JP2015104379A - Breed discrimination device and breed discrimination method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a breed discrimination device and a breed discrimination method capable of discriminating the breed of fry of eel highly accurately in a short time.SOLUTION: In a breed discrimination device including imaging means 2 for imaging fry A of eel stored in a transparent case 1, and a computer 3 for discriminating the breed of the fry of the eel on the basis of an image imaged by the imaging means 2, the computer 3 discriminates the breed of the fry of the eel on the basis of a plurality of physical feature points which are mutually different according to the breed.

Description

  The present invention relates to a breed discriminating apparatus and a breed discriminating method for discriminating the breed of an eel by imaging it.

  As many as 19 eel varieties have been confirmed, and their habitat distribution has spread to regions such as the tropics, subtropics, and temperate zones. Recently, due to changes in natural phenomena such as global warming and El Niño, Unfishing of Japanese eel flies (white eel) continues along the coast of Japan. However, larvae of eels that have been captured at the Mariana Trench and before reaching the coast of Japan include Japanese eels and other foreign eels (Bicara Pacifica, Marmorata, Ruzonensis, etc.). There are many cases where fry are mixed.

  On the other hand, when eels are cultivated, the cultivation method differs depending on the breed. This is more expensive than other foreign eels, so the quality is not stable. Therefore, it is necessary to discriminate varieties of captured eel fry, and conventionally, for example, discrimination of varieties based on genes, discrimination using differences in water temperature of habitat (see, for example, Patent Document 1), etc. Was done.

JP 2004-135649 A

  However, the determination technique based on the gene among the conventional techniques has a problem that it takes a relatively long time and cost for the determination. Also, in the discrimination using the difference in water temperature in the habitat, there is a problem that if the storage time in the same aquarium is long, it becomes used to the environment and the discrimination is not sufficient and the accuracy is poor.

  The present invention has been made in view of such circumstances, and it is an object of the present invention to provide a breed discriminating apparatus and a breed discriminating method that can discriminate varieties of eel fry in high accuracy and in a short time.

  The invention according to claim 1 is an apparatus for distinguishing varieties comprising imaging means for imaging eel fry and discrimination means for discriminating varieties of eel fry based on images captured by the imaging means, The discriminating means discriminates the varieties of eel fry based on a plurality of physical feature points different from each other.

  According to a second aspect of the present invention, in the breed discriminating apparatus according to the first aspect, one of the physical feature points is a ratio of a total length of the eel fry and a width dimension.

  According to a third aspect of the present invention, in the breed discriminating apparatus according to the first or second aspect, one of the physical feature points is a distribution state of a melanin pigment formed in a part of a eel fry. It is characterized by.

  The invention described in claim 4 is the breed discriminating apparatus according to any one of claims 1 to 3, wherein one of the physical feature points is based on the shape, size, or number of strips of a fin of eel fry. It is characterized by comprising.

  According to a fifth aspect of the present invention, in the breed discriminating apparatus according to any one of the first to fourth aspects, one of the physical feature points includes the number of bones in a predetermined part of the eel fry. Features.

  The invention described in claim 6 is characterized in that, in the breed discriminating apparatus according to any one of claims 1 to 5, the eel fry is put into a dead state and then imaged by the imaging means.

  Invention of Claim 7 was equipped with the conveyance means which can convey the eel fry to the imaging position of the said imaging means one by one in the kind discrimination | determination apparatus as described in any one of Claims 1-6. Features.

  The invention according to claim 8 is a breed discriminating method for picking up eel fry and discriminating varieties of eel fry based on the picked up image, based on a plurality of physical feature points different from each other. It is characterized by distinguishing varieties of eel fry.

  According to a ninth aspect of the present invention, in the breed discrimination method according to the eighth aspect, one of the physical feature points is a ratio of the total length of the eel fry to the width dimension.

  According to a tenth aspect of the present invention, in the breed discrimination method according to the eighth or ninth aspect, one of the physical features is a distribution state of a melanin pigment formed in a part of a eel fry. It is characterized by.

  The invention according to claim 11 is the breed discrimination method according to any one of claims 8 to 10, wherein one of the physical feature points is based on the shape, size, or number of streaks of eel fry. It is characterized by comprising.

  According to a twelfth aspect of the present invention, in the breed discrimination method according to any one of the eighth to eleventh aspects, one of the physical feature points includes the number of bones in a predetermined part of the eel fry. Features.

  A thirteenth aspect of the invention is characterized in that, in the breed discrimination method according to any one of the eighth to twelfth aspects, imaging is performed after the eel fry is put into a dead state.

  The invention described in claim 14 is characterized in that, in the breed discrimination method according to any one of claims 8 to 13, the eel fry is conveyed to the imaging position one by one and imaged.

  According to the first and eighth aspects of the invention, the eel fry breed is discriminated on the basis of a plurality of physical feature points different from each other, so that the eel fry breed can be discriminated with high accuracy and in a short time. it can.

  According to invention of Claims 2-5, 9-12, as a physical characteristic point for discrimination, the ratio of the full length and width dimension of the eel fry, the melanin pigment formed in a part of the eel fry Identify the eel fry varieties with higher accuracy by using all or any combination of the distribution status, fin shape, size or number of fins of the eel fry, and the number of bones in the specified part of the eel fry Can do.

  According to the inventions of claims 6 and 13, since imaging is performed after the eel fry is put into a pseudo-dead state, the varieties of the eel fry can be discriminated with high accuracy and in a short time while maintaining the living state.

  According to the seventh and fourteenth aspects of the present invention, eel fry are transported to the imaging position one by one and imaged, so that imaging and discrimination based on the image can be performed more easily and accurately.

The schematic diagram which shows the outline of the kind identification apparatus which concerns on embodiment of this invention Schematic diagram showing eel fry whose varieties are identified by the same cultivar identification device The flowchart which shows the kind identification method which concerns on embodiment of this invention The schematic diagram which shows the outline (a conveyance means is included) of the kind identification apparatus which concerns on embodiment of this invention.

Hereinafter, embodiments of the present invention will be specifically described with reference to the drawings.
The breed discriminating apparatus according to the present embodiment discriminates varieties of eel fry (white eel), particularly for sorting Japanese eel fry. As shown in FIGS. A transparent case 1 that can accommodate the fry A together with water, an imaging means 2, a computer 3 as a discrimination means, an illumination means 4, a cooling means 5 (see FIG. 4), and a transport means α. It is configured.

  The cooling means 5 is composed of a refrigerant for cooling the water stored in the container C, and the container C stores a large number of eel fry captured by fishing, for example. Then, by operating the cooling means 5 to cool the water in the container C to a predetermined temperature, the eel fry can be put into a temporary death state. The predetermined temperature for setting the asphyxia state according to the present embodiment is set to a temperature of 1 ° C. to 7 ° C. (activity stop temperature of eel fry). The eel fry that has been put into a dead state usually stiffens and does not move while the whole body is straight (substantially straight).

  However, the eel fry that has been put to a dead state by the cooling means 5 is transferred to the case 1 one by one, and conveyed to the imaging position by the imaging means 2 by the conveying means α. The transport means α according to the present embodiment is composed of a plurality of cases 1 connected endlessly (looped) by connecting means D such as wires, and the connecting means D is moved by a driving source (not shown). The case 1 can be sequentially conveyed.

  The imaging means 2 is composed of a camera (for example, a digital camera) that can image a eel fry A (an asylum-seed white eel) contained in the case 1 and electrically connected to the captured image data. 3 to be transmitted. Note that the imaging unit 2 according to the present embodiment is a digital camera capable of obtaining an image of 2 million pixels (1600 × 1200 pixels), for example.

  Moreover, the illumination means 4 which can irradiate light from the back surface and the upper surface is arrange | positioned in the imaging position by the imaging means 2, for example, and the eel fry A can be imaged more clearly. The illumination unit 4 according to the present embodiment is made of, for example, a white LED, and is configured to irradiate light from the back surface and the top surface with respect to the imaging position of the imaging unit 2. The light irradiation position of the illumination unit 4 can be arbitrarily set.

  The computer 3 (discriminating means) is for receiving the image data from the imaging means 2 and discriminating the breed of eel fry based on the image. In this embodiment, the discriminating target is the fry of Japanese eel. It is a personal computer that can determine whether or not. Here, the computer 3 as the discriminating means according to the present embodiment discriminates varieties of eel fry based on a plurality of physical feature points different from each other.

  For example, one of the physical feature points for discrimination consists of the ratio (L: W) of the total length L and the width dimension W of the eel fry A as shown in FIG. That is, although the physique of the eel fry A differs depending on the growth state even in the same variety, the ratio between the total length L and the width dimension W is often different depending on the variety, and by using this ratio, it is a Japanese eel fry. It is possible to discriminate between those that have a possibility (including both high and low possibility) and those that have little possibility.

  Also, one of the physical feature points for discrimination consists of the distribution of melanin pigments formed in a part of the eel fry A. In other words, the spots other than the Japanese eel fry are often distributed with spots made of melanin, and the spots are not distributed so much in the tails of the Japanese eel fry. Thus, it is possible to discriminate what is likely to be a Japanese eel fry (including both high and low possibility) and almost no possibility.

  Further, one of the physical feature points for discrimination consists of the shape, size, or number of strips of fins of eel fry A. In other words, the dorsal fin and tail fin of eel fry are often different in shape and size, or the number of streaks formed on the dorsal fin and tail fin, and by using the shape, size or number of strips, It is possible to discriminate what is likely to be fry (including both high and low possibility) and almost no possibility.

  Furthermore, one of the physical feature points for discrimination consists of the number of bones at a predetermined site of the eel fry A. That is, there are many eel fry, for example, the number of abdominal vertebrae, the number of vertebrae, and the number of ribs differ depending on the breed, and by using the number of the bones, there is a possibility that it is a Japanese eel fry (possibility Can be discriminated between those having high and low values) and those having little possibility. The eel fry can be sufficiently imaged of the internal bones by the light from the illumination means 4 because the body is transparent. For example, the eel fry can be captured by X-ray irradiation or a CT scanner. You may make it image an inside more accurately.

Next, the type identification method according to the present embodiment will be described with reference to the flowchart of FIG. 3 and the schematic diagram of FIG.
First, the cooling means 5 cools the container C to a predetermined temperature (in this embodiment, the temperature at which the eel fry is 1 ° C. to 7 ° C.), and puts it into a pseudo-dead state (pseudo-death process S1). Thereafter, the larvae larvae in the assassinated state are accommodated one by one in the case 1 of the transport means α and transported to the imaging position (transport process S2), and the eel fry A in the case 1 reaching the imaging position is imaged. 2 to capture an image (imaging step S3).

  Then, the image data picked up by the image pickup means 2 is transmitted to the computer 3 and image processing by the computer 3 is performed (image processing step S4). This image processing step S4 is a step for processing so that a captured image can be determined, and includes, for example, identification of a determination target (eel fry A) in a captured image, removal of noise, and the like. Thereafter, the breed of eel fry A is discriminated (discrimination step S5).

  Such discrimination step S5 is a step of discriminating the breed of eel fry A based on a plurality of physical feature points different from each other, and the physical feature points according to the present embodiment include, as described above, Ratio of full length and width dimensions of eel fry (distinguishing condition 1), distribution of melanin pigment formed in part of eel fry (discriminating condition 2), fin shape, size or strip of eel fry Various things such as the number (discrimination condition 3), the number of bones in a predetermined part of the eel fry (discrimination condition 4), and the like can be mentioned. Note that the conditions used for determination may be all of the determination conditions (1 to 4), or may be arbitrarily selected from the determination conditions (1 to 4).

  Therefore, the eel fry that satisfies all of the discrimination conditions used is discriminated as a Japanese eel fry, and the eel fry that does not satisfy any of them is discriminated as a fry of a different breed from the Japanese eel. As a result, when each discrimination condition is used alone, there is a risk that even if it is less likely to be a Japanese eel fry, it may be determined that it is a Japanese eel fry. Thus, Japanese eel fry can be discriminated more accurately.

  Then, among the cases 1 that are far from the imaging position, the one determined to be a Japanese eel fry is turned upside down above the aquarium B1, and the fry of the eel is dropped and accommodated in the aquarium B1. The larvae of the Japanese eels and other varieties are sorted by inverting the larvae that have been determined not to be eels upside down above the aquarium B2, and dropping the eels into the aquarium B2 (Sorting step S6).

  After the sorting in the sorting step S6 is completed, the case 1 is turned upside down to return to the original accommodable state, and the eel fry A in the assassinated state is received and transported to the imaging position again. The aquarium B1 contains 10-30 ° C. water, which is the activity temperature of eels. The fry that are identified as Japanese eels and stored in the aquarium B1 are restored from the asphyxia state to the active state. Will be.

  According to the present embodiment, since the eel fry is put into a dead state and then picked up to determine the breed based on the image, the eel fry breed is maintained in a highly accurate and short time and alive state. Can be determined. In other words, the eel fry A, which has been put into a dead state, normally stiffens and remains immobile while being in a straight state (substantially linear), and therefore is imaged by the imaging means 2 and by the computer 3 as the discrimination means. Since image processing and breed discrimination can be performed with high accuracy, the breed of eel fry can be discriminated with high accuracy and in a short time while maintaining the survival state (in this embodiment, whether it is a fry of Japanese eel Can be determined).

  In addition, since the eel fry is cooled to a predetermined temperature so as to be in a pseudo-dead state, it can be reliably and inexpensively brought into a pseudo-dead state and can be better restored from the pseudo-dead state to an active state. In particular, since the predetermined temperature is set to the activity stop temperature of 1 ° C. to 7 ° C., it is possible to more reliably enter into a pseudo-dead state. It should be noted that other temperatures may be set as long as the eel fry can be put into a dead state.

  Still further, since the larvae of the eels in the assassinated state are transported to the imaging position one by one by the transport means α according to the present embodiment, imaging and discrimination based on the images can be performed more easily and accurately. . In addition, a large number of asymptomatic eel fry are accommodated in the case 1, and for each image identified and identified for each discrimination target (for each captured eel fry) during discrimination by the computer 3 (discrimination means). A determination may be made.

  In particular, according to the present embodiment, the eel fry breed is discriminated based on a plurality of different physical feature points depending on the breed, so that the eel fry breed can be discriminated with high accuracy and in a short time. In other words, because there are differences in the physical feature points of each breed due to heredity, it is possible to discriminate varieties of eel fry in high accuracy and in a short time by multiplying the physical feature points as multiple discrimination conditions. (In this embodiment, it is possible to determine whether the fish is a Japanese eel fry).

  In addition, as physical features for discrimination, the ratio between the total length L and the width dimension W of the eel fry, the distribution of melanin pigment formed in a part of the eel fry, the shape of the fin of the eel fry, By using all or any combination of the size or number of stripes and the number of bones in a predetermined part of the eel fry, it is possible to discriminate varieties of eel fry with higher accuracy. The number of physical feature points used for discrimination is preferably as much as possible in order to improve accuracy. The appearance of physical feature points (for example, the ratio between the total length L and the width dimension W) and the internal physical points are preferred. It is preferable to combine with feature points (such as the number of bones).

  Although the present embodiment has been described above, the present invention is not limited to this. For example, the computer 3 as the discrimination means may be of any form (a personal computer, a microcomputer or the like). Moreover, the method of making it a dead state may be administration of an electric shock, a medicine, etc. other than what cools to activity stop temperature like this embodiment. Furthermore, it is good also as what discriminate | determines based on the image by an imaging means, without setting it as a pseudo-death state. In addition, the conveyance means (alpha) is not limited to the thing of this embodiment, It is good also as a conveyance means (belt conveyor etc.) of another form.

  Any variety identification device and variety identification method can be applied as long as it is a variety identification device and a variety identification method for identifying a variety of eel fry based on a plurality of different physical feature points depending on the variety.

1 Case 2 Imaging means 3 Computer (discrimination means)
4 lighting means 5 cooling means A eel fry

Claims (14)

Imaging means for imaging eel fry,
Discriminating means for discriminating the breed of eel fry based on the image captured by the imaging means;
A product type identification device comprising:
The said discrimination | determination means discriminate | determines the breed of the eel fry based on several physical feature points which are mutually different according to the breed.   2. The breed discriminating apparatus according to claim 1, wherein one of the physical feature points comprises a ratio of a total length of the eel fry to a width dimension.   3. The breed discriminating apparatus according to claim 1, wherein one of the physical feature points is a distribution state of a melanin pigment formed in a part of eel fry.   4. The breed discrimination apparatus according to any one of claims 1 to 3, wherein one of the physical feature points is a shape, size, or number of strips of eel fry.   One of the said physical feature points consists of the number of the bones in the predetermined site | part of the eel fry, The breed | species discrimination apparatus as described in any one of Claims 1-4 characterized by the above-mentioned.   The cultivar discrimination apparatus according to any one of claims 1 to 5, wherein an image of the eel fry is put into an asphyxia state and then imaged by the imaging means.   The breed discriminating apparatus according to any one of claims 1 to 6, further comprising a transport unit capable of transporting each eel fry to the imaging position of the imaging unit. A cultivar discriminating method for imaging eel fry and discriminating the varieties of eel fry based on the captured image,
A method for discriminating varieties characterized by discriminating varieties of eel fry based on a plurality of physical feature points different from each other.   9. The method according to claim 8, wherein one of the physical feature points comprises a ratio of the total length of the eel fry to the width dimension.   10. The method according to claim 8, wherein one of the physical feature points is a distribution state of a melanin pigment formed in a part of a eel fry.   11. The method according to claim 8, wherein one of the physical feature points is a shape, size, or number of strips of eel fry.   12. The method according to claim 8, wherein one of the physical feature points includes a number of bones in a predetermined part of the eel fry.   13. The method for discriminating varieties according to any one of claims 8 to 12, wherein the eel fry is imaged after being put into a pseudo-dead state.   14. The method for discriminating varieties according to any one of claims 8 to 13, wherein fry of eels are conveyed and imaged one by one to an imaging position.

Images