JP2000137810A - Individual identifier - Google Patents

Abstract

PROBLEM TO BE SOLVED: To decrease the number of dictionaries to be collated with and to increase the processing speed with respect to an individual identifier. SOLUTION: An animal dictionary storing part 60 stores the dictionaries which show the information on the biological features corresponding to every ID. Every dictionary includes the weight information on a relevant animal and also the information on a person who is uniquely related to the animal. A dictionary selection part 30 uses the animal weight and limits an animal dictionary to be used at the time of collation based on the weight of an individual to be identified. A dictionary selection part 40 using the ID of a manager identifies a person and limits an animal dictionary to be used at the time of collation based on the result of identification of the person. An animal individual identification part 50 uses the animal dictionaries of the part 60 which are limited at both parts 30 and 40 and identifies the individual to be identified.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an individual identification apparatus for identifying individuals based on biological characteristics, and more particularly, to an individual identification device.
For example, the present invention relates to an animal individual identification device for registering data for individual identification of animals and performing collation in an organization requiring individual management of animals such as (race) horses and (pastoral) cows.

[0002]

2. Description of the Related Art Individual identification of thoroughbreds at a racetrack, auction field, or a breeding ranch is carried out under the initiative of a pedigree control agency. The current method of identifying individuals in Japan is based on coat color, vitiligo on the limbs, vitiligo on the head, and curl. In the world, there are other methods based on blood type, branding, tattooing, etc. Reference: "Knowledge of Horses", II-
3. How to identify a horse, P. 153-P. 154).

[0003] In the case of individual identification of cattle, a method using identification nameplates such as collars and ear tags and branding and tattooing has been adopted in general ranches.

[0004] As an individual identification method of an animal that has recently attracted attention, there is a technique using an MC (Micro Chip). This is a chip with a built-in microminiature integrated circuit enclosed in a glass tube, which is implanted in the body of an animal with an injector such as a syringe.In the case of identification, the embedded signal is traced by a non-contact detector to trace the output signal. This is used as information for individual identification.

[0005]

However, the above-mentioned prior art has the following problems to be solved.
In the case of discrimination based on coat color, white mark, vitiligo, and curl, there are many horses with few features and horses with the same feature, so that the identification of the horse is often incomplete. In addition, there is a risk that the branding and tattoos may disappear or be tampered with, and improvements in animal welfare such as pain and local suppuration received by animals have been desired. In addition, although individual identification based on blood type is accurate, there is a disadvantage that a considerable processing time is required for determination and the cost is high.

[0006] The identification nameplate has a risk of being damaged, lost or stolen, and in the case of branding or tattooing, it has a risk of disappearing or being tampered with like a horse. ing. In particular, even if this falsification is revealed, it is difficult to prove where the person originally belonged.

[0007] The MC method can be used semi-permanently once it is embedded, and also has advantages such as high convenience. However, the operability of implantation in living animals, pain given to animals at the time of implantation, local reactivity such as swelling, tenderness, suppuration, etc., motor dysfunction and clinical abnormalities in animals, movement of MC in vivo There are many issues in terms of performance, operability of detector, change in detection sensitivity, stability, and reliability. And above all, from the aspect of animal welfare, there are animal officials who are reluctant to adopt the MC method,
A convenient identification method that replaces the MC identification method has been desired.

[0008]

The present invention employs the following structure to solve the above-mentioned problems. <Structure 1> An individual identification device that identifies an individual animal based on the biological characteristics of the animal stores an animal dictionary indicating information on biological characteristics corresponding to each ID, and stores an animal dictionary corresponding to each ID. An animal dictionary storage unit having weight information, and based on the weight of the individual to be identified, an animal dictionary selection unit that selects an animal dictionary having weight information in a predetermined range including the weight of the individual from the animal dictionary storage unit, An individual identification device comprising: an animal dictionary selected by an animal dictionary selection unit; and an animal matching unit that checks an individual to be identified.

<Structure 2> In an individual identification device for identifying an individual animal based on the biological characteristics of the animal, an animal dictionary indicating information on biological characteristics corresponding to each ID is stored, and an individual dictionary corresponding to each ID is stored. Based on the animal dictionary storage unit having the information of the person uniquely associated with the animal, the person identification unit that identifies the person, and the person information identified by the person identification unit,
An animal dictionary selecting unit for selecting an animal dictionary to which the person is related from the animal dictionary storage unit, and an animal matching unit for matching the animal dictionary selected by the animal dictionary selecting unit with an identification target individual An individual identification device characterized by the above-mentioned.

<Structure 3> In an individual identification device for identifying an individual animal based on the biological characteristics of the animal, an animal dictionary indicating information on biological characteristics corresponding to each ID is stored and corresponding to each ID. The weight information of the animal, the animal dictionary storage unit having information on the person uniquely associated with the animal, the person identification unit for identifying the person, the weight of the individual to be identified, and the person identification unit. Based on the person information, from the animal dictionary storage unit, an animal dictionary having information on the weight of a predetermined range including the weight of the individual, and an animal dictionary selection unit that selects an animal dictionary to which the person is associated, An individual identification device comprising: an animal dictionary selected by an animal dictionary selection unit; and an animal matching unit that checks an individual to be identified.

[0011]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of the present invention will be described below in detail with reference to specific examples. The invention relates to (race) horses,
(Maki) In order to identify animals at an organization that requires individual management of animals such as cattle, for example, register data on iris and iris granules and register data for collation processing.
The present invention relates to a verification device. Hereinafter, in a specific example, a case will be described in which a target animal is a horse, in particular.

FIG. 2 shows a front view of the eyeball of a horse. As shown in FIG. 2, the horse's eye mainly includes a pupil 10, an iris (iris) 11, and an iris granule 12 between upper and lower eyelids 13.

In addition, a transparent hemispherically raised cornea is provided in front of the pupil 10 and the iris 11. The major difference between horse eyes and human eyes is that the pupil 10 is elliptical,
It is to have iris granules 12 unique to horses and ruminants.

Light from the outside passes through the pupil 10 and reaches the retina at the back of the pupil. The iris 11 is a muscle surrounding the pupil 10 and has a function of controlling the amount of light incident on the pupil 10 by contracting and expanding. The iris granules 12 are located between the iris 11 and the pupil 10 and have a shape in which hemispherical raised granules are connected. The iris granules 12 have a black color rich in melanin pigment, and are said to have a function of absorbing dazzling daylight even when the iris 11 contracts.

The size and shape of the iris 11 and the iris granules 12 and the fine wrinkles and irregularities on the surface differ depending on the individual of the horse and the left and right of the eye, and there are individual differences. for that reason,
The iris 11 and the iris granules 12 are registered as reference data (hereinafter, referred to as a "dictionary") by imaging the horse's eyes with a camera, and the iris 11 and the iris granule data obtained at the time of the examination are compared and compared with the dictionary. It is possible to identify the target individual.

However, in a large-scale collation apparatus having several hundreds of registered horses, it takes a long time to search for a horse having the same ID as the input image from all the registered horses. As a method of avoiding this, there is a method of inputting a horse ID before collation and performing collation using only a dictionary of a single ID, but it is impossible to eliminate the trouble and trouble of inputting. Since it is possible, an alternative method has been desired.

On the other hand, according to the present invention, the individual identification device is provided with a function of inputting management information of each animal such as an animal weight and a manager, and the number of dictionaries to be collated with the information is reduced to speed up processing. Things. Hereinafter, the individual identification device of the present invention will be described in detail using specific examples.

<Specific Example><Configuration> FIG. 1 is a configuration diagram showing a specific example of the individual identification apparatus of the present invention. The device of the specific example is roughly divided into three functional units. These include a dictionary selection unit 30 using an animal weight, such as an animal weight input unit 31, a weight range calculation unit 32, a weight limit unit 33, and an animal weight recording unit 34, and an imaging unit 4.
1, an animal / human identification unit 42, a person dictionary selection unit 44, a person collation unit 45, an ID restriction unit 46, a dictionary selection unit 40 using an ID of an administrator such as a person dictionary storage unit 47, an animal dictionary selection unit 51, An animal identification unit 50 such as an animal matching unit 52 and a display unit 53.

Among these functions, the present embodiment is characterized in that a dictionary selection function for the animal dictionary storage unit 60 using the animal weight and an iris of the administrator are used for the individual identification function of the animal. This is the addition of a dictionary selection function.

The animal weight input unit 31 in the dictionary selection unit 30 using the animal weight is a function unit for acquiring weight data at the time of verification from a weight scale in horse weight measurement performed before individual identification.

The weight range calculation unit 32 is a processing unit that calculates the range of the weight to be restricted from the weight at the time of verification.

The weight limiting section 33 has a function of limiting the list of the animal dictionary storage section 60 based on the weight range, changes the flag of the horse ID whose weight at the time of the previous run is out of the weight range from 1 to 0, and performs verification. Has a function to exclude from the target.

The animal weight recording section 34 is a processing section for recording the weight in the animal dictionary storage section 60 for the next run.

The image pickup section 41 of the dictionary selection section 40 using the ID of the manager comprises an image input section such as a CCD video camera and lighting, and captures an image of a human or horse eye as a signal. The image input unit is a part that captures an image of an eye with a camera, and performs a process of converting analog optical information of the image of the eye into a digital electric signal by a sensor. In addition, the light is illuminated to capture the eyes with good contrast, and as a light source, it is difficult to perceive animals such as red light or near infrared light, infrared light to prevent the horse from dazzling and moving excessively Wavelength light is used.

The animal / human identification section 42 is a processing section for distinguishing between a human and a horse based on the image of the eyes, and has a pupil detection function and an oblateness calculation function.

The personal dictionary selecting section 44 is a personal dictionary storing section 4
7 for reading all data.

The person matching section 45 has a function of calculating a difference between the iris data in the person dictionary storage section 47 and the iris data of the input image and a function of identifying the manager based on the difference, and specifies a manager ID.

The ID restricting unit 46 is a processing unit for excluding a part of the dictionary in the animal dictionary storage unit 60 from the collation. When the manager ID of the horse in the dictionary is other than the ID identified by the person collating unit 45, Has a function of changing the flag from 1 to 0.

The person dictionary storage unit 47 is a dictionary database of human iris data, and is a list including an administrator ID and iris data.

The person dictionary selecting section 44 to the person dictionary storing section 47 constitute a person identifying section 43 for identifying a person.

The animal individual identification section 50 is a functional section for performing individual identification based on the biological characteristics of the animal, and is constituted by means described in, for example, JP-A-10-040375. .

The animal dictionary selecting section 51 in the animal individual identifying section 50 is a reading processing section of the animal dictionary storage section 60 and has a flag check function and a dictionary reading function.

The animal matching section 52 has a function of calculating the degree of difference between the image data of the animal dictionary storage section 60 and the input image and a function of determining the authenticity based on the degree of difference.

The display unit 53 has a function of displaying the authenticity determination result and the degree of difference received from the output result of the animal matching unit 52, and comprises an output device such as a display or a printer.

The animal dictionary storage section 60 is a horse dictionary database, and is a list including a horse ID, a dictionary image, the weight of a previous run, a manager ID, and a dictionary restriction flag. Here, the initial value of the dictionary restriction flag is set to 1, and the flag is rewritten to 0 when excluded from the dictionary at the time of collation by the weight restriction unit 33 or the ID restriction unit 46. .

<Operation> FIG. 4 is a flowchart showing the operation of the specific example. The steps will be described below in order.

[Step S1] The animal weight input unit 31
Get weight data from a horse scale. In the case of racehorses, this is usually used to measure horse weight before running.

[Step S2] The weight range calculator 32 calculates
Set the possible range of the weight of the previous run from the measured horse weight. The weight of a racehorse increases or decreases each time you run,
Since the running intervals are almost constant, the increase / decrease range is within a certain range. Therefore, add a certain value to the measured horse weight
The subtracted value becomes the upper and lower limits.

[Step S3] The weight limiting unit 33 changes, from the dictionaries in the animal dictionary storage unit 60, the flag of the dictionary whose weight at the time of the previous run is out of the weight range to 0. The initial value of the flag of the animal dictionary is set to 1, and the dictionary of the horse ID in which the flag is set to 0 is excluded in the later matching of the horse.

[Step S4] The operation of the image pickup section 41 will be described. The eye of a person or a horse is illuminated by illumination using a wavelength of red light, near-infrared light, or infrared light as a light source, and is imaged by an image input device such as a CCD video camera. CC
The D sensor is configured by a two-dimensional array of photoelectric conversion elements,
The reflected light of the imaging target is exposed for a certain period of time, and the voltage level imprinted by the photoelectric conversion is converted into a digital signal by quantizing it at a certain gradation. Thus, a two-dimensional array of image frames is obtained.

[Step S5] Animal / human identification section 42
Distinguishes people and horses from eye images. This example will be described with reference to the drawings.

FIG. 3 is an explanatory diagram of human eyes. Thus, the human eye has a pupil 20, an iris 21, a white eye 22, an eyelid 2
3 Comparing this with the image of FIG. 2 described above, the iris granules 12 are present in the horse's eyes but not in the human. The pupil 10 of the horse is elliptical but the pupil 20 of the human is a perfect circle. There are differences such as less exposure of white eyes.

Therefore, the human horse can be identified by detecting these differences. For example, when a pupil is used, first, the pupil has a low density (dark) and a uniform density. On the other hand, the iris has a higher density (brighter) than the pupil. Therefore, after detecting the coordinate sequence of the boundary between the pupil and the iris having a large difference in density using a difference filter, an ellipse that best approximates those points is applied. If the flatness of the ellipse (diameter of the short axis / diameter of the long axis) is approximately 1, it can be distinguished as a human, and otherwise, as a horse.

The method for detecting iris granules can be, for example, the following method. At the upper part of the pupil are iris granules, on which the iris is located. The change in density at the boundary of organs is larger than the change inside each organ. Therefore, first, when a density change detection process represented by the Sobel operator is performed, the pixel value at the boundary has a large value. Thus, the contour of the iris granule can be obtained by obtaining such an area of the pixel value.

As a method of detecting a pupil, for example,
Literature "Sakaguchi, Nakano, Yamamoto,"Driver's gaze detection while driving a car "IEICE PRU Technical Report,
PRU95-28 "and the like.

Various other identification methods can be applied to the present invention as a method for identifying a person and a horse.

[Step S6] After the horse weight is input, the personal identification of the manager is performed.

The person dictionary selecting section 44 stores the person dictionary storage section 4
7 and all the iris data are read.

[Step S 7] The person matching section 45 calculates the degree of difference between the inputted iris data of the administrator and the iris data of the person dictionary storage section 47. The degree of difference represents a distance between data, and various calculation methods such as an average difference between the identification target and the dictionary and a Euclidean distance are applicable to the present invention.

[Step S8] Next, the person verification unit 45
The ID of the dictionary having the minimum degree of difference is specified as the ID of the administrator. Alternatively, a method may be used in which all dictionary IDs equal to or less than a predetermined threshold are set as manager candidates.

[Step S9] The ID restricting unit 46 compares the manager ID with the ID identified by the person matching unit 45 in the dictionary of the animal dictionary storage unit 60, and sets the flag of the horse dictionary whose ID does not match the flag. Excluding the dictionary from matching by changing it to zero.

[Step S10] Animal dictionary selecting section 51
Reads the animal dictionary from the animal dictionary storage unit 60. At this time, the flag is checked, and only the dictionary whose flag is 1 is read. In this manner, the matching with the dictionary in which the horse weight or the manager does not match can be restricted in advance, so that the matching time can be reduced.

[Step S11] The animal matching section 52 calculates the difference between the dictionary in the animal dictionary storage section 60 and the input image.

[Step S12] Next, the animal matching section 52
Performs true / false determination based on the degree of difference. The dissimilarity is compared with a predetermined threshold value. If there is a dictionary whose dissimilarity is equal to or less than the threshold value, it is determined that the inspection target is true; otherwise, it is false. If the result of the authenticity determination is “true”, the process proceeds to an accepting process in step S13, and if the result is “false”, the process proceeds to a rejecting process in step S14.

[Step S13] The fact that the identification result is accept and the degree of difference are displayed on the display unit 53.

[Step S14] The fact that the identification result is rejection and the degree of difference are displayed on the display unit 53.

[Step S15] If the identification result is "accept", the horse weight of the corresponding horse ID in the animal dictionary is recorded, and the process ends.

<Effects> As described above, according to the specific example, the following effects can be expected. A function of inputting horse weight from a weight scale is provided, and the number of dictionaries used for collation is limited according to the horse weight. Therefore, the processing can be speeded up without requiring an input operation by a user.

Since the personal identification function of the administrator is provided by the iris and the dictionary used for collation is restricted by the administrator ID, it is possible to speed up the collation processing without requiring user input operation. Become.

<< Usage Form >> In the description of the present invention, the description has been made assuming that the matching unit of the horse and the dictionary use images, but the principle of the present invention is not limited to the case where matching is performed using various features extracted from the images. Exactly the same applies.

In the description of the present invention, the human collation unit uses iris, and the horse collation unit uses iris and iris granules. However, other personal identification methods and other biological characteristics are used. May be used.

In the description of the present invention, the case where a horse is used as an animal to be identified has been described, but any other animal can be realized in the same manner as in the specific example.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing a specific example of an individual identification device of the present invention.

FIG. 2 is an explanatory diagram of an eyeball image of a horse.

FIG. 3 is an explanatory diagram of a human eyeball image.

FIG. 4 is a flowchart showing the operation of a specific example of the individual identification device of the present invention.

[Explanation of symbols]

 43 Person identification unit 51 Animal dictionary selection unit 52 Animal matching unit 60 Animal dictionary storage unit

Claims (3)

[Claims] 1. An individual identification device for identifying an individual animal based on the biological characteristics of the animal, wherein an animal dictionary indicating information of biological characteristics corresponding to each ID is stored, and an animal dictionary corresponding to each ID is stored. An animal dictionary storage unit having weight information of an animal dictionary selecting unit for selecting an animal dictionary having weight information in a predetermined range including the weight of the individual from the animal dictionary storage unit based on the weight of the individual to be identified; And an animal matching section for matching the animal dictionary selected by the animal dictionary selecting section with the individual to be identified. 2. An individual identification device for identifying an individual animal based on the biological characteristics of the animal, wherein an animal dictionary indicating information on biological characteristics corresponding to each ID is stored and an animal dictionary corresponding to each ID is stored. An animal dictionary storage unit having information of a person uniquely associated with a person, a person identification unit for identifying a person, and the person from the animal dictionary storage unit based on the person information identified by the person identification unit. An animal dictionary selecting unit for selecting an attached animal dictionary; and an animal matching unit for matching the animal dictionary selected by the animal dictionary selecting unit with the individual to be identified. . 3. An individual identification device for identifying an individual animal based on the biological characteristics of the animal, wherein an animal dictionary indicating information of biological characteristics corresponding to each ID is stored, and an animal dictionary corresponding to each ID is stored. The animal dictionary storage unit having the weight information of the animal and the information of the person uniquely associated with the animal, the person identification unit for identifying the person, the weight of the individual to be identified, and the person identification unit An animal dictionary selection unit that selects an animal dictionary having weight information in a predetermined range including the weight of the individual from the animal dictionary storage unit based on the person information and the animal dictionary to which the person is related; And an animal matching section for matching the animal dictionary selected by the animal dictionary selecting section with the individual to be identified.