JP2003346148A - Muzzle pattern collating method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a muzzle pattern collating method capable of rapidly and inexpensively collating muzzle patterns with each other with less amount of data to see whether the muzzle patterns match each other or not. <P>SOLUTION: When the muzzle pattern 10 of cattle is collated, the muzzle pattern 10 of the cattle is preliminarily photographed, branch points 39 where groove in the skin of the cattle forming the muzzle pattern 10 are separated to two parts are extracted from a photographed muzzle pattern image, and the distribution state of the branch points 39 is stored. Later, the branch points 39 are extracted, in the same manner, from the photographed muzzle pattern image, and compared with the distribution of the stored branch points 39 to collate with the muzzle pattern of the cattle. The comparison of the muzzle pattern 10 can be performed also by comparing, in place of the branch points, the distribution of the longest line segments in the cell surrounded by the pattern lines showing the grooves in the photographed image. <P>COPYRIGHT: (C)2004,JPO

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for verifying a nose print, and more particularly to a method for verifying a nose print of a cow.

[0002]

2. Description of the Related Art Speaking of livestock registration, for example, registration of cattle,
Conventionally, in Japan, the `` Wagyu Registration Association '' for registering cow nose prints and the `` Holstein Registration Association '' for registering black and white spots on the body of Holstein dairy cows have been known. Beef Registration Association and Jersey Beef Registration Association
Etc.

[0003] Among them, the nose print of a cow is registered in advance, and a nose print collation method for identifying a cow individual by collation of the nose print later is reviewed. This is because the nose print registered in the calf does not change even when the cow grows, and serves as security for the identification of the cow.

A conventional method of collating a nose print has been to store a nose print obtained by adding black ink to a nose of a cow and visually compare a nose print obtained at a later date. With the development of the computer, the nose print of the nose of the cow is photographed in advance with a camera together with the individual identification number of the cow represented by a bar code or a number, etc., and converted into video data, which is recorded as image data in the computer. In addition, the collation with the nose print of a cow photographed later is performed between image data.

[0005]

However, in the method of comparing nose prints by comparing image data using a computer, the amount of data to be compared is enormous. The capacity must be increased, and there is a problem that the matching device becomes large-scale and the cost increases.

Therefore, an object of the present invention is to perform the collation of a nose print with as little data as possible by utilizing the characteristics of the nose print of a cow in collation of the nose print of a cow, thereby reducing the collation time and reducing the collation. An object of the present invention is to provide a method for collating a nose print that can reduce the size of the device and reduce the cost of the collation device.

[0007]

According to a first embodiment of the method of the present invention for achieving the above object, a nose print of a cow is photographed in advance, and a nose print is formed from the photographed nose print image. The branch point where the groove on the cow's skin is divided into two is extracted, the distribution state of the branch point is stored, and the branch point is extracted from the nose print image of the cow taken at a later date, and this is stored. It is characterized in that the nose print of a cow is collated by comparing it with the distribution of the branch points that are present.

In the second embodiment, a method of collating a cow by a nose print is to photograph a nose print of a cow in advance, and the photographed nose print image is surrounded by a groove on the skin of the cow forming the nose print. The longest line segment that falls within the plurality of cells is extracted, the distribution state of this line segment is stored, and this line segment is extracted from a nose print image of a cow taken at a later date, and its distribution is created. By comparing the distribution with the distribution of the stored line segments, the nose print of the cow is collated.

Further, in the method of collating a cow according to the third form with a nose print, a nose print of a cow is photographed in advance, and two grooves on the skin of the cow forming the nose print are formed from the photographed nose print image. And extract the longest line segment connecting the furthest branch points among the cells surrounded by the groove for each cell, and store this distribution state. In addition, by extracting this line segment from a cow's nose print image taken at a later date, creating its distribution, and comparing this distribution with the stored line segment distribution, collation of the cow's nose print It is characterized by the following.

In a fourth aspect of the present invention, in the first to third embodiments, when a nose print is taken, an image is taken and stored so that a cow's nostril appears on both sides of the nose print. Near the shortest distance straight line connecting the nostrils in the nose print image, or distribution of branch points or line segments in a predetermined area below this straight line,
The nose print of a cow is collated by comparing the distribution of a branch point or a line segment in a corresponding region in a nose print image of a cow taken at a later date.

Further, in a fifth aspect of the present invention, in the first to third embodiments, when the nose print is photographed, the cow is photographed so that the nostrils of the cow appear on both sides of the nose print and stored. The nose print image is divided into four parts by the shortest straight line connecting the nostrils and the perpendicular passing through the midpoint of this straight line, and the cow nose print image taken at a later date also passes through the midpoint of the shortest straight line connecting the nostrils. It is characterized in that the nose print of a cow is collated by dividing at least one set of distributions of branch points or line segments in a divided screen at the same position with respect to a quadrant divided by a perpendicular line.

Further, in a sixth aspect of the present invention, there is provided a method of collating a nostril pattern according to the fourth or fifth aspect, wherein the collation is performed at a later date with respect to the length of the shortest straight line connecting the nostrils in the stored nostril image. The ratio of the length of the shortest straight line connecting the nostrils in the cow's nose print image is determined, and the size of either the stored nose print image or the cow's nose print image taken at a later date is determined based on this ratio. After the two images are corrected to have the same size, the distribution of the branch points or the distribution of the line segments is compared with each other to collate the cow's nose pattern.

[0013] These nose print collation methods may be used to collate cow nose prints by combining some of them.

According to the nose print collation method of the present invention, nose prints can be compared based on a small amount of information in the photographed nose print data. Thus, the collation time can be reduced, the collation device can be downsized, and the cost of the collation device can be reduced.

[0015]

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing a method of collating a nose print of a cow according to the present invention with reference to the accompanying drawings.

FIG. 1A shows how a digital camera 11 photographs a nose print 10 of a cow 9 using a data card 1. When photographing, the nose print frame 1
Use 6. A nose print hole 17 is formed in the nose print frame 16. The nose print hole 17 is aligned with the nose print 10 of the cow 9 at the time of photographing, and a bar code or two-dimensional print is printed on the data card 1. The photographing of the nose print 10 is performed with the bar code positioned near the nose print imaging hole 17. Here, a panel is used for the nose print frame 16, but any shape may be used as long as the positional relationship between the nose print and the digital camera 11 is fixed.

FIG. 1B shows an example of an image taken by the digital camera 11 described in FIG. As described with reference to FIG. 1A, this image is an image obtained when the nose print 10 of the cow 9 is photographed together with the data card 1. In the present invention, when photographing the nose print 10 of the cow 9, the photograph is performed such that the nostrils 18 of the cow 9 are always photographed on both sides of the nose print 10. For this reason, it is convenient to prepare a plurality of types of the nose print frame 16 described with reference to FIG. 1A in which a nose print hole 17 having a size corresponding to the interval between the nostrils of the cow 9 is prepared. is there. The image photographed by the digital camera 11 includes a cow's unique number 2, a two-dimensional bar code 4 (4S is a cutout symbol),
An enlarged number 5 obtained by enlarging a part of the numerals in the unique number 2 and a blank 6 in which a handwritten numeral (in this example, a management number unique to the farmer is described) are recorded.

FIG. 2A shows a state in which an image photographed by the digital camera 11 shown in FIG. 1A is transmitted as image data from the farmer's computer 12 to the management center 20. Image data is sent from the farm computer 12 to the management center 20 via the communication line 13. The management center 20 includes a computer 21 connected to the communication line 13, a display 22 for displaying input image data, a barcode reader 23 for reading a barcode in an image displayed on the display 22, And a database 25 for storing and managing data. Barcode reader 23 and keyboard 24
Is input to the computer 21.

If the digital camera 11 is provided with a function of connecting to a communication device, and a photographed image can be transmitted without connecting to the farmer's computer 12 by connecting a portable telephone, the photographed image can be transmitted. The data can be transmitted to the computer 21 of the management center 20 as it is. Further, in recent years, a communication device may be built in the digital camera 11. In the digital camera 11 having such a built-in communication device, a captured image can be directly transmitted from the digital camera 11 itself to the computer 21 of the management center 20.
It is possible to send to.

FIG. 2B shows an example of a screen 26 displayed on the display 22 of the management center 20 after being transmitted from the farmer's computer 12 to the management center 20. The image data captured by the digital camera 11 described with reference to FIG. 1B is captured as cow image data and displayed in a cow image column 27 displayed on a screen 26 of the display 22. The two-dimensional barcode 4 in the image displayed in the cow image field 27 is read by software built in the computer 21 or by scanning the image with a barcode reader 23, and the unique number 2 of the cow is displayed.
Is decoded by the computer 21. The decoded cow's unique number 2 is displayed in the unique number column 28 on the screen 26. Although not shown, a unique file name having the content shown on the screen 26 is created using this unique number.

In the example shown in FIG. 1B, a handwritten character is described in a blank space 6 above the two-dimensional barcode 4. This handwritten character can be read with reference to the cutout symbol 4S of a two-dimensional barcode, and can be recorded in a database as data by character recognition.

It is to be noted that only the image data of the cow and the unique number 2 can be displayed on the screen only from the image data from the computer 12 of the farmer as in this example. On the other hand, other data of the cow corresponding to the unique number 2 is generally recorded and managed in another database. In this case, the database can be linked from the screen 26 so that the searcher of this screen can refer to another database from this screen 26 when he / she wants to know other data of this cow. be able to. By input from the keyboard 24 or the like, in addition to the image data and the unique number, information such as the birth date, birth place, and transfer history of the cow can be additionally displayed on the screen 26. is there.

When a plurality of types of image data are sent to the management center 20 for the same cow,
In the above, a plurality of image data can be stored for the same unique number based on the unique number of the data card included in the image data. When storing a plurality of image data for the same unique number, the file names of the same livestock to be registered in the database 25 are made different by adding a branch number to the same main file name. What is necessary is just to show that the livestock indicated by this file name is the same livestock.

In the case where it becomes necessary to collate the cow 9 with the nose print after a lapse of a predetermined period after the nose print 10 of the cow 9 is registered in the management center 20 in this manner, the nose print 10 of the present invention is used.
The method of matching will be described below.

Before explaining the collation method of the present invention, first,
The characteristics of the cow nose pattern will be described. As shown in FIG. 1B, the nose print 10 of the cow 9 is formed by a groove formed on the skin of the cow. The groove is closed, and the skin inside the closed groove is raised and convex. Since the convex portion surrounded by the groove has a substantially oval shape when imaged, the convex portion on the video screen is hereinafter referred to as a cell. In addition, there is one groove at the boundary between adjacent convex portions, and the groove surrounding one convex portion is always divided into two to surround the adjacent convex portion. Therefore, a line indicating the groove on the video screen is hereinafter referred to as a pattern line, and a point at which the pattern line is divided into two is hereinafter referred to as a branch point.

FIG. 3 shows image data of the photographed nose print 10. In the nose print collation method according to the first embodiment of the present invention, a pattern line 29 around each cell 19 included in the nose print 10 appearing in the image data is approximated by a straight line. Then, a branch point 39 of the pattern line 29 is detected. In the present invention, two nostrils 18 appearing in the image data are used.
And a straight line Y that vertically bisects the straight line X is also determined.

FIG. 4 is a diagram showing an example of an image in which only the branch point 39 and the straight lines X and Y are extracted from the image of FIG. In the present invention, only the branch point 39 and the data of the straight lines X and Y are stored in the management center 20 as the nose print comparison data.

When the nose print of the cow is collated later, data of only the branch point 39 and the data of the straight lines X and Y are similarly created from the image data of the nose print of the cow, and this is stored in the management center. A comparison is made between the branch point 39 stored in 20 and the data of the straight lines X and Y. Then, when the distributions of the branch points 39 match, it is determined that the two nose prints match. In this comparison, it is sufficient to compare only the coordinate data of the branch point 39, so that the data amount of the matching nose print is smaller than the case where the nose print is compared using the image data, and the matching time can be reduced. Can be planned.

In order to increase the speed of the determination, the comparison of the branch point 39 is performed only at the branch point 39 near the straight line X or only at the branch point 39 near the straight line Y below the straight line X. Can also perform the matching of the nose print. Further, the image data is divided into four regions A, B, C, and D by straight lines X and Y, and the distribution of the branch points 39 in at least one of these regions A to D is compared. The nose print can also be collated.

The nose print data of the cow initially recorded was for a calf of a cow, and the nose print data for comparison was obtained after the cow had grown, and the size of the nose changed. In the case, the length of the straight line X connecting the shortest distance between the two nostrils of the cow is compared, and the distribution of the branch point 39 photographed in the calf era is expanded and corrected at the rate of extension of the straight line X, and the current Compare the distribution of the branch points 39, or conversely, the branch points 39 taken at a later date
Is reduced and corrected and compared with the stored distribution of the branch points 39, so that more accurate matching of the nose print can be performed.

Next, a method of collating a nose print according to a second embodiment of the present invention will be described. In the second embodiment, similar to the first embodiment, each cell 1 included in the nose print 10 appearing in the image data is obtained.
The pattern line 29 around 9 is approximated by a straight line. In this case, the branch point 39 of the pattern line 29 may or may not be detected. Also in the second embodiment, a straight line X connecting the shortest distance between the two nostrils 18 shown in the image data is obtained, and a straight line Y which bisects the straight line X vertically is also obtained. .

In the second embodiment, as shown in FIG. 5, a plurality of cells 19 surrounded by a pattern line 29 forming the nose pattern 10 are formed.
Is extracted for each cell 19 one by one. Then, as shown in FIG. 6, only the line segment 49 and the straight lines X and Y are extracted from the image of FIG. 5, and these data are stored in the management center 20 as nose print comparison data. The line segment 49 can be stored as a vector.

When the nose print of the cow is collated later, data of only the line segment 49 and the data of the straight lines X and Y are similarly created from the image data of the nose print of the cow, and this is stored in the management center. The line segment 49 stored in 20 and the data of the straight lines X and Y are compared. In this comparison, both can be compared as a vector. Then, when the distribution of the line segment 49 (or the distribution of the vector) matches, it is determined that the two nose prints match. In this comparison, it is sufficient to compare only the coordinate data of the line segment 49 (the reference coordinates and the length of the vector in the case of comparison as a vector). The amount of data of the nose print of the stencil can be reduced, and the collation time can be reduced.

As in the first embodiment, in order to increase the speed of the judgment, a method of comparing the line segment 49 only in the vicinity of the straight line X or only in the vicinity of the straight line Y,
A method of comparing distributions in only at least one of the four regions A, B, C, and D divided by the above method may be adopted. In addition, in order to improve the matching accuracy, a straight line X
The method of comparing the distribution of the line segment 49 after matching the size of the image photographed in the calf era with the image photographed later at the stretched ratio can be performed in the same manner as in the first embodiment.

As a modified embodiment of the second embodiment,
As shown in FIG. 7, a plurality of cells 1 surrounded by a pattern line 29
9, the longest line segment 59 connecting the farthest branch points 39 may be extracted, and this line segment 59 may be used in place of the line segment 49.

Although the methods of some embodiments have been described above, if these methods are not performed independently but are performed in combination with each other, the collation accuracy of the nose print can be improved.

[0037]

As described above, according to the nose print collation method of the present invention, the nose prints are compared with each other by using a small amount of information based on the characteristics of the nose print of the cow in the photographed nose print data. Collation can be performed, so that the collation of the nose print can be performed with a small amount of data, so that the collation time can be reduced, the collation device can be downsized, and the cost of the collation device can be reduced. There is.

[Brief description of the drawings]

FIG. 1A is a diagram showing a state where a nose print of a cow is photographed by a digital camera using a data card, and FIG. 1B is a diagram showing an image photographed by the photographing of FIG.

2A is a diagram showing a state in which an image taken by the digital camera shown in FIG. 1A is transmitted as image data from a farmer's computer to a management center via a communication line, and FIG. It is a figure showing a registration screen.

FIG. 3 is a diagram illustrating a state where a branch point of a photographed nose pattern pattern line is extracted.

FIG. 4 is a diagram showing an example of an image showing only a branch point extracted from the image of FIG. 3;

FIG. 5 is a diagram illustrating a state in which the longest line segment that falls within the cell is extracted from a cell portion surrounded by a pattern line of a photographed nose pattern.

FIG. 6 is a diagram showing an example of an image in which only line segments are extracted from the image of FIG. 5;

FIG. 7 is a diagram illustrating a state in which a line segment connecting a furthest branch point in the cell is extracted from a cell portion surrounded by a pattern line of a photographed nose pattern.

[Explanation of symbols]

9 ... cow 10… nose print 11 ... Digital camera 12 ... Computer 13. Communication line 16 ... Photo frame 18 Nostrils 19 ... cell 20 ... Management center 21 ... Computer 22 ... Display 25 ... Database 27 ... Cow image column 28… Unique number column 29… Pattern line 39 ... Branch point 49, 59 ... line segment

Claims (7)

[Claims] 1. A method for collating a cow's nose print, comprising: photographing a cow's nose print in advance; and branching a groove on a cow's skin forming a nose print into two from a photographed nose print image. By extracting points, storing the distribution state of the bifurcation points, extracting the bifurcation points from the nose print image of the cow photographed at a later date, and comparing this with the stored distribution of bifurcation points, A method for matching a nose print, comprising: 2. A method of collating a cow's nose print, comprising: photographing a cow's nose print in advance; and extracting a plurality of cells surrounded by grooves on the cow's skin forming the nose print from the photographed nose print image. Is extracted, the distribution state of this line segment is stored, the line segment is extracted from the nose print image of a cow taken at a later date, the distribution is created, and this distribution is stored. A nose print collation method characterized in that a nose print of a cow is collated by comparing the distribution with a line segment that has been used. 3. A method for collating a cow's nose print, comprising: photographing a cow's nose print in advance; and branching a groove on the cow's skin forming the nose print into two from the photographed nose print image. A point is extracted, and among the plurality of cells surrounded by the groove, the longest line segment connecting the farthest branch points is defined as:
The distribution state is extracted and stored for each cell, and the line segment is extracted from the nose print image of the cow photographed at a later date to create the distribution, and this distribution is stored as the distribution of the stored line segment. A method of matching a nose print, comprising comparing the nose print of a cow by comparing. 4. The method according to claim 1, wherein, when photographing the nose print, photographing is performed such that the nostrils of the cow appear on both sides of the nose print. The distribution of the branch points or line segments in the vicinity of the shortest distance line connecting the nostrils in the stored nostril image, or in a predetermined area below the straight line, and the nose pattern image of a cow photographed at a later date. A noseprint collation method characterized by comparing a noseprint of a cow by comparing the distribution with a branch point or a line segment in a corresponding region in the inside. 5. The method according to claim 1, wherein, when photographing the nose print, photographing is performed such that the nostrils of the cow appear on both sides of the nose print. The stored nostril image is divided into four parts by the shortest distance straight line connecting the nostrils and a perpendicular passing through the midpoint of this straight line, and the cow nose pattern image taken at a later date is also the shortest distance connecting the nostrils. The nose print of a cow is collated by dividing at least one set of distributions of branch points or line segments in a divided screen at the same position with a straight line and a perpendicular passing through the middle point of the straight line. A method for collating a nose print, comprising: 6. The method according to claim 4 or 5, wherein the nose of the cow photographed at a later date with respect to the length of a shortest straight line connecting the nostrils in the stored nose print image. The ratio of the length of the shortest straight line connecting the nostrils in the crest image is determined, and the size of one of the stored nose pattern image and the cow nose pattern image photographed at a later date is corrected based on this ratio. And comparing the distribution of the branch points or the distribution of the line segments to match the nose print of the cow, thereby making the two images the same size. 7. A method of collating a nose print, comprising: combining a combination of the methods of collating a nose pattern according to claim 1 to collate a nose pattern of a cow.