photographing means for producing a sound of a frequency that causes a photographed object to turn around when photographing, and an animal identification information registering means transmits photograph data of a photograph photographed by the photographing means to the user terminal. and registers the received photo data in the management DB as animal identification information, and the notification means sends the animal-related information specified by matching that compares the images of the photos and calculates the similarity to the user terminal An animal search system that notifies is disclosed.

However, Patent Literatures 1 and 2 do not disclose means for determining the breed, coat color, and sex from photographs of animals using trained models, and means for identifying individuals.

Japanese Patent Application Laid-Open No. 2019-4703 JP 2016-224640 A

Therefore, the present invention provides a determination system and determination method capable of determining the breed, coat color and sex of an animal from a photograph of an animal by a simple method, or an individual using a photograph of an animal by a simple method. It is an object of the present invention to provide a judgment system and a judgment method comprising means for identifying.

Insurance companies that operate health insurance for animals, so-called pet insurance, have accumulated a huge number of photographs of animals and information on individual animals, and the inventors of the present invention use these I have been trying to find out if the above problem can be solved. As a result, we found that by training artificial intelligence using animal photos and animal breeds, coat colors, and genders as training data, it is possible to generate trained models that determine animal breeds, coat colors, and genders from animal photos. The present invention has been completed. In addition, the inventors have found that a trained model can be generated for determining whether facial images of a plurality of animals are taken of the same individual by using a plurality of facial images of animals of the same individual as training data. was completed.

That is, the present invention is the following [1] to [12].
[1] A receiving means for receiving an input of a face image of an animal other than a human, and a determination means for determining the breed of the animal from the face image of the animal input to the receiving means using a learned model. A judgment system,
The trained model performs learning using face images of animals other than humans and breeds of the animals as teacher data, and is a trained model that uses the face image of the animal as an input and determines the breed of the animal as an output. A decision system characterized by:
[2] A receiving means for receiving an input of a face image of an animal other than a human, and a determination means for determining the fur color of the animal from the face image of the animal input to the receiving means using a learned model. A judgment system,
The trained model performs learning using face images of animals other than humans and the coat colors of the animals as teacher data, and is a trained model in which the input is the face image of the animal and the output is the determination of the coat color of the animal. A decision system characterized by:
[3] A receiving means for receiving an input of a facial image of an animal other than a human, and a determination means for determining the sex of the animal from the facial image of the animal input to the receiving means using a learned model. A judgment system,
The trained model performs learning using face images of animals other than humans and the sex of the animals as teacher data, and is a trained model in which the input is the face image of the animal and the output is the gender determination of the animal. A decision system characterized by:
[4] The determination system according to any one of [1] to [3], wherein the facial image used as the training data is an image including the animal's eyes and their surroundings and excluding the ears, nose and mouth.
[5] The determination system according to any one of [1] to [3], wherein the facial image used as the training data is an image including the eyes, nose and mouth of the animal and not including the ears and the outline of the face.
[6] receiving means for receiving input of face images of animals other than humans;
A database storing face images and individual identification information of animals other than humans, and using a trained model, the face image of the animal input to the receiving means is an image of the same animal as the individual animal stored in the database. An individual identification system comprising a determination means for determining whether or not
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and output is a trained model for determining whether each face image is a face image of a certain individual or another individual.
[7] The individual identification system of [6], wherein the face image used as the training data is an image containing the eyes, nose and mouth of the animal and not containing the ears and the outline of the face.
[8] Receiving means for receiving input of facial images of animals to be entered or exited;
a database that stores facial images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal entrance/exit management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. .
[9] Receiving means for receiving an input of a face image of an animal to be examined at a veterinary hospital;
a database that stores facial images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. .
[10] Receiving means for receiving an input of a face image of an animal to be trimmed or shampooed at a pet salon;
a database that stores facial images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. .
[11] Receiving means for receiving an input of a face image of an animal that is a candidate for an animal to be searched;
a database that stores facial images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. .
[12] A method for generating a trained model for determining whether or not a plurality of facial images of animals other than humans are images of the same individual, wherein images of animals other than humans are used as teacher data, 1. A method of generating a trained model, characterized by inputting an image including the animal's eyes and their surroundings but excluding the ears, nose and mouth into a computer including artificial intelligence, and allowing the artificial intelligence to learn.

According to the present invention, a judgment system and judgment method capable of judging the breed, coat color and sex of an animal from a photograph of the animal in a simple manner, and means for identifying an individual using a photograph of the animal in a simple manner. It is possible to provide a determination system and determination method comprising It is also possible to use the determination system of the present invention to provide an animal entry/exit management system, an insurance management system, and the like.

It is a figure showing an example of the suitable face image of an animal. It is a figure showing an example of the suitable face image of an animal. 1 is a schematic configuration diagram showing one embodiment of an entrance/exit management system of the present invention; FIG. It is a flowchart figure showing an example of the flow of entrance/exit management by the entrance/exit management system of this invention. It is an example of an animal face image used in the example. It is an example of an animal face image used in the example. It is an example of an animal face image used in the example. It is an example of an animal face image used in the example. It is a figure showing correspondence of labeling of an example. It is a figure showing the result of an Example. It is a figure showing correspondence of labeling of an example. It is a figure showing the result of an Example. It is a figure showing correspondence of labeling of an example. It is a figure showing the result of an Example. 15(a) to 15(e) show images of individual individuals, and FIG. 15(f) shows the correspondence between images and IDs (labels) of individual individuals. show. It is a figure showing the result of an Example.

<Product type determination system>
The determination system of the present invention uses a receiving means for receiving an input of a face image of an animal other than a human and a learned model to determine and output the breed of the animal from the face image of the animal input to the receiving means. and determination means.

[Receiving means]
The accepting means of the present invention is means for accepting an input of a face image of an animal whose breed is to be determined. Examples of animals include mammals such as dogs, cats, rabbits, and ferrets, birds, reptiles, and pets, with mammals being preferred, and dogs and cats being more preferred. The image reception method may be any method such as scanning, inputting and transmitting image data, and capturing an image by photographing on the spot. The format of the face image is not particularly limited, but the face image is preferably a photograph of the animal's face taken from the front, and more preferably a photograph showing the animal's face enlarged as shown in FIG. Such photographs include photographs such as those of a person's driver's license. Also preferred are images used on animal health insurance cards, as in FIG.

Images may be in black and white, grayscale, or color. Images that do not show the entire animal's face, images whose shape has been edited with image editing software, images that include multiple animals, images that have faces so small that their eyes and ears cannot be recognized, or images that are unclear. I don't like it. As for the image, it is preferable that the image is normalized and the resolution and the like are unified.

[Determination means]
The judging means of the present invention performs learning using face images of animals other than humans and breeds of the animals as teacher data, and is trained using face images of animals as input and judgment of the breed of the animal as output. Including model. A variety is a unit of a biological population below the species of an organism. For example, in terms of dogs, dog breeds are also called dog breeds, specifically toy poodles, Chihuahuas, miniature dachshunds, Shiba Inu, Pomeranians, Yorkshire terriers, miniature schnauzers, Shih tzu, French dogs. Bulldog, Papillon, Maltese, Labrador, Dalmatian, Chow Chow and the like. In terms of cats, breeds of cats are also called cat breeds, and include Scottish Fold, American Shorthair, Norwegian Forest Cat, Russian Blue, British Shorthair, Ragdoll, Maine Coon, and Persian. Rabbits include Netherland Dwarf, Holland Lop, Lop Ear, Mini Rex, Dwarf Lop, and American Fuzzy Lop.

Artificial intelligence (AI) is preferable as the trained model. Artificial Intelligence (AI) is a software or system that imitates the intellectual work of the human brain on a computer. A computer program, etc., that performs and learns from experience. Artificial intelligence may be general-purpose or specialized, and may be deep neural networks, convolutional neural networks, or the like, and open software can be used.

Artificial intelligence is trained using teacher data to generate a trained model. Learning may be either machine learning or deep learning, but deep learning is preferred. Deep learning is a development of machine learning, and is characterized by automatically finding feature quantities.

A learning method for generating a trained model is not particularly limited, and publicly available software can be used. For example, DIGITS (the Deep Learning GPU Training System) published by NVIDIA can be used. In addition, for example, learning may be performed by a known support vector machine method disclosed in "Introduction to Support Vector Machine" (Kyoritsu Shuppan) or the like.

Teacher data for learning are animal face images and animal breeds. The face image of the animal as teacher data may be the same as or different from the face image described in the reception method. Information about the breed of the animal can be obtained, for example, as information provided when applying for insurance from an animal hospital or the owner of the animal to be insured. Alternatively, an image may be viewed in advance, and a person may visually determine the breed of the individual animal associated with the image, and label it. Moreover, the face image of the animal used as training data is preferably an image that includes the animal's eyes and their surroundings but does not include the ears, nose and mouth. Both eyes may be reflected, or only one eye may be reflected. If the face image of the animal includes the animal's eyes and their surroundings but does not include the ears, nose, and mouth, the effects of trimming, staining of body hair, etc. on individual identification are reduced.
It is also preferable to use an image that includes the eyes, nose and mouth of the animal and does not include the ears and the outline of the face as the facial image of the animal used as training data.

[output]
When the determining means of the present invention receives a face image of an animal as input information, it determines the breed of the animal using the learned model.
The output format is not particularly limited, and for example, the prediction judgment can be output by displaying "toy poodle", "chihuahua", or "papillon" on the screen of the personal computer. Also, as incidental information, the certainty of product type determination may be output at the same time. For example, "toy poodle (reliability: 80%)".
The determination system of the present invention may additionally have output means for receiving determination results from the determination means and outputting the determination results.

<Hair Color Judgment System>
The determination system of the present invention uses a receiving means for receiving an input of a face image of an animal other than a human and a learned model to determine and output the fur color of the animal from the face image of the animal input to the receiving means. and determination means.

[Receiving means]
The acceptance means of the present invention is the same as the above-described variety determination system.

[Determination means]
The determination means of the present invention performs learning using the face images of animals other than humans and the coat colors of the animals at the time of photographing as teacher data, and the input is the face image of the animal, and the output is the coat color of the animal at the time of photographing. Includes a trained model that determines Coat colors include, but are not limited to, black, black & silver, brown, cream, white, chocolate, yellow, and the like. It is also possible to set the type of coat color for each species or breed of animal.

The training data for learning is the face image of the animal and the coat color of the animal at the time of photographing. The face image of the animal as teacher data may be the same as or different from the face image described in the reception method. Information about the fur color of the animal can be obtained, for example, as information provided when applying for insurance from an animal hospital or the owner of the animal to be insured. Alternatively, a coat color classification may be created in advance for each species or breed of animal, and a person may visually determine the coat color of the individual animal related to the image by looking at the image, and label it. . Other points of the learned model are the same as those of the breed determination system.

[Output means]
When the determining means of the present invention receives a facial image of an animal as input information, it determines the coat color of the animal when the facial image is taken, using the learned model.
The output format is not particularly limited, and for example, the prediction determination can be output by displaying "black", "brown", or "cream" on the screen of the personal computer. Moreover, as incidental information, the certainty of hair color determination may be output at the same time. For example, "Brown (reliability: 80%)".
The determination system of the present invention may additionally have output means for receiving determination results from the determination means and outputting the determination results.

<Gender determination system>
The determination system of the present invention uses reception means for receiving an input of a face image of an animal other than a human, and uses a trained model to determine and output the sex of the animal from the face image of the animal input to the reception means. and determination means.

[Receiving means]
The acceptance means of the present invention is the same as the above-described variety determination system.

[Determination means]
The judging means of the present invention performs learning using face images of animals other than humans and the sex of the animals as teacher data, and the face image of the animal is used as an input, and the sex of the animal is judged as an output. Including model.

Teacher data for learning are animal face images and the sex of the animals. The face image of the animal as teacher data may be the same as or different from the face image described in the reception method. Information about the sex of the animal can be obtained from, for example, an animal hospital or the owner of the animal to be insured as information provided when applying for insurance. Other points of the learned model are the same as those of the breed determination system.

<Individual identification system>
The individual identification system of the present invention includes a receiving means for receiving input of facial images of animals other than humans, a database storing facial images and individual identification information of animals other than humans, and a learned model, using the receiving means. determining means for determining whether or not the face image of the animal input to is the image of the same individual as the individual animal stored in the database.

[Receiving means]
The acceptance means of the present invention is the same as the above-described variety determination system.

[Database]
The database of the present invention associates and stores facial images of animals and individual identification information of individual animals related to the facial images. Examples of individual identification information include species, breed, sex, age, weight, and body length of the animal. Alternatively, an ID number may be assigned to each animal. Furthermore, health-related information such as the animal's hospital visit history, surgery history, and drug administration history, and information related to pet salon usage history such as trimming history, shampoo history, nail clipping history, and the like may be attached to the individual identification information. The database may be managed in the form of a database server, managed on a cloud server, or distributed.

[Determination means]
The judging means of the present invention includes a trained model.

Teacher data for learning are animal face images. The face image of the animal as teacher data may be the same as or different from the face image described in the reception method.
As a learning method, for example, a plurality of face images taken on the same day for each individual and face images taken of other individuals are prepared. A method of learning as an ID can be mentioned.
In addition, it is also possible to use so-called triplet training, in which three images are grouped into one set, and one of them is labeled as Positive if it is similar to one of the images (Query), and labeled as Negative if it is not. .
Animal facial images used as training data include animal eyes and their surroundings but do not include ears, nose and mouth, or images that include animal eyes, nose and mouth but do not include ear and facial contours. Images are preferred.

The determining means, for example, reads the animal face image stored in the database and compares it with the animal face image input from the receiving means. Then, it is determined whether or not the image stored in the database and the image input from the receiving means are images of the same individual. This determination can be performed repeatedly, and may be performed for all the images of the same species of animals stored in the database, or may be performed only for some of the images.

[output]
The format of the output is not particularly limited, and the judgment can be output by displaying, for example, "the same individual" or "not the same individual" on the screen of the personal computer. Further, when it is determined that the face image of the animal input from the receiving means is the same individual as the specific individual stored in the database, the individual identification information of the specific individual is also output. You may In addition, a plurality of images of animals stored in the database may be presented in descending order of probability of being the same individual as the animal input from the reception means.

Also, by using the individual identification system of the present invention, an image of one eye of an animal is input to the receiving means, and the individual identified by the one eye is identified, or the owner of the image of the other eye is determined. It can be applied to a system that

Further, the individual identification system of the present invention can be used to input an image of one eye of an animal to a receiving means and apply it to a system for determining which eye is left or right.

<Entrance control system>
The entrance/exit management system of the present invention comprises reception means for receiving an input of a facial image of an animal to enter or exit, a database for storing the facial image and individual identification information of the animal, and the animal received by the reception means. a determination means for determining whether or not the individual reflected in the facial image of the animal is the same as the individual stored in the database; and an output means for outputting the determination result of the determination means. In the management system, the determining means uses a trained model to determine whether or not the face image of the animal received by the receiving means is the same individual image as the individual animal stored in the database. The learned model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and receives an input from a certain individual animal. or the face image of another individual animal, and the output is a trained model that determines whether each face image is a face image of a certain individual or another individual It is characterized.

INDUSTRIAL APPLICABILITY The entrance/exit management system of the present invention can be used, for example, in pet hotels, dog runs, pet cafes, etc., where it is desired to grasp and manage the entrance and exit of animals to specific areas or rooms.

The reception means is not limited, and for example, images captured by imaging means such as surveillance cameras fixed indoors, network cameras, and cameras attached to smartphones can be received through the network.

The database, determination means, and output means are the same as above.

An example of an embodiment of the entrance/exit management system of the present invention will be described with reference to FIG. 3 in the case of a pet hotel.
First, the user of the pet hotel registers as a member on the website of the pet hotel through the terminal 13, and then registers the species, breed, name, date of birth, weight, sex, and vaccination status of the pet to be accommodated at the pet hotel. The face image of the pet is registered together with the individual identification information such as. The individual identification information of the registered pet is stored in the database 12 managed by the pet hotel.
Next, the user makes a reservation for the pet hotel on the website through the terminal 13, and visits the pet hotel with the pet on the reserved date and time.
An employee of the pet hotel photographs the pet by a photographing means 16 such as a camera installed in the pet hotel. Then, the photographed image is input to the receiving means 15 through the network.
The processing calculation unit 17 refers to the database 12, and uses the determination unit 11 to determine whether or not the face image of the pet stored in the database 12 and the received image are the same individual. The determination is repeated for each face image of the pet stored in the database 12, and when it is determined that they are the same individual, the individual identification information of the pet is output together with the face image of the pet by the output means 14 (personal computer). screen).
At this time, the pet hotel employee uses the output determination result and pet individual identification information to determine that the pet trying to use the pet hotel is the same individual as the pet registered as a member. and allow the pet to enter.

In FIG. 3, a terminal 13 is a terminal used by a user. Examples of the terminal 13 include a personal computer and a tablet terminal. The terminal 13 includes a processing unit such as a CPU, a storage unit such as a hard disk, ROM or RAM, a display unit such as a liquid crystal panel, an input unit such as a mouse, keyboard, touch panel, etc., and a communication unit such as a network adapter. .

At the time of application or membership registration, the user may take a photograph of the target animal's face using the camera of the smartphone on the spot, and input and transmit the photograph. For example, the user takes a photograph of the face of the animal to be insured according to the instructions displayed on the screen of the terminal 13 and sends it to the database 12 when an appropriate photograph is taken. At this time, the server is separately provided with a photographing assistance means consisting of an image determination program, and the photographing assistance means determines whether the animal's entire face is imaged or the animal's face is photographed from the front. It may be determined whether or not the photograph is suitable for identity determination, and the determination result may be transmitted to the user through an interface or terminal.

In this embodiment, the server is configured by a computer, but any device may be used as long as it has the functions of the present invention. The server may be a server on the cloud.

The storage unit 10 is composed of, for example, a ROM, a RAM, or a hard disk. The storage unit 10 stores an information processing program for operating each unit of the server, and particularly stores determination means (learned model) 11 .

The determination means (learned model) 11 receives the facial image of the animal input by the pet hotel as described above, and determines whether the animal included in the image is the same individual as the facial photograph of the animal stored in the database. It outputs the determination whether or not. The determination means (learned model) 11 in this embodiment includes, for example, a deep neural network or a convolutional neural network.

The processing calculation unit 17 executes identity determination using the determination means (learned model) 11 stored in the storage unit.

The interface unit (communication unit) includes reception means 15 and output means 14, for example, receives a face image of an animal from a photographing means, and transmits to the terminal the determination result of identity and the same individual as the photographed individual. Output individual identification information about

With the entrance/exit management system of this embodiment, the pet hotel can easily determine that the pet brought by the user is the same individual as the pet registered as a member, and the reception of the pet hotel. can be done smoothly.

FIG. 4 shows a flowchart of individual identification based on the embodiment of the entrance/exit management system of the present invention. An employee of the pet hotel uses a photographing means to photograph the face of the pet brought by the user, and inputs it to the reception means of the server using a terminal (step S1). The processing operation unit of the server compares the uploaded face image with the face image of the animal registered in advance in the database using the determination means (learned model), and determines whether or not they are the same individual. Determine (step S2). The output means outputs the judgment result by displaying it on the terminal screen, etc., and presents it to the employee of the pet hotel (step S3).

<Management system>
The animal management system of the present invention comprises a receiving means for receiving an input of a face image of an animal to be examined at a veterinary hospital, a database for storing the face image and individual identification information of the animal, and a receiving means for receiving the face image and the individual identification information of the animal. determining means for determining whether or not the individual reflected in the face image of the animal obtained is the same as the individual stored in the database; and output means for outputting the result of determination by the determining means. In the management system, the determining means uses a trained model to determine whether or not the face image of the animal received by the receiving means is the same individual image as the individual animal stored in the database. The learned model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and receives an input from a certain individual animal. or the face image of another individual animal, and the output is a trained model that determines whether each face image is a face image of a certain individual or another individual It is characterized.

The animal management system of the present invention can be used, for example, when a pet insurance provider wants to know whether a pet covered by pet insurance has been examined.

<Management system>
The management system of the present invention comprises a receiving means for receiving an input of a face image of an animal to be trimmed or shampooed at a pet salon, a database for storing the face image and individual identification information of the animal, and an input received by the receiving means. determining means for determining whether or not the individual reflected in the face image of the animal obtained is the same as the individual stored in the database; and output means for outputting the result of determination by the determining means. In the management system, the determining means uses a trained model to determine whether or not the face image of the animal received by the receiving means is the same individual image as the individual animal stored in the database. The learned model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and receives an input from a certain individual animal. or the face image of another individual animal, and the output is a trained model that determines whether each face image is a face image of a certain individual or another individual It is characterized.

The animal management system of the present invention can be used, for example, when a pet salon wants to know whether a pet to be serviced is a pet registered as a member, and the past service provision history.

<Management system>
The management system of the present invention comprises a receiving means for receiving an input of a facial image of an animal that is a candidate for an animal to be searched, a database for storing the facial image and individual identification information of the animal, and an input received by the receiving means. determining means for determining whether or not the individual reflected in the face image of the animal obtained is the same as the individual stored in the database; and output means for outputting the result of determination by the determining means. In the management system, the determining means uses a trained model to determine whether or not the face image of the animal received by the receiving means is the same individual image as the individual animal stored in the database. The learned model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and receives an input from a certain individual animal. or the face image of another individual animal, and the output is a trained model that determines whether each face image is a face image of a certain individual or another individual It is characterized.

The animal management system of the present invention can be used, for example, when searching for a lost pet and wanting to check whether the found animal is the pet being searched for.

<Age range determination system>
The age range determination system of the present invention uses a receiving means for receiving an input of a facial image of an animal other than a human, and uses a trained model to determine the age range of the animal from the facial image of the animal input to the receiving means. and determination means for outputting.

The age range is the approximate age of the animal. For example, classification such as young, young, middle-aged, and old may be used.

The acceptance means and determination means are the same as those of the above-described variety determination system.

[Example 1]
Toy Poodle, Chihuahua, Miniature Dachshund, Shiba Inu, Pomeranian, Yorkshire Terrier, Miniature Schnauzer, Shih Tzu, French Bulldog, Papillon, and Maltese. As an example, the photographs shown in Figures 5 to 8 (color photographs were used. They were unified into 256 x 256 pixels.) and dog breed information related to each image (as shown in Fig. 9, each dog breed is numbered). ) was used as training data, deep learning was performed, and a trained model was generated.
Deep learning was performed using a convolutional neural network under the TensorFlow environment in Anaconda.
Using the generated learning model, as a test, images (images showing only the eyes and their surroundings) different from the images used to generate the above trained model were prepared for 40 dogs for each breed. made a judgment.
The results are shown in FIG. The percentage of correct answers that correctly answered the dog breed was 71.6% as a whole.

[Example 2]
Deep learning was performed using 40 face photographs of toy poodles with different coat colors for each color to generate a trained model. The facial photographs used are images showing only the eyes and their surroundings, and there are 40 black and silver hair color images, 40 brown hair color images, 40 cream hair color images, and white hair color images. was 40 images.
Under the TensorFlow environment in Anaconda, we used a convolutional neural network to label the photo data with numbers corresponding to each coat color of black & silver, brown, cream and white, as shown in Fig. 11. did the learning.
Using the generated learning model, a test was performed using a facial photograph (image of only the eyes and their surroundings) other than the facial photograph used for evaluation of the learned model. The facial photographs used in the test were images showing only the eyes and their surroundings. There were 40 images with black and silver hair colors, 40 with brown hair colors, 40 with cream hair colors, and 40 with white. 40 images of hair color.
The results are shown in FIG. The percentage of correct answers for hair color was 85.0% as a whole.

[Example 3]
Deep learning was performed using 40 face photographs of Labradors with different hair colors for each color, and a learned model was generated. The face photographs used were images showing only the eyes and their surroundings, and there were 40 images of black hair color, 40 images of chocolate hair color, and 40 images of yellow hair color.
Under the TensorFlow environment of Anaconda, using a convolutional neural network, photo data was labeled with numbers corresponding to each coat color of black, chocolate, and yellow, as shown in Fig. 13, and deep learning was performed. .
Using the generated learning model, a test was conducted using a facial photograph different from the facial photograph used for evaluation of the learned model. The face photographs used in the test were images showing only the eyes and their surroundings, and included 40 images of black hair color, 40 images of chocolate hair color, and 40 images of yellow hair color.
The results are shown in FIG. The correct answer rate of correctly answering the hair color was 86.7% as a whole.

[Example 4]
Forty face images were prepared for each of five toy poodles. Each facial image included eyes, nose, and mouth, but no ears or facial contours.
Deep learning was performed using 24 images for each of the 5 toy poodles to generate a learned model. As shown in FIGS. 15(a) to 15(e), the images of the five toy poodles include "Individual A", "Individual B", "Individual C", "Individual D", and "Individual E". An ID (label) was attached according to the
Under the TensorFlow environment in Anaconda, using a convolutional neural network, the photo data is divided into "individual A", "individual B", "individual C", "individual D", "individual D", as shown in FIG. Deep learning was performed by labeling each individual of individual E” with a number corresponding to each individual.
Using the generated learning model, a test was performed using a facial photograph (image showing the eyes, nose and mouth) different from the facial photograph used to evaluate the above learned model. The number of facial photographs used for the test was 8 for each individual.
The results are shown in FIG. The percentage of correct answers for hair color was 95% as a whole.

Claims (6)

a receiving means for receiving an input of a facial image of an animal other than a human;
A database storing facial images and individual identification information of animals other than humans;
determining means for determining whether or not the face image of the animal input to the accepting means is the same individual image as the individual animal stored in the database, using a trained model. and
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and output is a trained model for determining whether each face image is a face image of a certain individual or another individual. 2. The individual identification system according to claim 1, wherein the facial image used as the training data is an image including the eyes, nose and mouth of the animal and excluding ears and facial contours. Receiving means for receiving input of facial images of animals about to enter or leave; a database for storing facial images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal entrance/exit management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model is trained using facial images of animals other than humans as teacher data, with multiple animal facial images as input and multiple animal facial images of the same individual photographed as output. 1. An entrance/exit management system characterized in that it is a trained model for determining whether or not an object is a thing. a receiving means for receiving input of face images of animals to be examined at a veterinary hospital; a database for storing face images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. . Receiving means for receiving an input of a face image of an animal to be trimmed or shampooed at a pet salon; a database for storing the face image and individual identification information of the animal;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. . Receiving means for receiving input of facial images of animals that are candidates for animals to be searched; a database for storing facial images and individual identification information of animals;
determining means for determining whether or not the individual reflected in the face image of the animal received by the receiving means is the same individual as the individual stored in the database;
an output means for outputting the determination result by the determination means;
An animal management system comprising:
wherein the determination means is means for determining, using a trained model, whether or not the face image of the animal accepted by the acceptance means is an image of the same individual as an individual animal stored in a database; ,
The trained model performs learning using face images of animals other than humans as training data, assigns ID information for each individual to each face image, and inputs an animal face image of a certain individual or another individual. animal face images, and the output is a learned model that determines whether each face image is a face image of a certain individual or a face image of another individual. .

Images