Method and electronic device for detecting capture angle of image for acquiring biometric information of animal

Abstract

An embodiment of the present invention provides a method and an electronic device capable of detecting the capture angle from an image captured for biometric recognition of an animal. A method for detecting the capture angle of an image for acquiring biometric information of an animal according to an embodiment of the present invention comprises the steps of: acquiring an image including biometric information of an animal; detecting a plurality of feature points from the biometric information; extracting a spatial correlation of the plurality of feature points; and determining a rotation direction of the biometric information according to the spatial correlation.

Description

Method and electronic device for detecting the shooting angle of an image to acquire biological information of an animal

[0001] The present invention relates to a method and an electronic device for detecting the shooting angle of an image for acquiring biological information of an animal.

[0002] In modern society, there is a growing demand for companion animals that can live alongside humans and provide emotional support. To provide various supplementary services, such as life cycle management and health care, there is an increasing need to manage information about companion animals by creating databases. This requires individual identification information, and specific objects that can be used can be defined for each type of animal. For example, similar to human fingerprints, a dog's nose print (the shape of the nose wrinkles) is known to differ from individual to individual, and it is generally known that once a dog reaches adulthood (at six months of age), these characteristics do not change for the remainder of its life. Therefore, in the case of dogs, nose prints can be utilized as a means of identification.

[0003] When using nose prints as a biometric recognition method, the likelihood that images captured by a typical user are suitable for biometric recognition is low. Since users cannot determine which images are suitable for recognition and animals have a habit of turning their heads away without recognizing the act of being photographed, there is a problem in that it is difficult to obtain images of a quality suitable for biometric recognition if animals are photographed in the same way a user photographs a person. In particular, when performing biometric recognition via nose prints, a frontal photograph of the nose is required; however, it is difficult to capture a frontal image of a dog because of its habit of frequently turning its head.

[0004] Therefore, it is necessary to automatically filter out non-frontal images during the shooting process for biometric recognition, and to this end, it must be determined whether the nose in the currently captured image is facing forward.

[0005] Embodiments of the present invention provide a method and an electronic device capable of detecting a shooting angle in an image captured for animal biometric recognition.

[0006] A method for detecting the shooting angle of an image for acquiring biological information of an animal according to an embodiment of the present invention comprises: acquiring an image of the biological information of an animal; detecting a plurality of feature points in the biological information; extracting a spatial correlation of the plurality of feature points; and determining the rotation direction of the biological information according to the spatial correlation.

[0007] In an embodiment of the present invention, the plurality of feature points are feature points constituting the left nostril area, the right nostril area, and the philtrum area.

[0008] In an embodiment of the present invention, the step of extracting spatial correlations of the left nostril region, the right nostril region, and the philtrum region includes: a step of setting a first judgment element based on the left nostril region and the right nostril; and a step of setting a second judgment element based on the philtrum region. The step of determining the direction of rotation of the nose may include: a step of calculating the spatial correlation between the first judgment element and the second judgment element; and a step of determining the direction of rotation of the nose according to the spatial correlation.

[0009] In an embodiment of the present invention, the first judgment element may be composed of a first circle passing through the center of gravity of the left nostril area and the center of gravity of the right nostril on a virtual sphere corresponding to the nose.

[0010] In an embodiment of the present invention, the second judgment element may be composed of a second circle passing through both endpoints of the philtrum area on a virtual sphere corresponding to the nose.

[0011] In an embodiment of the present invention, the step of calculating the spatial correlation between the first judgment element and the second judgment element may include: setting a straight line extending from the center point of the sphere to the intersection point of the first circle and the second circle as the X-axis; setting a straight line extending from the center point of the sphere to the second circle and perpendicular to the X-axis as the Z-axis; and setting a straight line perpendicular to the X-axis and the Z-axis from the center point of the sphere as the Y-axis.

[0012] In an embodiment of the present invention, the rotation angle of the nose can be determined based on the directions of the X-axis, the Y-axis, and the Z-axis.

[0013] In an embodiment of the present invention, the step of determining the rotation angle of the nose may include the step of determining the roll, yaw, and pitch rotation angles with respect to the X-axis, the Y-axis, and the Z-axis.

[0014] An electronic device according to the present invention comprises a memory; and a processor electrically connected to the memory. The processor acquires an image containing biological information of an animal, detects a plurality of feature points in the biological information, extracts spatial correlations of the plurality of feature points, and determines the rotation direction of the biological information according to the spatial correlations.

[0015] According to an embodiment of the present invention, the shooting angle can be detected in an image captured for the biometric recognition of an animal.

[0016] Figure 1 illustrates the image acquisition process for animal biometric recognition.

[0017] FIG. 2 is a block diagram showing the configuration of an electronic device according to the present invention.

[0018] FIG. 3 is a flowchart illustrating a method for detecting the shooting angle of an image to acquire biological information of an animal according to the present invention.

[0019] FIGS. 4 to 11 illustrate an example of a process for detecting the shooting angle of an image according to the present invention.

[0020] FIGS. 12 and FIGS. 13 illustrate other examples of the process of detecting the shooting angle of an image in an image.

[0021] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. The present invention may be embodied in various different forms and is not limited to the embodiments described herein.

[0022] To clearly explain the present invention, parts unrelated to the explanation have been omitted, and the same reference numerals are used for identical or similar components throughout the specification.

[0023] In addition, in various embodiments, components having the same configuration are described using the same reference numerals only in the representative embodiment, and in other embodiments, only configurations different from the representative embodiment are described.

[0024] Throughout the specification, when a part is described as being "connected (or combined)" with another part, this includes not only cases where they are "directly connected (or combined)" but also cases where they are "indirectly connected (or combined)" with other members in between. Furthermore, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0025] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0026] Hereinafter, a method and an electronic device for detecting the shooting angle of an image for acquiring biological information of an animal according to the present invention will be described. FIG. 1 illustrates an image acquisition process for biological recognition of an animal. FIG. 1 illustrates a process for acquiring a nose print image suitable for biological recognition when a dog's nose print is used as biological information.

[0027] Referring to FIG. 1, an image including an animal's face is captured (S110). In the captured image, a region of interest corresponding to the animal's nose area is identified (S120), and whether the image of the region of interest has quality suitable for biometric recognition is examined (S130). Here, the quality evaluation criteria may include the brightness, size, clarity, and shooting angle of the region of interest. When using a nose print as a biometric recognition means, it is required to acquire a frontal image of the nose. Alternatively, if the nose is captured at a tilted angle, it is necessary to determine the degree of tilt at which the image was captured in order to extract nose print information from the image of the nose. Accordingly, the present invention provides a method for detecting the shooting angle of the nose when using a nose print as biometric information.

[0028] FIG. 2 is a block diagram showing the configuration of an electronic device (100) according to the present invention. The image capturing and shooting angle determination method according to the present invention may be executed by an application installed on a device such as a smartphone or by a server providing a service through an application. Here, the application includes an application that operates on a mobile device such as a smartphone or a PC (Personal Computer) and a web-based application.

[0029] The electronic device (100) according to the present invention may correspond to a mobile device such as a smartphone or a server. The electronic device (100) according to the present invention includes a memory (150) and a processor (110) electrically connected to the memory (150). Additionally, the electronic device (100) may include a communication module (120) for transmitting or receiving data with another device, a display (130) for visually outputting information, and an input / output interface (140) for connecting with another device or for inputting and outputting information.

[0030] The processor (110) can perform operations and data processing for the operation of the electronic device (100), and control each module of the electronic device (100). The processor (110) can execute one or more software programs stored in memory (150). The processor (110) may include a general-purpose processor (e.g., CPU) that runs an operating system managing the overall operation of the electronic device (100). Additionally, the processor (110) may include a dedicated processor (e.g., GPU, NPU) for specific computation processing. The processor (110) may include one or more processing circuits. The method of operation of the electronic device (100) described below may be executed by the processor (110).

[0031] The communication module (120) provides an environment in which the electronic device (100) can communicate with an external entity (e.g., an authentication server, a base station, an IoT device, a user device). The communication module (120) may include a device for performing wired or wireless communication. The communication module (120) may provide data received from an external entity to the processor (110). The communication module (120) may convert the data provided from the processor (110) and transmit it to the external entity.

[0032] The display (130) is a device for outputting visual information and may include a panel and a control circuit. The memory (150) may store programs, such as an operating system and an application for the operation of the electronic device (100), and data used during the execution of the program. The memory (150) may include volatile memory (e.g., DRAM) and non-volatile memory (e.g., flash memory). Additionally, the memory (150) may include a mass storage device for organizing a database.

[0033] FIG. 3 is a flowchart illustrating a method for detecting the shooting angle of an image for acquiring biological information of an animal according to the present invention. The process of detecting the shooting angle of an image described below can be executed by a processor (110) of an electronic device (100).

[0034] A method for detecting the shooting angle of an image for acquiring biological information of an animal according to the present invention comprises the steps of: acquiring an image including the nose of an animal (S310); detecting a left nostril area (LH), a right nostril area (RH), and a philtrum area (PH) in the nose (S320); extracting a spatial correlation between the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH) (S330); and determining the direction of rotation of the nose according to the spatial correlation between the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH) (S340).

[0035] In step S310, the processor (110) acquires an image containing biological information of an animal. In the present invention, the biological information includes the animal's nose. In addition, the biological information may include at least one of the animal's entire body, face, eyes, ears, and mouth. An image for biological recognition of the animal is captured, and an image of the nose region for nose print recognition may be extracted from the image. As a quality inspection process for the extracted image of the nose region, the shooting angle detection according to the present invention may be applied. The image may be an image captured by a camera embedded in the electronic device (100), or an image captured by another device and then transmitted to the electronic device (100).

[0036] In step S320, the processor (110) detects a plurality of feature points in the biological information. The plurality of feature points are feature points that constitute the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH). The processor (110) can detect the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH) in the image by inputting the nose image into a pre-trained object detection model. The processor (110) can set the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH) by connecting coordinates that define the borders of the left and right nostrils and the philtrum of the nose in the image. As illustrated in FIG. 4, the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH) can be detected in the nose of an animal.

[0037] In step S330, the processor (110) extracts spatial correlations of a plurality of feature points. The processor (110) may extract spatial correlations of the left nostril region (LH), the right nostril region (RH), and the philtrum region (PH). The step of extracting spatial correlations of a plurality of feature points (S330) includes the step of setting a first judgment element based on the left nostril region (LH) and the right nostril (RH), and the step of setting a second judgment element based on the philtrum region (PH).

[0038] The first judgment element consists of a first circle passing through the center of gravity (LP) of the left nostril area (LH) and the center of gravity (RP) of the right nostril area (RH) on a virtual sphere (SPH) corresponding to the nose. The second judgment element consists of a second circle passing through the two endpoints (PP1, PP2) of the philtrum area (PH) on a virtual sphere (SPH) corresponding to the nose.

[0039] First, the processor (110) can generate a virtual sphere (SPH) corresponding to the nose. The processor (110) can generate a virtual sphere (SPH) that is most similar to the area occupied by the nose in the image. The processor (110) can generate a plurality of candidate spheres similar to the nose in the image and generate a virtual sphere (SPH) that is most similar in shape to the nose in the image among them. As illustrated in FIG. 5, a virtual sphere (SPH) corresponding to the nose of an animal can be generated. Additionally, as illustrated in FIG. 6, the center point (CP) of the virtual sphere (SPH), the center of gravity (LP) of the left nostril area (LH), the center of gravity (RP) of the right nostril area (RH), and the two endpoints (PP1, PP2) of the philtrum area (PH) can be set.

[0040] The processor (110) can generate a first circle (C1) as a first decision element that is inscribed in the sphere (SPH) and passes through the center of gravity (LP) of the left nostril region (LH) and the center of gravity (RP) of the right nostril region (RH). The first circle (C1) is defined as an ellipse that intersects the sphere (SPH) and a plane formed by three points (CP, LP, RP). As illustrated in FIG. 7, a virtual first circle (C1) can be generated that is inscribed in the sphere (SPH) and simultaneously passes through the center of gravity (LP) of the left nostril region (LH) and the center of gravity (RP) of the right nostril region (RH).

[0041] The processor (110) can generate a second circle (C2) as a second judgment element that is inscribed in the sphere (SPH) and passes through the two endpoints (PP1, PP2) of the philtrum region (PH). The second circle (C2) is defined as an ellipse that intersects the sphere (SPH) and a plane formed by three points (CP, PP1, PP2). As illustrated in FIG. 8, a virtual second circle (C2) that is inscribed in the sphere (SPH) and simultaneously passes through the two endpoints (PP1, PP2) of the philtrum region (PH) can be generated.

[0042] In step S340, the processor (110) can determine the direction of rotation of the nose based on the spatial correlation of the left nostril area (LH), the right nostril area (RH), and the philtrum area (PH). The step of determining the direction of rotation of the nose (S340) may include the step of calculating the spatial correlation between a first judgment element and a second judgment element, and the step of determining the direction of rotation of the nose based on the spatial correlation.

[0043] The processor (110) can determine the rotation angle of the nose based on the shape of the first circle (C1) and the second circle (C2). The rotation angle of the nose can be detected using the shape of the first circle (C1) and the second circle (C2), which are virtual circles generated as in FIG. 8.

[0044] As an example, the step of calculating the spatial correlation between the first judgment element and the second judgment element includes the step of setting a straight line extending from the center point (CP) of the sphere (SPH) to the intersection point of the first circle (C1) and the second circle (C2) as the X-axis, the step of setting a straight line extending from the center point (CP) of the sphere (SPH) to the second circle (C2) and orthogonal to the X-axis as the Z-axis, and the step of setting a straight line extending from the center point (CP) of the sphere (SPH) and orthogonal to the X-axis and the Z-axis as the Y-axis.

[0045] As shown in FIG. 9, a straight line extending from the center point (CP) of the sphere (SPH) to the intersection point of the first circle (C1) and the second circle (C2) is set as the X-axis. Here, there are two intersection points of the first circle (C1) and the second circle (C2), and the X-axis can be set as the intersection point existing on a minor arc consisting of the center of gravity (LP) of the left nostril area (LH) and the center of gravity (RP) of the right nostril area (RH).

[0046] When the X-axis is set, as shown in FIG. 10, a straight line extending from the center point (CP) of the sphere (SPH) to the second circle (C2) and perpendicular to the X-axis is set as the Z-axis. A straight line extending toward the second circle (C2) while perpendicular to the X-axis becomes the Z-axis. Here, among the two Z-axis candidates perpendicular to the X-axis, the straight line pointing upward becomes the Z-axis.

[0047] Subsequently, as shown in FIG. 11, a straight line perpendicular to the X-axis and Z-axis from the center point (CP) of the sphere (SPH) is set as the Y-axis. Once the X-axis, Y-axis, and Z-axis are determined as in FIG. 11, the rotation angle of the nose can be determined based on the directions of the X-axis, Y-axis, and Z-axis. The step of determining the rotation angle of the nose involves determining the roll, yaw, and pitch rotation angles with respect to the X-axis, Y-axis, and Z-axis. For example, once the X-axis, Y-axis, and Z-axis directions toward which the nose faces are determined as in FIG. 11, the roll, yaw, and pitch rotation angles can be determined, respectively, according to the angles with respect to the reference X-axis, reference Y-axis, and reference Z-axis indicated by the dotted lines. Through a similar process, the X-axis, Y-axis, and Z-axis directions toward which the nose faces are determined as in FIG. 12 and FIG. 13, and accordingly, the roll, yaw, and pitch rotation angles can be determined, respectively.

[0048] The processor (110) can determine whether the captured image is a frontal image of the nose based on the calculated roll, yaw, and pitch rotation angles. For example, as shown in FIG. 12, if the roll, yaw, and pitch rotation angles are small, it can be determined that it is a frontal image. As shown in FIG. 11 and FIG. 13, if the roll, yaw, and pitch rotation angles are large, it can be determined that it is not a frontal image.

[0049] Alternatively, the processor (110) may include the calculated roll, yaw, and pitch rotation angles as additional information in the image containing the nose. The roll, yaw, and pitch rotation angles can be used as training data for biometric recognition using the nose in the future.

[0050] Although this embodiment has been described with a focus on detecting feature points of the nose and determining the rotation angle, multiple feature points can be detected in other biological information of animals, whether or not they include a nose, to extract spatial correlations between the feature points, and the rotation direction of the biological information can be determined according to the spatial correlations.

[0051] The embodiments and drawings attached to this specification merely clearly illustrate a part of the technical concept included in the present invention, and it is obvious that variations and specific embodiments that can be easily deduced by a person skilled in the art within the scope of the technical concept included in the specification and drawings of the present invention are all included within the scope of the rights of the present invention.

[0052] Accordingly, the scope of the present invention should not be limited to the described embodiments, and all things equivalent to or having equivalent variations to the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention.

Claims

1. A method for detecting the shooting angle of an image for acquiring biological information of an animal, Step of acquiring an animal's biological information image; A step of detecting a plurality of feature points in the above-mentioned bio-information image; A step of extracting spatial correlations of the plurality of feature points; and A method comprising the step of determining the rotation direction of the bio-information according to the spatial correlation above.

2. In Paragraph 1, A method in which the above plurality of feature points are feature points constituting the left nostril region, the right nostril region, and the philtrum region of the nose.

3. In Paragraph 2, The step of extracting spatial correlations of the above plurality of feature points is, A step of setting a first judgment element based on the above-mentioned left nostril area and the above-mentioned right nostril; and It includes the step of setting a second judgment element based on the above-mentioned philtrum area, and The step of determining the direction of rotation of the nose above is, A step of calculating the spatial correlation between the first judgment element and the second judgment element; and A method comprising the step of determining the direction of rotation of the nose according to the spatial correlation above.

4. In Paragraph 3, A method in which the above-mentioned first judgment element is composed of a first circle passing through the center of gravity of the left nostril region and the center of gravity of the right nostril on a virtual sphere corresponding to the nose.

5. In Paragraph 4, The above second judgment element is a method comprising a second circle passing through both endpoints of the philtrum area on the above sphere.

6. In Paragraph 5, The step of calculating the spatial correlation between the first judgment element and the second judgment element is: A step of setting a straight line extending from the center point of the sphere to the intersection of the first circle and the second circle as the X-axis; A step of setting a straight line extending from the center point of the sphere to the second circle and perpendicular to the X-axis as the Z-axis; and A method comprising the step of setting a straight line perpendicular to the X-axis and the Z-axis from the center point of the sphere as the Y-axis.

7. In electronic devices, Memory; and Includes a processor electrically connected to memory, The above processor is, Acquire images containing the animal's biological information, and Detecting multiple feature points in the above bio-information image, and Extracting the spatial correlation of the above multiple feature points, and An electronic device that determines the rotation direction of the bio-information according to the spatial correlation above.

8. In Paragraph 7, The above plurality of feature points are electronic devices that are feature points constituting the left nostril region, the right nostril region, and the philtrum region of the nose.

9. In Paragraph 8, The above processor is, A first judgment element is established based on the above-mentioned left nostril area and the above-mentioned right nostril, and A second judgment element based on the above-mentioned philtrum area is established, and Calculate the spatial correlation between the first judgment element and the second judgment element, and An electronic device that determines the direction of rotation of the nose according to the spatial correlation above.

10. In Paragraph 9, The above-mentioned first judgment element is an electronic device comprising a first circle passing through the center of gravity of the left nostril region and the center of gravity of the right nostril on a virtual sphere corresponding to the nose.

11. In Paragraph 10, The above second judgment element is an electronic device composed of a second circle passing through both endpoints of the philtrum area on the above sphere.

12. In Paragraph 11, The above processor is, A straight line extending from the center point of the sphere to the intersection of the first circle and the second circle is set as the X-axis, and A straight line extending from the center point of the sphere to the second circle and perpendicular to the X-axis is set as the Z-axis, and An electronic device that sets a straight line perpendicular to the X-axis and the Z-axis from the center point of the sphere as the Y-axis.

Images