Method and apparatus for providing companion animal entity authentication service by using remote biometric recognition

Abstract

A method by which a service provision system provides an entity authentication service for a target companion animal, according to one embodiment, may comprise the steps of: acquiring biometric raw data for the target companion animal from a biometric information acquisition device; determining the raw data quality of the biometric raw data; extracting biometric feature information from the biometric raw data on the basis of the determined raw data quality; authenticating, on the basis of the extracted biometric feature information and pre-stored biometric information in a database, whether the companion animal is the same entity as the entity specified in the pre-stored biometric information in the database; and outputting the authentication result of whether the entities are the same.

Description

Method and device for providing pet individual authentication service using remote biometric recognition

[0001] The present disclosure relates to a method and device for providing a companion animal individual authentication service using remote biometric recognition.

[0002] The present invention relates to a technology for recognizing, authenticating, and managing the biometric information of companion animals based on remote biometric technology. Since no technology has been disclosed regarding the data collection, management, and authentication conditions for managing the biometric information of companion animals, there is a need for the development of technologies for remote companion animal biometric data collection, management, and authentication.

[0003] According to one embodiment, a service providing system for providing a companion animal individual authentication service and an operating method thereof may be provided.

[0004] According to one embodiment of the present disclosure for achieving the above-described technical problem, a method for providing an individual authentication service for a target companion animal by a service providing system may be provided, comprising: acquiring raw biometric data for the target companion animal from a biometric information acquisition device; determining raw data quality of the raw biometric data; extracting biometric characteristic information from the raw biometric data based on the determined raw data quality; authenticating whether the companion animal is the same individual as an individual specified in biometric information stored in the pre-stored database based on the extracted biometric characteristic information and biometric information in a pre-stored database; and outputting an authentication result regarding whether the companion animal is the same individual.

[0005] According to another embodiment for achieving the above-described technical problem, a service providing system for providing an individual authentication service for a target companion animal, comprising: a network interface; a memory storing one or more instructions; and at least one processor executing the one or more instructions; wherein the at least one processor executes the one or more instructions to thereby obtain raw biometric data for the target companion animal from a biometric information acquisition device, determine raw data quality of the raw biometric data, extract biometric characteristic information from the raw biometric data based on the determined raw data quality, and authenticate whether the companion animal is the same individual as an individual specified in biometric information pre-stored in the database based on the extracted biometric characteristic information and biometric information in a pre-stored database, and output an authentication result as to whether the companion animal is the same individual.

[0006] According to another embodiment for achieving the above-described technical problem, a method for providing an individual authentication service for a target companion animal by a service providing system, comprising the steps of: acquiring raw biometric data for the target companion animal from a biometric information acquisition device; determining raw data quality of the raw biometric data; extracting biometric characteristic information from the raw biometric data based on the determined raw data quality; authenticating whether the companion animal is the same individual as an individual specified in the biometric information stored in the pre-stored database based on the extracted biometric characteristic information and the biometric information stored in the pre-stored database; and outputting an authentication result as to whether the companion animal is the same individual; A computer-readable recording medium having recorded thereon a program for executing the method on a computer may be provided.

[0007] According to one embodiment, it is possible to manage the biometric information of a companion animal that satisfies certain quality conditions.

[0008] According to one embodiment, a pet individual authentication service can be provided based on the biometric information of the pet that satisfies certain quality conditions.

[0009] Figure 1 is a drawing showing an example of the characteristics of a pet's nose pattern.

[0010] Figure 2 is a drawing showing an example of the facial features of a companion animal.

[0011] Figure 3 is a drawing showing an example of an ROI image for a pet nose pattern.

[0012] Figure 4 is a diagram showing the biometric data flow of a biometric information acquisition device based on a client-server structure.

[0013] Figure 5 is a diagram showing the data exchange format of a biometric information acquisition device.

[0014] Figure 6 is a diagram showing a remote object authentication service process for pet object authentication.

[0015] Figure 7 is a diagram showing the data collection and preprocessing process during the pet individual authentication process.

[0016] Figure 8 is a diagram showing a 1:1 identity verification procedure for pet individual authentication.

[0017] Figure 9 is a diagram showing the general protocol of a scenario test.

[0018] Figure 10 is a drawing showing an example of lighting positioning that can be considered in the process of obtaining companion animal biometric information for building a database.

[0019] Figure 11 is a drawing showing an example of biometric devices placed at various angles.

[0020] Figure 12 is a diagram showing the architecture of a companion animal authentication platform.

[0021] Figure 13 is a diagram showing the companion animal authentication platform subscription and registration flow.

[0022] Figure 14 is a diagram showing the login and authentication flow of the companion animal authentication platform.

[0023] Figure 15 is a diagram showing the flow of a case of pet individual authentication failure.

[0024] Figure 16 is a flowchart illustrating a method for a service providing system to specify ROI according to one embodiment.

[0025] FIG. 17 is a flowchart illustrating a method for a service providing system to specify ROI according to another embodiment.

[0026] FIG. 18 is a flowchart illustrating a method by which a service providing system according to one embodiment provides a biometric-based pet platform service.

[0027] FIG. 19 is a flowchart of a method for determining shooting environment information to determine the quality of a captured image of a companion animal or biometric information obtained from a captured image, according to an embodiment of the present invention.

[0028] Figure 20 is a flowchart illustrating a method for a service providing system according to one embodiment to store and transmit biometric information.

[0029] FIG. 21 is a diagram illustrating a method by which a service providing system according to one embodiment performs DB separation and access.

[0030] Figure 22 is a flowchart illustrating a method for registering biometric information for operating a biometric-based pet platform by a service providing system according to one embodiment.

[0031] FIG. 23 is a flowchart illustrating a method for registering biometric information for operating a biometric-based pet platform by a service providing system according to another embodiment.

[0032] FIG. 24 is a flowchart illustrating a method for registering biometric information for operating a biometric-based pet platform by a service providing system according to another embodiment.

[0033] FIG. 25 is a flowchart illustrating a method for determining whether an electronic device and a server are the same or different individuals through biometric information matching by interworking with each other according to an embodiment.

[0034] FIG. 26 is a block diagram of an electronic device or service system according to one embodiment.

[0035] FIG. 27 is a block diagram of an electronic device or service system according to another embodiment.

[0036] Figure 28 is a flowchart of a method in which a service providing system according to one embodiment provides an individual authentication service for a target companion animal.

[0037] According to this embodiment, a method for providing an individual authentication service for a target companion animal by a service providing system may be provided, comprising: acquiring raw biometric data for the target companion animal from a biometric information acquisition device; determining raw data quality of the raw biometric data; extracting biometric characteristic information from the raw biometric data based on the determined raw data quality; authenticating whether the companion animal is the same individual as an individual specified in biometric information pre-stored in a database based on the extracted biometric characteristic information and biometric information in a pre-stored database; and outputting an authentication result regarding whether the companion animal is the same individual.

[0038] A service providing system for providing an individual authentication service for a target companion animal, comprising: a network interface; a memory storing one or more instructions; and at least one processor executing the one or more instructions; wherein the at least one processor executes the one or more instructions to thereby obtain raw biometric data for the target companion animal from the biometric information acquisition device, determine raw data quality of the raw biometric data, extract biometric characteristic information from the raw biometric data based on the determined raw data quality, authenticate whether the companion animal is the same individual as an individual specified in biometric information pre-stored in the database based on the extracted biometric characteristic information and biometric information in a pre-stored database, and output an authentication result as to whether the companion animal is the same individual.

[0039] The terms used in this specification will be briefly explained, and the present disclosure will be described in detail.

[0040] The terms used in this disclosure have been selected from widely used, current terms, taking into account the functions of the disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this disclosure should not be defined simply as names, but rather based on the meanings of the terms and the overall content of the disclosure.

[0041] When a part of the specification is said to "include" a component, this does not exclude other components, but rather implies the inclusion of other components, unless otherwise specifically stated. Furthermore, terms such as "part," "module," etc., used throughout the specification refer to a unit that processes at least one function or operation, which may be implemented in hardware, software, or a combination of hardware and software.

[0042] Below, with reference to the attached drawings, embodiments of the present disclosure are described in detail so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in the drawings, parts irrelevant to the description are omitted for clarity of description of the present disclosure, and similar parts are designated with similar reference numerals throughout the specification.

[0043] The method for providing an entity authentication service described herein may be performed by a service providing system. In one embodiment, the service providing system may include at least one of an electronic device, a client device, a biometric information acquisition device, or a server. In one embodiment, the method for providing an entity authentication service may be performed by the service providing system or at least one device included in the service providing system alone, or by the linkage of at least two or more devices.

[0044] In addition, the technologies disclosed in this specification disclose the following recommendations and topics. The technologies described in this specification follow the contents of Recommendation ITU-T X.1095. The recommendation defines an infrastructure that can perform individual authentication of companion animals using remote biometrics. It specifies multimodal biometrics using the companion animal's nose print (nose print, nose pattern) and face. The recommendation can be applied to various companion animal services such as registration, insurance, and e-healthcare. Since individual authentication of companion animals is always performed in a non-cooperative environment, criteria for obtaining multimodal biometrics suitable for individual authentication of companion animals must be defined.

[0045] Requirements for devices capable of acquiring multiple biometrics and the architecture of an operating platform for robust multi-biometric applications are needed. This recommendation specifies the functional requirements for a biometric capture device and biometric data collection for companion animal authentication. It also defines the platform architecture, performance testing methodology, and privacy concerns.

[0046] The recommendations described herein cover the following topics. In this specification, companion animals may include dogs and cats. Furthermore, multi-biometric identification may include the companion animal's nose print (nose print, nose pattern) and facial information (e.g., facial features). Biometric information acquisition devices may include specialized cameras, such as digital cameras, mobile cameras, infrared cameras, high-speed cameras, and optical scanners. Furthermore, key words for the invention described herein may include "cat," "dog," "individual authentication," "face," "multi-biometric identification," "nose print," "companion animal," and "registration."

[0047] 1. Scope: This recommendation specifies the functional requirements for a biometric data acquisition device (e.g., a biometric data acquisition device) and biometric data collection for pet animal authentication. It also defines platform architecture, performance testing methods, and privacy issues. The following topics are covered within the scope of this recommendation: Pet animals refer to companion animals, such as dogs and cats. Multimodal remote biometric data may include biometric data about nose patterns (nose prints, nose markings) and faces. Biometric data acquisition devices (e.g., biometric data acquisition devices) refer to specialized cameras, such as digital cameras, mobile cameras, infrared cameras, high-speed cameras, and optical scanners.

[0048] 2. References: The following ITU-T Recommendations and other referenced documents are incorporated into this Recommendation by reference. The versions listed were valid at the time of publication. All Recommendations and other referenced documents are subject to revision; therefore, users of this Recommendation are encouraged to check the applicability of the latest versions of the Recommendations and other referenced documents listed below. A list of currently valid ITU-T Recommendations is published periodically. Reference to a document within this Recommendation does not imply that the document itself becomes a Recommendation.

[0049] 3. Definitions: 3.1. Among terms defined elsewhere, this Recommendation uses the following terms defined elsewhere: 3.1.1. Biometric information (e.g. biometric) acquisition device [b-ISO / IEC 2382-37]: A device that acquires signals from biological characteristics and converts them into captured biological samples. 3.1.2. DET (error detection trade-off) plot [b-ISO / IEC 19795-1]: The relationship between false-negative and false-positive errors as the discrimination threshold in a binary classification system varies. 3.1.3. Digital camera [b-ISO 29301]: A device that detects images using a chip array image sensor, such as a charge-coupled device (CCD) or complementary metal-oxide-semiconductor (CMOS), and converts the visual image into an electrical signal. 3.1.4. EER (Equivalent Error Rate) [b-ISO / IEC 2382-37]: The value for which the False Reject Rate (FRR) and the False Accept Rate (FAR) are the same. 3.1.5. FRR (Full Entity Rejection Rate) [b-ISO / IEC 2382-37]: The rate at which verification requests with real biometric data are falsely rejected. 3.1.6. FAR (False Entity Acceptance Rate) [b-ISO / IEC 2382-37]: The rate at which verification requests with false biometric data are falsely accepted. 3.1.7. FTE (Failure to Enroll) [b-ISO / IEC 2382-37]: The failure to create and store a biometric enrollment data record for an eligible biometric capture subject according to the biometric enrollment policy. 3.1.8. FTA (Failure to Acquire Rate) [b-ISO / IEC 2382-37]: Failure to accept a biometric sample of interest output from a biometric capture process for subsequent comparison. 3.1.9. False Match [b-ISO / IEC 2382-37]: Determination of a match between a biometric probe and a biometric reference from different biometric capture targets. 3.1.10.FMR (False Match Rate) [b-ISO / IEC 2382-37]: The rate at which, during a completed biometric comparison test, comparison results of subjects with different biometric data are falsely matched. 3.1.11. False Mismatch [b-ISO / IEC 2382-37]: The determination of a mismatch between a biometric probe and a biometric reference with the same biometric capture subject and the same biometric characteristics. 3.1.12. FNMR (False Mismatch Rate) [b-ISO / IEC 2382-37]: The rate at which, during a completed biometric comparison test, comparison results of subjects with the same biometric data are falsely mismatched. 3.1.13. Optical Image Stabilization [b-ISO 20954-1]: The ability to compensate for image displacement in the focal plane due to movement of a handheld camera by moving part or all of the optical system and / or the image sensor based on a camera motion detection means. 3.1.14. Optical Scanner [b-ISO 6196-7]: A scanner that uses light to inspect patterns. 3.1.15. Scenario Evaluation [b-ISO / IEC 2382-37]: An evaluation that measures end-to-end system performance in a prototype or simulated application, with a test team. 3.1.16. Technology Evaluation [b-ISO / IEC 2382-37:]: An offline evaluation of one or more algorithms for the same biometric modality using an existing or specially collected sample corpus.

[0050] 3.2. The following terms are defined in this Recommendation: 3.2.1. Face: Biometric information, such as the facial features of a pet. 3.2.2. Caregiver: A person who cares for a pet at home or in a shelter. 3.2.3. Mobile Camera: A camera integrated into a smartphone or mobile device. 3.2.4. Nose Pattern: Biometric information, such as the wrinkle pattern on a pet's nose. 3.2.5. Pan: The angle at which the camera head moves horizontally without changing the camera position. 3.2.6. Specialized Camera: A camera designed for a specific purpose or use, such as an infrared camera or a high-speed camera. 3.2.7. Tilt: The angle at which the camera head moves vertically without changing the camera position.

[0051] 4. Abbreviations and Acronyms This advisory uses the following abbreviations and acronyms: DB: database; OIS: optical image stabilization; PII: personally identifiable information; ROI: region of interest.

[0052] 5. No rules.

[0053] 6. Prerequisites: None.

[0054] 7. Overview of Multimodal Remote Biometric Information for Pet Individual Authentication

[0055] 7.1. Types of multimodal remote biometric information

[0056] 7.1.1. Nose Pattern: The nose pattern is a biometric feature that uniquely identifies a pet with a wrinkled nose. The nose pattern consists of ridges and valleys. Ridges are relatively high, flat areas, while valleys are relatively low, elongated, and sunken areas. These ridges and valleys are mapped into a polygonal pattern, and this complex pattern serves as a unique biometric marker for each pet.

[0057] 7.1.2. Face: The face is the biometric information that represents the unique identity of a pet animal with geometric features between the eyes, nose, and muzzle.

[0058] 7.2. The characteristics of remote biometric information for pet individual authentication are as specified in this specification. First, the nose pattern-related recommendations in 7.2.1 are described in detail with reference to Figure 1 below.

[0059] Figure 1 is a drawing showing an example of the characteristics of a pet's nose pattern.

[0060] Referring to Figures (110) and (120) of FIG. 1, raw biometric data obtained by photographing a companion animal are illustrated. Referring to Figures (110) and (120), examples of nose pattern (e.g., nose pattern) features (e.g., nasal print features) of a companion animal are illustrated. According to one embodiment, the raw biometric data may include video or image information of the nostril (112, 122) region and the philtrum (114, 124) region of the companion animal. The nose pattern (116, 126) may be identified from the nose region data included in the raw biometric data. The nose pattern is mainly located between the nostrils of the companion animal and may have a very complex skin wrinkle pattern. The nose pattern of each companion animal may represent the unique identity of each companion animal. The nose pattern may be used to uniquely identify each companion animal. 7.2.2. Face-related recommendations of the above recommendation will be described in detail below with reference to FIG. 2.

[0061] Figure 2 is a drawing showing an example of the facial features of a companion animal.

[0062] In one embodiment, the biometric raw data may include data on at least one of a nose region, a face region, or a snout region of a companion animal. In one embodiment, the snout region may include a nose region. The face of a companion animal, like a human, has unique geometric features for each companion animal, and facial features may be extracted by detecting the eyes (212), nose (214), and snout of the companion animal. In one embodiment, the biometric raw data may include biometric feature information including a nose pattern (e.g., nose pattern feature) and facial features of the companion animal. Referring to Figure (210), biometric raw data of an image type acquired by photographing a companion animal is illustrated.

[0063] Figure 3 is a drawing showing an example of an ROI image for a pet nose pattern.

[0064] Referring to FIG. 3, a ROI (312) identified in the raw biometric data is illustrated. According to one embodiment, the service providing system can provide an individual authentication service for companion animals by utilizing the raw biometric data including the ROI satisfying certain conditions. Below, the requirements for a biometric information capture device (e.g., a biometric information acquisition device) for individual authentication of a pet (e.g., a companion animal) among the above recommendations are described.

[0065] Biometric information capture devices that acquire raw biometric data must meet the following requirements according to the recommendation.

[0066] 8. Requirements for biometric information acquisition devices for pet individual authentication

[0067] 8.1. Types of biometric information acquisition devices

[0068] According to one embodiment, sensors for remotely detecting biometric information of pets can be categorized into three types of image recording devices: mobile cameras, digital cameras, and specialized cameras. Sensors for detecting biometric information through contact can be optical scanners. According to one embodiment, the biometric information acquisition device can include at least one of a mobile camera, a digital camera, a specialized camera, and an optical scanner.

[0069] 8.2. Functional Requirements for Biometric Information Acquisition Devices for Pets

[0070] Biometric capture devices (e.g., biometric acquisition devices) must be able to handle unexpected movements of pets. Sensors that remotely detect biometric information must meet minimum requirements for image resolution, shutter speed, ISO, and aperture. Furthermore, sensors that detect biometric information through contact must position the pet's biometric information within the prism area of ​​an optical scanner. Minimum requirements may be determined by the quality of the region of interest (ROI) image containing the pet's biometric information. The ROI image of the nose pattern must contain at least 60% of the biometric information, and the biometric information ratio must be measured by the number of pixels within the image.

[0071] S No.ItemsRequirements1Pixels5 megapixels (MP)2Sensor size1 / 3 inch3Aperturef / 1.84Resolution1 080 x 1 080 pixels5Shutter speed (indoor)1 / 1 000 th of a second to 1 second6Shutter speed (outdoor)1 / 500 th of a second to 1 second7ISO200 to 400

[0072] Table 1 above shows the minimum requirements for a sensor used at a distance, including items such as pixels, sensor size, aperture, resolution, and shutter speed (indoors and outdoors). A biometric information acquisition device for acquiring biometric raw data at a distance according to the present disclosure may include a sensor that satisfies the requirements set forth in Table 1.

[0073] S No.ItemsRequirements1Pixels2 megapixels (MP)2Resolution500 DPI3Frame per second (fps)10 fps4Image formatRAW, BMP, WSQ, JPEG 2000

[0074] Table 2 above shows the minimum requirements for a contact-type sensor, including pixel count, resolution, frames per second, and image format. In one embodiment, a biometric information acquisition device for acquiring biometric raw data through contact may include a sensor that satisfies the requirements set forth in Table 2 above.

[0075] S No.ItemsRequirements1Size of ROI256 × 256 pixels2Ratio of biometrics (in ROI)60%

[0076] Table 3 above shows the minimum requirements for a ROI for a nose pattern, including the size of the region of interest and the ratio of biometric information within the ROI. The service providing system according to the present disclosure can determine whether an ROI satisfying the ROI conditions according to Table 3 is specified in the biometric raw data acquired by a biometric information acquisition device. FIG. 4 is a diagram illustrating the biometric data flow of a biometric information acquisition device based on a client-server architecture.

[0077] When biometric information is used for pet animal individual authentication, the procedure illustrated in FIG. 4 must be followed. This procedure has a sensor-based client-server architecture and may be either separate or integrated depending on the presence or absence of a communication device. The procedure illustrated in FIG. 4 may be performed by a service providing system. In one embodiment, the service providing system may include a biometric information acquisition device (410), a client (420), and a server (430). The configurations of the biometric information acquisition device, the client, and the server may each correspond to the configuration of the electronic device described below.

[0078] In S412, according to one embodiment, the client (420) may transmit a data request to the biometric information acquisition device (410). In S414, the biometric information acquisition device (410) may activate at least one of a camera or a sensor. In S416, the biometric information acquisition device (410) may acquire data by using at least one of a camera or a sensor. In S418, the biometric information acquisition device (410) may transmit data including the acquired biometric raw data to the client (420). In S420, the client (420) may detect biometric information from the acquired biometric raw data. In S422, the client (420) may extract features from the acquired biometric information or biometric raw data. In S423, the client (420) may perform a quality assessment on the extracted features or biometric raw data.

[0079] At S424, the client (420) may transmit a biometric information template to the server (430) based on the quality assessment result. In one embodiment, the client (420) may transmit either the extracted feature information or the biometric raw data to the server, or may transmit the extracted feature information and the biometric raw data together to the server. At S426, the server (430) may compare the biometric information template transmitted from the client with a registered template. At S428, the server (430) may generate a comparison result between the biometric information template transmitted from the client (420) and the registered template. At S430, the server (430) may transmit information about the comparison result to the client. At S420, the client (420) may perform individual verification or identification of the current target companion animal based on the comparison result obtained from the server (430).

[0080] Figure 5 is a diagram showing the data exchange format of a biometric information acquisition device.

[0081] The biometric information acquisition device according to the present disclosure may also be referred to as a biometric information acquisition device. Referring to FIG. 5, the data exchange format of the biometric information acquisition device according to item 8.3 of the above recommendation is illustrated.

[0082] According to one embodiment, data exchanged between internal devices of a service providing system may include a format as illustrated in FIG. 5. According to one embodiment, data exchanged between internal devices of a service providing system (e.g., a biometric information acquisition device, an electronic device, a client, a server) may include at least one of a file header (510), biometric raw data (520), biometric characteristic data (530), or a security block (540). According to one embodiment, the format (e.g., a format) may include a file header indicating basic information, biometric raw data, and characteristic data.

[0083] The above format shall be in accordance with the contents of the following recommendation corresponding to item 8.3 of the above recommendation items described below.

[0084] 8.3.1. File Header

[0085] The file header format consists of basic information summarizing the characteristics of the biometric raw data and feature data, including sensor, time, and measurement information.

[0086] 8.3.2. Biometric raw data

[0087] The biometric raw data format consists of a length header indicating the length of the raw data, signal quality, and an array of raw data measured from a biometric information acquisition device.

[0088] 8.3.3. Biometric data

[0089] The biometric feature data format consists of a length header indicating the length of the feature data and binarized data implementing the unique features of each pet animal extracted from the biometric raw data.

[0090] 8.3.4. Security Block

[0091] The security block is optional and contains additional security parameters. It indicates whether all biometric information is signed and whether the raw data or feature data is encrypted.

[0092] Figure 6 is a diagram showing a remote object authentication service process for pet object authentication.

[0093] Referring to FIG. 6, a remote biometric authentication model for performing a remote entity authentication service provided by a service provision system is illustrated. The remote biometric authentication model may comply with the following 9. Pet entity authentication platform architecture requirements according to the above recommendation.

[0094] 9. Pet Object Authentication Platform Architecture Requirements

[0095] 9.1. Overview

[0096] The pet individual authentication model using remote biometric information consists of data acquisition, data transmission, and biometric authentication processes.

[0097] The pet authentication model illustrated in Figure 6 primarily describes an authentication model utilizing a mobile camera. Key application models of the pet authentication platform include abandoned animal rescue, pet insurance, pet health management, and pet travel.

[0098] In one embodiment, the service providing system may obtain data about a companion animal in accordance with the above recommendation at S610. For example, the service providing system may obtain a photographed image (604) by photographing the target companion animal (602), and obtain feature data (612) from the obtained photographed image (604). The feature data (612) may include facial features (614) and nose patterns (616). In S620, the service providing system may perform normalization processing on the obtained feature data (612) and store the normalized data in data storage (626). In one embodiment, the normalized data may include normalized facial features (622) and nose patterns (624). In S630, the service providing system may perform biometric authentication based on the normalized feature data stored in data storage (626). According to this embodiment, biometric authentication can be applied to various applications (632) for providing pet tech services, abandoned animal rescue insurance, pet healthcare, and pet travel services.

[0099] Figure 7 is a diagram showing the data collection and preprocessing process during the pet individual authentication process.

[0100] Figure 7 illustrates the process by which a service provider system acquires raw biometric data, preprocesses the acquired raw biometric data, performs a quality assessment on the preprocessed data, and extracts features from the data based on the quality assessment results. The data collection and preprocessing process performed by the service provider system conforms to the following recommendations:

[0101] 9.2. Functional Requirements for the Pet Object Authentication Mechanism

[0102] 9.2.1. Data Acquisition and Preprocessing

[0103] Biometric data of pets (e.g., companion animals) is collected from a biometric capture device and preprocessed for signal optimization prior to feature extraction. The raw biometric data is preprocessed using analog or digital filters. When a camera is used as the biometric capture device, the filters should be optimized to reduce noise caused by unrestricted lighting and the pet's movement. When an optical scanner is used as the biometric capture device, the filters should be optimized to reduce noise caused by unrestricted movement and moisture from the pet's nose. If the quality of the filtered raw biometric data is not sufficient for individual authentication of each pet, the collected data should be discarded and the acquisition process repeated.

[0104] 9.2.2. Feature Extraction and Registration in Biometric Databases

[0105] Individual features are extracted from biometric information. For each biometric characteristic, an algorithm is used to extract biometric features that minimize within-subject variability and maximize between-subject variability. The extracted biometric features are registered in a database (DB). If the same pet animal is later attempted for authentication, the biometric feature data set is loaded into the DB via ID, and the pet animal is authenticated through feature comparison.

[0106] According to the above recommendation, the service providing system can acquire raw biometric data from a camera (702) or an optical scanner (704). For example, in S702, the service providing system can perform preprocessing for noise reduction of raw biometric data (e.g., a photographed image) acquired from the camera. In S710, the service providing system can acquire preprocessed biometric information (710) generated through the data preprocessing. Furthermore, according to one embodiment, in S704, the service providing system can acquire a scanner image from an optical scanner, perform preprocessing for noise reduction on the acquired scanner image, and acquire preprocessed biometric information (710) that has been preprocessed for noise reduction in S710.

[0107] In S712, the service providing system can obtain a quality assessment result (712) by performing a quality assessment on the preprocessed biometric information. In S714, the service providing system can determine a quality score (714) based on the quality assessment result performed on the preprocessed biometric information. If the quality score is identified as satisfying a threshold score or a predetermined quality level, the service providing system can extract a feature (716) from the preprocessed biometric information in S716. According to one embodiment, the service providing system can use a biometric feature extraction algorithm that reduces intra-individual variability and increases inter-individual variability in extracting biometric information features from biometric raw data identified as satisfying a predetermined quality level.

[0108] However, if the service providing system determines that the quality score does not meet a threshold or a predetermined quality level, it may re-acquire raw biometric data from the camera or optical scanner. In one embodiment, the service providing system according to the present disclosure may discard data that does not meet a predetermined quality score requirement and acquire new raw biometric data for the target companion animal.

[0109] Although not shown in FIG. 7, the service providing system can determine the quality of biometric raw data acquired from the biometric information acquisition device, and if the determined data quality is identified as satisfying a predetermined raw data quality level, biometric characteristic information can be extracted from the biometric raw data.

[0110] In addition, according to one embodiment, the service providing system may identify a ROI (e.g., a region of interest) from the biometric raw data, even if the raw data quality level of the biometric raw data is identified as satisfying a predetermined quality level, determine a quality level for the identified ROI region, and then extract biometric feature information from the ROI region if the quality level for the identified ROI region is identified as satisfying the predetermined quality level.

[0111] As another example, the service providing system may extract biometric features from the biometric raw data if the ROI region identified from the biometric raw data is identified as satisfying a predetermined quality level.

[0112] In another example, the service providing system may utilize the biometric characteristic information for a companion animal authentication service when the quality of the biometric raw data is identified as satisfying a predetermined raw data quality level, the quality level of the ROI region extracted from the biometric raw data is identified as satisfying a predetermined quality level, and the quality level of the biometric characteristic information extracted from the ROI region is further identified, and then the quality level of the biometric characteristic information extracted from the ROI region is identified as satisfying a predetermined condition.

[0113] According to one embodiment, the service providing system can determine whether the quality status of the biometric raw data, which is determined based on a quality evaluation factor regarding at least one of brightness, noise, or clarity of the biometric raw data, satisfies a raw data quality level sufficient to extract the biometric characteristic information.

[0114] In another example, the service providing system may perform a step of determining whether a brightness score of biometric raw data is greater than or equal to a first threshold brightness score, and a step of determining that the quality of the biometric raw data does not satisfy a target quality level for extracting biometric characteristic information if the brightness score of the biometric raw data is identified as being less than the first threshold brightness score, and a step of determining a noise score of the biometric raw data if the brightness score of the biometric raw data is identified as being greater than or equal to the first threshold brightness score.

[0115] In another example, the service providing system may further perform the step of determining whether the noise score of the biometric raw data identified as being greater than or equal to the first threshold brightness score is greater than or equal to a second threshold noise score, and if the noise score of the biometric raw data is identified as being less than the second threshold noise score, determining that the quality of the biometric raw data does not satisfy the target quality level for extracting the biometric characteristic information, and if the noise score of the biometric raw data is identified as being greater than or equal to the second threshold noise score, determining the sharpness score of the biometric raw data.

[0116] According to another example, the service providing system may further perform the steps of determining a clarity score regarding the clarity level of the biometric raw data identified as being greater than or equal to the second threshold noise score, and determining that the quality of the biometric raw data does not satisfy a target quality level for extracting the biometric characteristic information if the clarity score of the biometric raw data is identified as being less than a third threshold clarity score, and determining that the raw data quality of the biometric raw data satisfies a target raw data quality level for extracting the biometric characteristic information if the clarity score of the biometric raw data is identified as being greater than or equal to the third threshold clarity score.

[0117] According to another example, the service providing system may further perform the step of determining a focus out score according to a focus value of the biometric raw data identified as having a noise score greater than or equal to the second threshold noise score, the step of determining a motion blur score according to a motion value of the biometric raw data identified as having a noise score greater than or equal to the second threshold noise score, and the step of determining, when the determined focus out score is less than a fourth threshold focus out score or the determined motion blur score is less than a fifth threshold motion blur score, the step of determining the raw data quality of the biometric raw data determined as having a focus out score less than or equal to the fourth threshold focus out score or the motion blur score less than the fifth threshold motion blur score as satisfying a raw data quality level from which the biometric feature information is to be extracted.

[0118] Figure 8 is a diagram showing a 1:1 identity verification procedure for pet individual authentication.

[0119] The 1:1 identity verification procedure for pet individual authentication provided by the service provision system may follow the contents of the matching algorithm in 9.2.3 below according to the recommendation.

[0120] 9.2.3. Matching Algorithm

[0121] In the 1:1 verification method, the registered biometric data is compared one-to-one with the biometric data of the pet attempting authentication. When the pet attempts authentication, the features extracted from the measured biometric information are compared with the features registered in the database. As shown in Figure 8, the pet's ID is presented and the registered biometric data is loaded from the database. A similarity score between the features is calculated, and if the score exceeds a threshold, the result is passed. The similarity score must be calculated using an objective mathematical calculation, such as the Euclidean distance or Mahalanobis distance.

[0122] In the 1:N identification method, the data of the pet to be identified is compared with all data in the database. Since data comparison is performed on all registered data, the number of matching attempts increases exponentially with the number of registered pets. This analysis process preferably uses a majority-vote consensus analysis method to increase the reliability of the matching calculation, and a process for comprehensively evaluating the calculation results is also required. The pet with the highest match is determined to be the same individual as the identification requester, and the results should be provided.

[0123] 9.3. Functional Requirements for Remote Biometric Information Transmission Protocol

[0124] This section defines the functional requirements for a remote biometric information transmission protocol. The transmitted biometric information must demonstrate a certain level of compliance, interoperability, and security. The remote biometric information transmission protocol is an application protocol and is implemented with standards-based communication protocols, whether wired or wireless.

[0125] 9.4. General Requirements for the Pet Object Authentication Test DB

[0126] 9.4.1. Data Acquisition Requirements for Test DB

[0127] Data acquisition is a crucial part of the process due to the accuracy of the individual authentication mechanism. It's also important to consider the data acquisition environment and the uncooperative nature of pets.

[0128] Biometric data from pets can be biased due to lighting and exposure to biometric capture devices. Therefore, biometric data from pets must be acquired in a controlled environment. To maintain objective criteria for performance testing, several conditions for the acquisition environment must be met.

[0129] Pet animals are uncooperative biometric data capture targets. To obtain images suitable for remote biometric data applications, a process is required to clean up the target biometric data. The acquisition process can be repeated multiple times to build a test database.

[0130] 9.4.2. Test DB Construction Procedure and Method

[0131] Remote biometric data acquisition should be conducted in a comfortable environment with the pet to avoid triggering unexpected behavior. This environment can be set up with the assistance of the owner, veterinarian, or animal trainer. If using a camera, it is recommended to conduct the acquisition in an indoor environment that maintains a certain level of lighting.

[0132] 9.4.3. Metadata Features of the Test DB

[0133] A remote biometric database for pet entity authentication consists of common environment, device, and feature metadata.

[0134] ClassFeaturesMeaningDB_InfoCountryCitySupplierRegisterDateRevisionDateRevisionHistoryVersion

[0135] Table 4 above shows common metadata including country, city, provider, registration date, modification date, modification history and version of the remote biometric information test DB.

[0136] ClassFeaturesMeaningEnvironment_InfoExperimentConditionLuxDevice_InfoDeviceTypeMaxResolution

[0137] Table 5 above shows the environment and device metadata of the test DB. Environment information may include characteristics regarding experimental conditions, and device information may include characteristics regarding device type and maximum resolution.

[0138] ClassFeaturesMeaningFile_InfoFileFormatFileNameDirectoryPathFileSizeBiometrics_InfoBiometricTypeNose pattern, faceRawDataImage or videoImageResolutionSubject_InfoBirthDateGenderBreedGuardian_InfoGuardianIDMiscellaneous_InfoOrderOfRepeatComment

[0139] Table 6 above shows the characteristic metadata of the test DB. The File_Info class can include features for file format, file name, directory path, and file size; the Biometrics_Info class can include features for biometric information type (nose pattern, face), biometric raw data (image or video), and image resolution; the Subject_Info class can include features for date of birth, gender, or breed; Guardian_Info can include features for guardian ID; and the Miscellaneous_Info class can include features for repetition order and notes.

[0140] 9.4.4. Data Exchange Format for Test DB

[0141] Remote biometric information and related data from pets must be encrypted and compressed on the server and stored in a specific database. The compressed information must be accessible only to designated individuals working on the project.

[0142] 10. Performance Testing Methodology for Pet Object Authentication Mechanism

[0143] 10.1. General

[0144] This section defines guidelines for a performance testing methodology based on technology and scenario evaluation. Key performance metrics include the FTE (Failure to Enroll) rate, FTA (Failure to Acquire) rate, FRR (False Object Rejection Rate), FAR (False Object Acceptance Rate), Equivalent Error Rate (EER), and Decision Error Tradeoff (DET) plots. Technical evaluation of remote biometric authentication algorithms is an offline evaluation that repeatedly evaluates the algorithm's recognition performance and processing speed against an evaluation database comprised of pre-collected biometric sample data and a standardized database. This evaluation method allows for the comparison of the performance of various algorithms.

[0145] 10.2. Technology Evaluation Procedure

[0146] 10.2.1. Building a Test DB

[0147] In the technical evaluation, the test database must meet the minimum requirements listed in Table 7. The test database should contain at least 500 pets of various breeds and ages, with 2 to 20 biometric data per pet, at least two acquisition environments, and a total of 1,000 to 10,000 biometric data. In particular, the acquisition environment must consider the presence of a guardian, dog trainer, or handler during the acquisition process to prevent accidents such as dog bites. Furthermore, pet movement, out-of-focus biometric data capture devices, and moisture in the biometric data must be controlled to an appropriate level.

[0148] ClassRequirementsNumber of subjects (N)500Number of breeds10Biometrics per subject (M)2 to 20Number of acquisition environment2Resolution1 080 x 1 080 pixelsSize of ROI256 x 256 pixelsRatio of biometrics (in ROI)60%Minimum transactions on comparison decisions with the same biometric subjects500 (= MC2×N)Minimum transactions on comparison decisions with different biometric subjects499,500 (= NC2×M2)

[0149] Table 7 above shows the minimum requirements for DB testing. The test DB must satisfy the requirements of Table 7, including the number of test subjects (N), number of breeds, number of biometric information per subject (M), number of acquisition environments, resolution, ROI size, ratio of biometric information within ROI, minimum transaction for comparison decisions between subjects with the same biometric information, and minimum transaction for comparison decisions between subjects with different biometric information.

[0150] 10.2.2. Sample Quality Testing

[0151] The test database should reflect the diversity of pet animals, and the diversity should be limited to a certain range to analyze the competitiveness of performance evaluations. Sample quality testing of the database should be conducted to ensure that the test database is constructed under conditions suitable for evaluation.

[0152] 10.2.3. Technical Testing

[0153] The technology testing process consists of two phases: preparation and evaluation. The preparation phase proceeds as follows:

[0154] (1) Contact us and provide a brief introduction to the evaluation environment. (2) Prepare a document detailing the contract, results, and evaluation process. (3) Share a sample database that meets the minimum requirements for a test database. (4) Conduct a small-scale preliminary test using the sample database.

[0155] The evaluation steps proceed as follows:

[0156] (1) Perform tests using a standardized database. (2) Analyze performance test results and report the results.

[0157] 10.2.4. Analysis Testing and Reporting Results

[0158] The analysis and reporting procedures should be performed as follows:

[0159] (1) Description of the technology used. (2) Introduction to the evaluation environment and criteria. (3) Specification of the test database used. (4) Test database quality assessment. (5) Performance evaluation test procedures.

[0160] 10.3. Scenario Evaluation Procedure

[0161] 10.3.1. Evaluation Plan

[0162] Before conducting a scenario assessment, you must prepare the test scenario, evaluation metrics, environment, test algorithm, and participants. Additionally, the following items should be confirmed in advance:

[0163] ItemsDescriptionScenario featuresDefinition of application: Objective of the evaluation and scenarioEvaluation metrics: FAR, FRR, etc.Environment and platform: Indoor or outdoorEvaluation policyPolicy related to the whole evaluation processLevel of trialsMaximum and minimum levels of registration and authentication trialsNumber of repeatsThe number of participants needed to visit the platformMinimum number of participantsCalculation based on the rule of 3-Estimates with FAR-Estimates with FRRRecording methodMethod to record the results of registration and authentication

[0164] 상기 표 8은 시나리오 테스트 체크리스트를 나타낸다.

[0165] 10.3.2. 시나리오 테스트

[0166] According to the above-described recommendation, the service providing system can provide a service for 1:1 individual authentication. For example, the service providing system can pre-generate a registered biometric information DB (804) based on an ID and a password (802). When input biometric information (806) is acquired, the service providing system can identify facial features (808) and nose patterns (810). The service providing system can perform a matching analysis (Analysis 1) on the facial features (808) of the input biometric information and the facial features (812) of the retrieved biometric information (814). In addition, the service providing system can perform a matching analysis (Analysis 2) on the nose pattern (810) of the input biometric information and the nose pattern (816) of the retrieved biometric information (814). The service providing system can determine a matching score (818) based on the results of Analysis 1 and Analysis 2. The service provision system can determine (820) whether to authenticate a companion animal specific to the input biometric information (806) based on the matching score (818) and provide a result (822) of positive or negative.

[0167]

[0168] Figure 9 is a diagram showing the general protocol of a scenario test.

[0169] Scenario test participants must initially register their biometric information upon registration. N represents the total number of visits by the participant. Participants who fail to register for the test are only responsible for intruder matching. A service providing system implementing the protocol according to Figure 9 may adhere to the following recommendations.

[0170] 10.3.3. Analysis Testing and Results Reporting

[0171] The scenario assessment results report consists of a summary, plan, procedures, data log, data analysis, data storage, and assessment results.

[0172] (1) Summary: A summary of information about participants, evaluation results, etc. (2) Scenario: A description of the overall setup of the evaluation, such as objectives, metrics, and environment (3) Plan: A detailed description of the evaluation plan (4) Procedure: A description of the process from initial contact to the end of the evaluation (5) Data Log: A list of participants, registration, and certification results (6) Data Analysis: Reporting of key and submetric results (7) Data Storage: A description of data storage and storage methods (8) Evaluation Results: Conclusions for each metric and testing algorithm

[0173] 11. PII Protection for Individual Authentication Services for Pets and Their Guardians

[0174] 11.1. PII Protection Policy

[0175] When remote biometric mechanisms are applied to individual authentication platforms, personally identifiable information (PII) protection policies are required to minimize the risk of personal information leakage for pet owners.

[0176] 11.1.1. DB separation

[0177] To protect the guardian's personal information from external attacks using the pet database, the guardian database and the pet database must be separated. The guardian ID must be logically and physically separated from the pet's biometric information. In this case, a common identifier that can identify both the guardian and the pet is required. This common identifier must meet the following security requirements:

[0178] (1) Extraction of guardian IDs and pet biometric information using only common identifiers must be prohibited. (2) If a specific database is attacked and illegally modified, each database administrator must be able to recognize and report the attack. (3) If one administrator attempts to modify database contents using a private key, other administrators must be able to recognize the change.

[0179] 11.1.2. Guardian Information

[0180] Personal information contained in guardian information must be protected. Examples of guardian personal information include name, phone number, date of birth, address, text, voice, and media. If an administrator operating a pet authentication service using remote biometrics attempts to collect personal information from guardians, the following policies must be in place.

[0181] (1) Guardian identifiers must be used appropriately, and their intended use must be disclosed in advance. (2) Care must be taken to avoid collecting unnecessary data in accordance with data collection restrictions. (3) If the administrator needs to link each guardian's personal information, each guardian must obtain consent from the administrator for the use of their information elsewhere.

[0182] Appendix I. Use Case of Database Construction Scenario for Pet Object Authentication

[0183] (This appendix does not constitute an essential part of this recommendation.)

[0184] I.1. Database Construction Requirements for Pet Object Authentication

[0185] I.1.1. Data Acquisition Environment

[0186] In one embodiment, the service providing system may provide a registration process, an authentication process, and a service for repeat visitors according to the protocol of FIG. 9 for scenario testing of an individual authentication service for companion animals. For example, in step S910, the service providing system may perform a registration quality test. The service providing system may verify whether the companion animal's biometric information (e.g., facial features, nose pattern) meets certain quality requirements. For example, in step S912, if the service providing system determines that the quality requirements are met, the service providing system may store the information in a database. If the companion animal's biometric information does not meet the quality requirements, the service providing system may request the user to re-register.

[0187] The service providing system according to the present disclosure can achieve accuracy and reliability of a companion animal biometric authentication system through processes S912 to S914.

[0188] For example, in S914, if biometric information satisfying a certain quality requirement is identified and an authentication attempt occurs using the biometric information, the service providing system can compare the entered biometric information with information stored in a database to confirm whether it is the actual registered pet individual. If the comparison results match, the service providing system can determine authentication success, and if they do not, the authentication fails. According to one embodiment, the matching in S914 can be evaluated using the False Rejection Rate (FRR) and Genuine Acceptance Rate (GAR) indices.

[0189] In S916, the service providing system can evaluate its matching ability to accurately determine whether an unregistered pet or another pet is authenticated when authentication is attempted using the biometric information of the pet. For example, when an unregistered pet's biometric information is entered, the service providing system can compare the entered biometric information with all pet biometric information stored in the database, and if no matching information is found, the authentication fails. If a matching information is found, the authentication succeeds (since the information is not actually registered, this is an error). In S918, the service providing system can record the number of pet authentication attempts. For example, if the number of visits exceeds a predefined number N, the test is terminated. Otherwise, the service providing system can move to visit N-1 and proceed with the next authentication attempt.

[0190] Figure 10 is a drawing showing an example of lighting positioning that can be considered in the process of obtaining companion animal biometric information for building a database.

[0191] Referring to Figures (1010), (1012), and (1014) of FIG. 10, examples of lighting positions in an environment where a biometric information acquisition device of a service provision system photographs a target companion animal are illustrated. Figure (1010) illustrates a case where the image of the left portion is captured brightly when the left light in the figure is turned on, Figure (1014) illustrates a case where the image of the right portion is captured brightly when the right light in the figure is turned on, and Figure (112) illustrates a case where the entire area is captured evenly and brightly when all lights are turned on.

[0192] Figure 11 is a drawing showing an example of biometric devices placed at various angles.

[0193] Referring to Figures (1112) and (1114) of FIG. 11, examples of biometric information acquisition devices positioned at various angles are illustrated. In one embodiment, the biometric information acquisition device may include a biometric recognition device.

[0194] To conduct objective performance testing, the biometric information acquisition device of a service provision system must consider various environmental parameters of the environment in which the biometric information is acquired. For objective performance testing, the environment in which the service provision system acquires biometric information, the biometric information acquisition device used to acquire biometric information, and the database construction process should adhere to the following recommendations.

[0195] I.1.1. Data Acquisition Environment

[0196] Conducting objective performance tests requires considering various environmental parameters. This scenario describes the location, lighting, and camera angle of the biometric capture device used to build the database. Furthermore, only the nose pattern is captured as biometric data.

[0197] The location can be indoors or outdoors. Lighting can be set in various directions, and the camera angle can be set horizontally or vertically along the front of the pet.

[0198] I.1.2. Biometric information capture device

[0199] To minimize unexpected image quality biases that may occur due to the camera, we recommend using a camera with optical image stabilization (OIS) and a USB 3.0 system. The number of cameras is calculated based on environmental parameters, including lighting and camera angle.

[0200] DevicesThe number of pan parameters(A)The number of tilt parameters(B)The number of devices(C = A*B)Mobile camera339

[0201] Table 9 above shows an example of calculating the number of biometric devices. I.2. Database construction process requirements

[0202] I.2.1. Preparation Process

[0203] Suitable locations for database development include pet playgrounds, pet parks, animal shelters, and rabies vaccination events, where many pets gather. Signage and instructions should be provided for participants. To prevent accidents such as dog bites, safety rules should be announced in advance, and animal experts, such as animal trainers and veterinarians, should be present.

[0204] I.2.2. Main Process

[0205] I.2.2.1. Entering Metadata

[0206] Pet owners and guardians participating in the database must agree to the privacy policy. After reviewing the privacy policy, guardians enter their pet's metadata, excluding their pet's biometric information.

[0207] I.2.2.2. Preparing to Acquire Biometric Data

[0208] The camera should be placed approximately 20-40 cm away from the pet. The owner should lift the pet's face and keep it calm. Before capturing biometric data, a portion of the biometric data should be cleaned.

[0209] I.2.2.3. Acquisition of Biometric Data

[0210] Biometric information must be captured when the camera is well-focused on the biometric information. If multiple cameras are used, captures should be timed to coincide with the moment when two or more cameras are well-focused on the biometric information. The number of captures is calculated based on location type, lighting, and camera angle parameters. This process can be repeated until biometric information is collected under various conditions.

[0211] The number of indoor illumination(A)The number of outdoor illumination(B)The number of pan parameters(C)The number of tilt parameters(D)The number of acquisition(E = (A+B)*C*D)313336

[0212] Table 10 above shows an example of calculating the number of acquisitions.

[0213] I.3. Metadata Features

[0214] In this scenario, the metadata features follow those in Section 9.4.3.

[0215] ClassFeaturesMeaningDB_InfoCountryCitySupplierRegisterDateRevisionDateRevisionHistoryVersion

[0216] Table 11 above shows the common metadata of the test DB.

[0217] ClassFeaturesMeaningEnvironment_InfoExperimentConditionLuxDevice_InfoDeviceTypeMaxResolution

[0218] Table 12 above shows the environment and device metadata of the test DB.

[0219] ClassFeaturesMeaningFile_InfoFileFormatFileNameDirectoryPathFileSizeBiometrics_InfoBiometricTypeNose patternRawDataImage or videoImageResolutionSubject_InfoBirthDateGenderBreedGuardian_InfoGuardianIDMiscellaneous_InfoOrderOfRepeatComment

[0220] Table 13 above shows the characteristic metadata of the test DB.

[0221] I.4. Lost Pet Rescue Service Based on Pet Individual Authentication Using Remote Biometric Information

[0222] By running performance tests, remote biometric information using verified pet animal nose patterns can be applied to rescue services for lost pets.

[0223] Appendix II. Use Case of a Remote Biometric Object Authentication Model for Pets

[0224] (This appendix does not constitute an essential part of this recommendation.)

[0225] Figure 12 is a diagram showing the architecture of a companion animal authentication platform.

[0226] The companion animal authentication platform architecture illustrated in Fig. 12, the companion animal authentication platform subscription and registration flow of Fig. 13 described below, and the companion animal authentication platform login and authentication flow of Fig. 14 follow the contents of the following recommendations.

[0227] II.1. Pet Object Authentication Platform Architecture Requirements

[0228] II.1.1. Overview

[0229] This scenario describes the use cases and applications of a pet authentication platform. Services requiring accurate pet identification implement remote biometrics functionality within the platform architecture and utilize the pet's unique ID and the owner's unique ID. An example of a pet authentication platform architecture is as follows:

[0230] II.1.2. Registration

[0231] To use certain features of the pet authentication platform, such as pet adoption services and pet insurance, owners must register their pet's information, including their personal information and biometric data. If duplicate pet information is provided, registration may be blocked to prevent abuse.

[0232] II.1.3. Authentication

[0233] The platform can establish an entity authentication process as a prerequisite for providing services, such as providing sensitive information about pets and their owners. When a pet owner requests to use a specific service, the platform searches for a pet authentication request. If the authentication result is successful, the owner can use the service. However, if the result is unsuccessful, the platform can deny the owner access to the service.

[0234] According to the above recommendation, in S1210, the service providing system can execute a platform for providing an entity authentication service. The user can send a platform execution request to the service providing system, and the service providing system can execute the platform in response to the user's execution request. In S1212, the service providing system can provide users (e.g., guardians) with membership registration and login functions, and can generate and manage a unique ID for each guardian. In S1213, the service providing system can build and manage a guardian database that stores the guardian's personal information and unique ID. When unique ID information for the guardian is generated, the service providing system can transmit the necessary metadata to the guardian database (1213).

[0235] At S1214, the service providing system can obtain pet information, including the pet's biometric information, from the guardian and register the obtained pet information. The service providing system can build and manage a pet database that stores the pet's biometric information, metadata, and unique ID. At S1215, the service providing system can transmit the metadata and biometric information regarding the pet to the pet database (1215).

[0236] In S1216, the service providing system can manage a unique ID, which is a common identifier that can recognize both the guardian and the pet, by transmitting it to each DB, which is logically and physically managed separately from the guardian ID and the pet's biometric information. In S1218, the service providing system can safely store the registered guardian and pet information in the guardian DB and the pet DB, or perform an authentication procedure based on the matching result. In S1220, the service providing system can perform a procedure for registering new companion animal information or matching (authenticating) it with existing registered information.

[0237] The service provision system according to the present disclosure can improve personal information protection and data management efficiency by dividing and storing information on guardians and companion animals in logically and physically separated DBs.

[0238] Figure 13 is a diagram showing the companion animal authentication platform subscription and registration flow.

[0239] A service provision system according to one embodiment provides a pet registration and management service and can perform a platform subscription and registration process according to FIG. 13.

[0240] In S1302, the service providing system can process membership registration and login procedures for pet guardians (users) based on user input on a predetermined user input interface. In S1304, the service providing system can obtain guardian information input based on user input on an input interface for providing a predetermined service.

[0241] At step S1306, the service providing system can obtain pet information input including biometric information. At step S1308, the service providing system can identify whether the obtained pet information is already registered information. At step S1310, the service providing system can confirm whether there is additional pet information to be registered in addition to the pet information already registered from the user. If it is identified that there is additional pet information to be registered, the service providing system can obtain additional pet information including biometric information about the pet to be added. If it is identified that there is already registered pet information and there is no additional pet information to be registered, the service providing system can terminate the process.

[0242] In S1312, if the entered pet information is identified as already registered pet information, the service providing system can match the registered pet information with the guardian information. Once the matching is complete, the service providing system can terminate the process according to FIG. 13.

[0243] Figure 14 is a diagram showing the login and authentication flow of the companion animal authentication platform.

[0244] In step S1402, the service providing system may process a platform login procedure using an ID / password. In step S1406, the service providing system may receive a request for a specific service from a user (e.g., a guardian). In one embodiment, this service may be a service requiring pet authentication or a service for displaying pet information.

[0245] At S1406, the service providing system can obtain a pet authentication request. When the pet authentication request is obtained, the service providing system can search the pet database (1406) and the guardian database (1408) containing biometric information, obtain the biometric information retrieved from the pet database (1406), and obtain a guardian ID from the guardian database (1408). At S1408, the service providing system can obtain the pet biometric information.

[0246] At S1410, the service providing system can check whether the pet biometric information obtained at S1408 matches the pet information already registered in the DB based on the guardian DI and the retrieved biometric information obtained from the companion animal DB (1406) and the guardian DB (1408), respectively. At S1412, if a match is confirmed, the service providing system can display the pet information and provide the service, and if a match is not confirmed, the process disclosed in FIG. 14 can be terminated.

[0247] In addition, according to one embodiment, although not shown in FIG. 14, the service providing system can determine whether there is a match by comparing the biometric raw data acquired from the client or the biometric information acquisition device with data in the corresponding companion animal database and guardian database. However, according to another example, the service providing system may perform matching with data in the companion animal database and guardian database based on both the biometric raw data acquired from the client or the biometric information acquisition device and the biometric feature information extracted from the biometric raw data. According to another example, the service providing system may perform matching with data in the companion animal database or guardian database using biometric feature information extracted from a ROI in the biometric raw data.

[0248] Figure 15 is a diagram showing the flow of a case of pet individual authentication failure.

[0249] If a guardian fails to authenticate their pet using a single biometric data more than N times, their access to the platform may be blocked. To re-register their pet on the platform after being blocked, the guardian must submit new biometric data to prove that the pet is identical to the one previously registered. The platform administrator may determine whether to allow re-registration of the pet based on the submitted biometric data.

[0250] For example, in S1502, the service providing system can obtain a user's request. In S1504, the service providing system can attempt authentication based on information provided by the user (e.g., biometric information of the companion animal). In S1506, the service providing system can check whether the authentication attempt was successful. In S1508, if the authentication attempt is identified as failed, the service providing system can check whether the current authentication attempt is N or more times. In S1510, the service providing system can provide a service for pet individual authentication if the authentication attempt result in S1506 is identified as successful. In S1512, the service providing system can block the service for individual authentication if the authentication attempt confirmed in S1508 is N or more times. However, if the authentication attempt confirmed in S1508 is less than N times, the service providing system can request the user to attempt authentication in S1504 again.

[0251] Figure 16 is a flowchart illustrating a method for a service providing system to specify ROI according to one embodiment.

[0252] In S1610, the service providing system can detect the edge of the nose region and the regions corresponding to the two nostrils from the biometric raw data in the form of an image or video acquired from a biometric information acquisition device. For example, the service providing system can first find the face region in the image by utilizing a traditional face detection algorithm such as Haar Cascade or a deep learning-based object detection model such as YOLO (You Only Look Once), SSD (Single Shot Multibox Detector), or Faster R-CNN. Then, the system can analyze the characteristic shape and color information of the nose within the region to identify the nose region, and analyze the dark regions that exist as a pair of nostrils to detect the two nostril regions. In particular, an artificial intelligence model or CNN model specialized in animal face detection (e.g., DogFaceNet, CatFaceNet, etc.) can be used to more accurately detect the face and nose region of a pet. Alternatively, the service providing system can simultaneously detect the nose region and nostrils by utilizing a deep learning-based object detection model.

[0253] In S1620, the service providing system can designate an ROI if the size of the area detected by the two nostrils and the height within the image exceed a preset threshold. For example, the service providing system can primarily designate an ROI if the size of the area detected by the nostrils is greater than a preset threshold size and the average height or each height of the two areas detected by the nostrils is located within a preset range on the entire biometric raw data image.

[0254] In S1630, if the service providing system identifies that an ROI has been designated for the pet's nose area, it can display a bounding box by specifying four location information based on the upper left corner of the nose area. For example, the service providing system can set the horizontal and vertical lengths based on the upper left corner of the nose area, thereby creating a rectangular bounding box that encloses the nose area.

[0255] At step S1640, the service providing system can measure the image resolution of the bounding box generated at step S1630. Specifically, the service providing system can calculate the horizontal and vertical resolutions by counting the number of pixels contained within the bounding box, and determine whether these values ​​are greater than the minimum resolution requirement of 256x256 pixels. However, the resolution is not limited to the above-described resolution.

[0256] In S1650, the service providing system can calculate the ratio of pixels corresponding to the actual nose region within a specified ROI. For example, the system can count pixels determined to be the nose region by analyzing the skin color or texture of the nose within the ROI, and compare this number to the total number of pixels in the ROI to calculate the ratio. If this ratio is 60% or greater, the ROI can be determined to contain sufficient nose region information. However, in another example, the service providing system can also use an artificial intelligence model or other algorithm to determine whether the nose or facial features of a companion animal within the ROI are of a level suitable for use in an individual authentication service.

[0257] In S1660, the service providing system can determine the ROI as the final nose region if both the resolution condition of step S1640 and the nose region ratio condition of step S1650 are satisfied.

[0258] FIG. 17 is a flowchart illustrating a method for a service providing system to specify ROI according to another embodiment.

[0259] In S1710, the service providing system can detect an area corresponding to the pet's face from the raw biometric data acquired from the biometric information acquisition device. In S1720, the service providing system can specify the location of a pre-learned nose area within the detected pet face area. For example, a landmark detection model based on a convolutional neural network (CNN) can be used to predict the locations of major parts of the face, such as the eyes, nose, and mouth, and thereby specify the location of the nose area. In S1730, if the nose area has been properly identified, the service providing system can generate a bounding box by specifying four pieces of location information based on the upper left corner of the nose area.

[0260] In step S1740, the service providing system can measure the image resolution of the bounding box generated in step S1730. Specifically, the system can count the number of pixels contained within the bounding box to calculate the horizontal and vertical resolutions, and determine whether these values ​​exceed the minimum resolution requirement of 256x256 pixels.

[0261] In S1750, the service providing system can calculate the ratio of pixels corresponding to the actual nose region within a specific ROI region. For example, the system can count pixels determined to be the nose region by analyzing the skin color or texture of the nose within the ROI, and compare this number with the total number of pixels in the ROI to calculate the ratio. If this ratio is 60% or greater, the ROI can be determined to contain sufficient nose region information. However, in another example, the service providing system can also determine whether the ROI contains a nose or facial features suitable for use in an individual authentication service by using other algorithms or methods, rather than the pixel ratio within the ROI region.

[0262] In step S1760, the service providing system can confirm the ROI as the final nose region if both the resolution condition of step S1740 and the nose region ratio condition of step S1750 are satisfied. In other words, the ROI contains sufficient resolution and valid nose region information, and thus can be utilized for additional processing such as pet recognition or biometric authentication.

[0263] FIG. 18 is a flowchart illustrating a method by which a service providing system according to one embodiment provides a biometric-based pet platform service.

[0264] At S1810, the service providing system can transmit a request to acquire biometric information from the client to the camera device. At S1820, the service providing system can acquire biometric information corresponding to the pet's noseprint from the camera device. At S1830, the service providing system can extract feature information from the biometric information acquired from the client. At S1840, the service providing system can measure the quality of the biometric information based on the extracted feature information. For example, the service providing system can calculate the proportion of valid feature information or measure the number based on factors such as brightness, focus, and movement.

[0265] In S1850, the service providing system can transmit data to the server to measure the similarity with previously stored biometric information if the quality is above a certain level. At this time, the similarity measurement can be performed by comparing valid feature information. In S1860, the service providing system can calculate the score of the similarity measurement result and determine that the same entity exists if it exceeds a certain threshold, and determine that the entity exists differently if it does not. In S1870, the service providing system can provide platform services if it is determined to be the same entity. If it is determined to be a different entity, a failure notification is sent and the entity can be retried. However, if the number of retrials exceeds a certain number, service access can be restricted.

[0266] FIG. 19 is a flowchart of a method for determining shooting environment information to determine the quality of a captured image of a companion animal or biometric information obtained from a captured image, according to an embodiment of the present invention.

[0267] In the S1910, the service providing system can perform brightness analysis of the shooting environment. For example, the service providing system can analyze the brightness of the shooting environment by measuring the Lux value through a biometric information acquisition device or by measuring the Pixel Intensity of the display. The Lux value is directly measured through the light sensor, and the Pixel Intensity represents the intensity of light received by the image sensor, and can be used to indirectly estimate brightness through analysis of the captured image.

[0268] In the S1920, the service providing system can analyze the movement of a subject. For example, the service providing system can analyze the movement of a subject by measuring the optical flow or Laplacian on the screen. Optical flow is a method for calculating a motion vector by tracking the movement of pixels between image frames, and the Laplacian is an operator that represents the amount of brightness change in an image, which can be used to detect the outline or movement of objects within the image.

[0269] In the S1930, the service providing system can perform shake analysis of the camera device. For example, the service providing system can analyze the camera device's shake by measuring the device's gyro sensor value (OIS) or measuring the difference image (DIS) from the device display. OIS (Optical Image Stabilization) is a technology that compensates for shake by detecting the movement of the sensor itself, while DIS (Digital Image Stabilization) is a technology that analyzes changes between captured image frames and compensates for shake through software.

[0270] Figure 20 is a flowchart illustrating a method for a service providing system according to one embodiment to store and transmit biometric information.

[0271] In S2010, the service providing system can receive raw data (e.g., raw biometric data) and feature data (biometric characteristic data) from a client. The client can be a user's device or an external system, with raw data referring to original data collected from sensors, and feature data referring to characteristic information extracted from the raw data. In S2020, the service providing system can measure the signal quality of the received raw data. For example, data quality can be assessed using the signal-to-noise ratio (SNR) or another appropriate metric.

[0272] In S2030, the service provider system can send a failure notification to the client without storing the raw data if it fails to meet a certain signal quality threshold. This may be a preemptive measure to prevent low-quality data from degrading system performance or causing errors. In S2040, the service provider system can separately store feature data extracted from the raw data. Because feature data is smaller and more efficient to process than raw data, it can be utilized in subsequent tasks such as authentication and analysis.

[0273] FIG. 21 is a diagram illustrating a method by which a service providing system according to one embodiment performs DB separation and access.

[0274] In S2110, the service providing system can receive raw data and feature data from the client. For example, the service providing system can obtain raw data (e.g., raw biometric data), such as photos or videos of a pet taken from an app on a user's smartphone (e.g., a biometric information acquisition device or biometric information capture device), and feature data (e.g., biometric feature information) containing the pet's feature information extracted from the data, and transmit the obtained raw data and feature data to the guardian database.

[0275] In S2120, the service provider system can measure the signal quality of the received raw data. For example, the quality of the biological raw data can be assessed using the signal-to-noise ratio (SNR) or other quality assessment metrics for raw data quality assessment. For example, based on the quality assessment results, the service provider system can transmit raw data that satisfies a predetermined quality level to the companion animal database.

[0276] In S2130, the service providing system may transmit a failure notification to the client without storing the raw data if the raw data obtained from the biometric information acquisition device or the client does not exceed a specific signal quality threshold.

[0277] In addition, although not illustrated in FIG. 21, according to one embodiment, the client transmits the acquired raw biometric data and the biometric characteristic information acquired from the raw biometric data to the server, and the server can determine the quality of the raw biometric data transmitted from the client. If the server determines that the quality of the raw biometric data is below a threshold quality level, the server may not store the raw biometric data in the companion animal database, but may instead store the raw biometric data or transmit an authentication failure notification to the client. However, if the server determines that the quality of the raw biometric data transmitted from the client is above a threshold quality level, the server may store biometric information including at least one of the raw biometric data or the biometric characteristic information in the companion animal database.

[0278] In S2140, the service provider system can store received data in the guardian database and pet database. For example, the service provider system can store and manage data in the guardian database and pet database by linking the guardian's unique number and the pet's unique number.

[0279] For example, a service providing system or server may allow access only to the pet database when an authentication attempt request from a client or other device is identified. When processing a pet authentication request, the service providing system may attempt authentication solely using biometric information stored in the pet database. However, if the service providing system identifies a missing person report or consent to access personal information from the guardian, the service providing system may use the unique number of the authenticated pet to access the guardian database and retrieve the guardian's personal information (e.g., contact information) associated with the pet.

[0280] More specifically, the server can build, store, and manage a pet database and a guardian database. The server manages the databases by linking the guardian's unique number with the pet's unique number. For example, the guardian database can store the guardian's unique number and the pet's unique number (this may require a common identifier that can identify both the guardian and the pet), and the pet database can store the pet's biometric information linked to the guardian's unique number. However, the service providing system can prevent the leakage of the guardian's personal information by logically and physically separating and storing the guardian's unique number (e.g., guardian ID) and the pet's biometric information.

[0281] For example, the server according to the present disclosure secures personal information exposure and security by physically and logically separating the companion animal database and the guardian database, but when an event such as the guardian's consent or a missing person's report is identified, access to the guardian database matching the unique number of the pet that is exceptionally authenticated can be permitted, and personal information, etc. can be retrieved from the guardian database at the user's request.

[0282] Figure 22 is a flowchart illustrating a method for registering biometric information for operating a biometric-based pet platform by a service providing system according to one embodiment.

[0283] In S2210, the service providing system can transmit a request to acquire biometric information from a client (e.g., a user's smartphone app) to the photographing device. For example, if a user inputs a "Register Pet Inscription" button through the user interface, the request can be transmitted to the photographing device. In S2220, the service providing system can acquire biometric information corresponding to the pet's inscription from the photographing device.

[0284] In S2230, the service provision system can extract feature information (facial features, nose pattern features) from biometric information acquired from a client. For example, image processing algorithms can be used to extract and digitize features such as unique patterns, ridges, and branch points from a fingerprint image.

[0285] In S2240, the service providing system can transmit data to the server when a certain number of extracted biometric data has accumulated. For example, the client can acquire 10 fingerprint images in batches and transmit them to the server. However, in another example, the service providing system can also immediately transmit fingerprint images acquired in real time from the client to the server. Furthermore, the client can only transmit at least one of the biometric raw data or feature information to the server, and quality checks on at least one of the biometric raw data or feature information can be performed solely on the server.

[0286] In the S2250, the service provision system can measure the quality of the biometric information transmitted from the server. For example, the quality score can be calculated by calculating the percentage of valid feature information based on factors such as brightness, focus, and movement, or by measuring the number of valid feature information.

[0287] At step S2260, if the service provider system determines that the quality score exceeds a certain threshold, the service provider system can store the corresponding biometric information in the companion animal database. At step S2270, the service provider system repeats the process from step S2210 until two or more biometric information items are stored. If fewer than two items are stored, the process can be retried from step S2210.

[0288] FIG. 23 is a flowchart illustrating a method for registering biometric information for operating a biometric-based pet platform by a service providing system according to another embodiment.

[0289] In S2310, the service providing system can transmit a request to acquire biometric information from the client to the photographing device. In S2320, the service providing system can acquire biometric information corresponding to the pet's noseprint from the photographing device. In S2330, the service providing system can extract feature information from the biometric information acquired from the client and calculate a quality score. For example, an image processing algorithm can be used to extract features such as unique patterns, ridges, and branch points from the raw biometric data, and the quality score can be calculated by measuring the proportion or number of valid feature information based on factors such as brightness, focus, and movement.

[0290] In S2340, the service provider system can repeat the biometric raw data acquisition process until a certain number of feature information with a quality score above a certain level has been accumulated. For example, if the quality score is low or the number of feature information is insufficient, the system can prompt the user to retake the image or request additional image acquisition.

[0291] At S2350, if a sufficient number of high-quality feature information is secured, the service providing system can store the extracted feature information in the companion animal database or transmit it from the client to the server. In one embodiment, quality inspection or measurement may be performed on the client, and the server may only store feature information or data with a quality score above a certain level. At S2360, if the number of biometric information pieces that have passed the quality level and have been stored is less than two, the service providing system may retry from S2310. That is, if necessary to secure at least two pieces of valid biometric information, the service providing system may request the user to take additional photographs and repeat the data acquisition process.

[0292] FIG. 24 is a flowchart illustrating a method for registering biometric information for operating a biometric-based pet platform by a service providing system according to another embodiment.

[0293] Referring to FIG. 24 according to an embodiment, a process is illustrated in which quality verification of biometric raw data and feature information is performed by both a client (performing a pre-inspection) and a server (performing a detailed inspection). In S2410, the service providing system may transmit a request for biometric information acquisition from the client to the photographing device.

[0294] In S2420, the service providing system can acquire biometric information corresponding to the pet's noseprint from the photographing device. In S2430, the service providing system can extract feature information from the biometric raw data acquired from the client and calculate a quality score for the biometric raw data or feature information. For example, an image processing algorithm can be used to extract features such as unique patterns, ridges, and branch points from the noseprint image, and the quality score can be calculated by measuring the proportion or number of valid feature information based on factors such as brightness, focus, and movement.

[0295] In S2440, the service providing system can transmit the feature information and original information to the server when a certain number of feature information with a quality score above a certain level has accumulated. The S2450 service providing system uses the transmitted feature information and original information to recalculate the quality score on the server and verify that it is above a certain level. According to one embodiment, the quality score calculation method used by the server and client can be differentiated. For example, the client can perform a quick pre-check, while the server can perform a more precise check.

[0296] At S2460, the service provider system stores biometric information in the companion animal database if the quality score exceeds a certain threshold during the server verification process. At S2470, the service provider system repeats the process from S2410 until two or more biometric information items are stored. If fewer than two items are stored, the process can be retried from S2410.

[0297] FIG. 25 is a flowchart illustrating a method for determining whether an object is the same or different through biometric information matching by having an electronic device and a server interconnect with each other according to an embodiment.

[0298] In one embodiment, the electronic device may correspond to a biometric information acquisition device or client device. In S2502, the electronic device (1000) may acquire multiple biometric information pieces for a single object. For example, the electronic device may capture a pet's face from multiple angles or capture multiple parts of a nose to collect various biometric information pieces.

[0299] In S2504, the server (2000) can store multiple biometric information items that satisfy preset quality conditions. The quality conditions may include various factors such as brightness, resolution, and focus, and information that falls below the standards may not be stored or may be processed separately.

[0300] In S2506, the electronic device (1000) may transmit a plurality of authentication biometric information including a plurality of acquired biometric information to the server. According to one embodiment, the electronic device (1000) may also transmit at least one of a plurality of raw biometric data and feature information extracted from the raw biometric data to the server. In S2508, the server (2000) may generate a plurality of registration biometric information of a specific individual to be compared among the plurality of registration biometric information. In other words, registered information of the same individual as the individual attempting authentication may be retrieved and prepared for comparison.

[0301] In S2510, the server (2000) can calculate a comparison score by comparing multiple authentication biometric information with multiple registration biometric information one-to-one without repetition. For example, each authentication biometric information can be compared with all registration biometric information to calculate a similarity score, and the highest score can be determined as the comparison score for the corresponding authentication attempt.

[0302] In S2512, the server (2000) can determine whether the authentication biometric information transmitted from the electronic device and the registration biometric information stored on the server are the same entity based on the one-to-one comparison scores. For example, if the average or maximum value of the comparison scores exceeds a certain threshold, the entity can be authenticated as the same entity, and otherwise, the entities can be determined to be different entities.

[0303] At S2514, the server (2000) may transmit the result of determining whether the entity is the same as the above to the electronic device. At S2516, the electronic device (1000) may output the authentication result or authentication content related to the authentication result. For example, if authentication is successful, a service use screen may be displayed with the message "Authentication has been completed." If authentication fails, a "Authentication failed" message may be displayed along with instructions for a retry or error.

[0304] FIG. 26 is a block diagram of an electronic device or service system according to one embodiment.

[0305] FIG. 27 is a block diagram of an electronic device or service system according to another embodiment.

[0306] According to one embodiment, the electronic device (1000) may correspond to one of the client device, biometric information acquisition device, or server described above. The block diagram of the drawing illustrated in FIG. 26 may correspond to a block diagram of a service providing system.

[0307] According to one embodiment, the electronic device (1000) may include a network interface (1500), a memory (1700), and a processor (1300). However, not all of the illustrated components are essential components. The electronic device (1000) may be implemented with more components than the illustrated components, or may be implemented with fewer components.

[0308] For example, as illustrated in FIG. 27, an electronic device (1000) according to one embodiment may further include a user input interface (1100), an output unit (1200), a sensing unit (1400), and an A / V input unit (1600) in addition to a processor (1300), a memory (1700), and a network interface (1500).

[0309] The user input interface (1100) refers to a means for a user to input a sequence for controlling the electronic device (1000). For example, the user input interface (1100) may include, but is not limited to, a key pad, a dome switch, a touch pad (contact electrostatic capacitance type, pressure resistive film type, infrared detection type, surface ultrasonic conduction type, integral tension measurement type, piezo effect type, etc.), a jog wheel, a jog switch, etc. The user input interface (1100) may receive a user's input sequence for a screen output on a display of the electronic device (1000). In addition, the user input interface (1100) may also receive a user's touch input touching the display or a key input through a graphical user interface on the display.

[0310] The output unit (1200) can output an audio signal, a video signal, or a vibration signal, and the output unit (1200) can include a display (1210), an audio output unit (1220), and a vibration motor (1230). The display (1210) includes a screen for displaying and outputting information processed in the electronic device (1000). The audio output unit (1220) outputs audio data received from the network interface (1500) or stored in the memory (1700). In addition, the audio output unit (1220) outputs an audio signal related to a function performed in the electronic device (1000). The vibration motor (1230) can output a vibration signal.

[0311] The processor (1300) typically controls the overall operation of the electronic device (1000). For example, the processor (1300) may control the user input unit (1100), the output unit (1200), the sensing unit (1400), the network interface (1500), the A / V input unit (1600), etc., by executing programs stored in the memory (1700). In addition, the processor (1300) may perform at least one of the operations of the service providing system described in FIGS. 1 to 25 by executing programs stored in the memory (1700).

[0312] According to one embodiment, the service providing system or processor (1300) may control the operation of the service providing system or devices included in the service providing system to provide an individual authentication service for a target companion animal. For example, the processor (1300) may obtain raw biometric data for the target companion animal from a biometric information obtaining device, determine raw data quality of the raw biometric data, extract biometric characteristic information from the raw biometric data based on the determined raw data quality, and authenticate whether the companion animal is the same individual as the individual specified in the biometric information stored in the pre-stored database based on the extracted biometric characteristic information and the biometric information in the pre-stored database.

[0313] In one embodiment, the processor (1300) may preprocess the acquired raw biometric data by applying an analog or digital filter to reduce noise, and may also determine the raw data quality of the preprocessed raw biometric data.

[0314] According to one embodiment, the step of determining raw data quality performed by the processor (1300) may include the step of determining whether an ROI region identified from the biometric raw data satisfies a preset resolution condition and the step of determining whether an ROI region identified from the biometric raw data satisfies a preset ROI quality condition.

[0315] According to one embodiment, the step of determining the raw data quality performed by the processor (1300) may include the steps of identifying a ROI region related to the nose or face region of the companion animal from the biometric raw data, identifying whether an image resolution of the identified ROI region is 256X256 pixels or more, confirming whether a ratio of the number of pixels identified as the nose or face region of the companion animal within the ROI region to the total number of pixels within the biometric raw data is greater than or equal to a threshold ratio, and determining that the raw data quality of the biometric raw data satisfies a raw data quality level from which the biometric feature information is to be extracted when the image resolution of the ROI region is 256X256 pixels or more and the ratio of the number of pixels identified as the nose or face region of the companion animal within the ROI region to the total number of pixels within the captured image is identified as greater than or equal to a threshold ratio.

[0316] Specifically, the processor (1300) can obtain a user's input touching the screen of the electronic device (1000) by controlling the user input unit. According to one embodiment, the processor (1300) can also control a microphone to obtain the user's voice. The sensing unit (1400) can detect the state of the electronic device (1000) or the state around the electronic device (1000) and transmit the detected information to the processor (1300). The sensing unit (1400) may include at least one of a magnetic sensor (1410), an acceleration sensor (1420), a temperature / humidity sensor (1430), an infrared sensor (1440), a gyroscope sensor (1450), a position sensor (e.g., GPS) (1460), a pressure sensor (1470), a proximity sensor (1480), and an RGB sensor (illuminance sensor) (1490), but is not limited thereto. Since the function of each sensor can be intuitively inferred from its name by those skilled in the art, a detailed description thereof will be omitted.

[0317] The network interface (1500) may include one or more components that enable the electronic device (1000) to communicate with other devices (not shown) and a server (2000). The other devices (not shown) may be computing devices such as the electronic device (1000) or sensing devices, but are not limited thereto. For example, the network interface (1500) may include a wireless communication interface (1510), a wired communication interface (1520), and a mobile communication unit (530).

[0318] The wireless communication interface (1510) may include, but is not limited to, a short-range wireless communication unit, a Bluetooth communication unit, a near field communication unit, a WLAN (Wi-Fi) communication unit, a Zigbee communication unit, an infrared (IrDA, infrared Data Association) communication unit, a WFD (Wi-Fi Direct) communication unit, etc. The wired communication interface (1520) may connect a server (2000) or an electronic device (1000) via a wire.

[0319] The mobile communication unit (1530) transmits and receives wireless signals with at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signals may include various types of data according to transmission and reception of voice signals, video call signals, or text / multimedia messages. According to one embodiment, the network interface (1500) may perform transmission and reception of biometric raw data, biometric information, biometric characteristic information, quality measurement results, and authentication results between each device in the service providing system. The A / V (Audio / Video) input unit (1600) is for inputting audio signals or video signals, and may include a camera (1610) and a microphone (1620), etc. The camera (1610) may obtain image frames such as still images or moving images through an image sensor in a video call mode or a shooting mode. The image captured through the image sensor may be processed through a processor (1300) or a separate image processing unit (not shown).

[0320] The microphone (1620) receives an external acoustic signal and processes it into electrical voice data. For example, the microphone (1620) can receive an acoustic signal from an external device or a user. The microphone (1620) can receive a user's voice input. The microphone (1620) can utilize various noise removal algorithms to remove noise generated during the process of receiving an external acoustic signal.

[0321] The memory (1700) can store programs for processing and controlling the processor (1300), and can also store data input to or output from the electronic device (1000). In addition, the memory (1700) can store images or videos acquired by the electronic device (1000) from an external device. According to one embodiment, the memory (1700) may be a database stored in a server device. For example, the memory (1700) may include a database storing the aforementioned companion animal information and a database storing guardian information.

[0322] The memory (1700) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk.

[0323] The programs stored in the memory (1700) can be classified into a plurality of modules according to their functions, for example, a UI module (1710), a touch screen module (1720), a notification module (1730), etc. The touch screen module (1720) can detect a user's touch gesture on the touch screen and transmit information about the touch gesture to the processor (1300). The touch screen module (1720) according to some embodiments can recognize and analyze a touch code. The touch screen module (1720) may also be configured as separate hardware including a controller.

[0324] The notification module (1730) can generate a signal to notify the occurrence of an event in the electronic device (1000). Examples of events occurring in the electronic device (1000) include reception of a call signal, reception of a message, input of a key signal, and schedule notification. The notification module (1730) can output a notification signal in the form of a video signal through the display unit (1210), output a notification signal in the form of an audio signal through the sound output unit (1220), or output a notification signal in the form of a vibration signal through the vibration motor (1230).

[0325] Figure 28 is a flowchart of a method in which a service providing system according to one embodiment provides an individual authentication service for a target companion animal.

[0326] In S2801, the service providing system can obtain raw biometric data of the target companion animal from a biometric information acquisition device. In S2820, the service providing system can determine the raw data quality of the raw biometric data. In S2830, the service providing system can extract biometric characteristic information from the raw biometric data based on the determined raw data quality. In S2840, the service providing system can authenticate whether the companion animal is the same individual as the individual specified in the biometric information stored in the pre-stored database based on the extracted biometric characteristic information and the biometric information in the pre-stored database. In S2850, the service providing system can output an authentication result regarding whether the companion animal is the same individual.

[0327] The method according to one embodiment may be implemented in the form of program instructions that can be executed by various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, either singly or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present disclosure, or may be known and usable by those skilled in the art of computer software.

[0328] In addition, a computer program device including a recording medium storing a program for performing another method according to the above embodiment may be provided. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and perform program instructions such as ROMs, RAMs, flash memories, and the like. Examples of the program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc.

[0329] Although the embodiments of the present disclosure have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concepts of the present disclosure defined in the following claims also fall within the scope of the present disclosure.

Claims

1. In a method in which a service provision system provides an individual authentication service for a target companion animal, A step of acquiring raw biometric data on the target companion animal from a biometric information acquisition device; A step of determining raw data quality of the above biometric raw data; A step of extracting biometric characteristic information from the biometric raw data based on the determined raw data quality; A step of authenticating whether the companion animal is the same individual as the individual specified in the biometric information stored in the pre-stored database based on the extracted biometric characteristic information and the biometric information in the pre-stored database; and A method comprising: a step of outputting an authentication result as to whether the above objects are the same; 2. In the first paragraph, the step of determining the raw data quality is A step of determining whether the ROI area identified from the above biometric raw data satisfies a preset resolution condition; and A method comprising: a step of determining whether a ROI region identified from the above biometric raw data satisfies a preset ROI quality condition; 3. In the first paragraph, the step of determining the raw data quality is A step of identifying a ROI area related to the nose or face area of ​​the companion animal from the above biometric raw data; A step of identifying whether the image resolution of the identified ROI area is 256X256 pixels or more; A step of checking whether the ratio of the number of pixels identified as the nose or face region of the companion animal within the ROI area to the total number of pixels within the biometric raw data is greater than or equal to a threshold ratio; and A method comprising: a step of determining that the raw data quality of the biometric raw data satisfies a raw data quality level from which the biometric characteristic information is to be extracted, when the image resolution of the ROI area is 256X256 pixels or more, and the ratio of the number of pixels identified as the nose or face area of ​​the companion animal within the ROI area to the total number of pixels within the captured image is greater than a threshold ratio; 4. In a service provision system that provides individual authentication services for target companion animals, network interface; Memory that stores one or more instructions; and At least one processor executing one or more of the instructions; The at least one processor executes the one or more instructions, Obtaining raw biometric data on the target companion animal from a biometric information acquisition device, Determining the raw data quality of the above biometric raw data, Extracting biometric characteristic information from the biometric raw data based on the determined raw data quality, Based on the extracted biometric characteristic information and the biometric information in the pre-stored database, it is authenticated whether the companion animal is the same individual as the individual specified in the biometric information stored in the pre-stored database, A service providing system that outputs an authentication result as to whether the above is the same entity.

5. In a method in which a service provision system provides an individual authentication service for a target companion animal, A step of acquiring raw biometric data on the target companion animal from a biometric information acquisition device; A step of determining raw data quality of the above biometric raw data; A step of extracting biometric characteristic information from the biometric raw data based on the determined raw data quality; A step of authenticating whether the companion animal is the same individual as the individual specified in the biometric information stored in the pre-stored database based on the extracted biometric characteristic information and the biometric information in the pre-stored database; and A computer-readable recording medium having recorded thereon a program for executing a method on a computer, comprising: a step of outputting an authentication result as to whether the object is the same as the above;

Images