Apparatus and method for identifying individual agricultural products

Abstract

To realize highly accurate discrimination in a label free state, in an individual identification device of an agricultural product and a method.SOLUTION: An individual identification device 1 of an agricultural product comprises: a light source 10 which irradiates an agricultural product 2 with light in a predetermined excitation wavelength of 700nm or less; a camera 20 which captures the agricultural product 2 irradiated with the light source 10; an extraction unit 33 which extracts mottling of the agricultural product 2 from a fluorescent image of the agricultural product 2 captured by the camera 20; a storage unit 40 which stores the mottling for each individual 2 of the agricultural product; and a collation unit 34 which confirms identity of the individual 2 of the agricultural product by collating the mottling stored in the storage unit 40 with newly captured and extracted mottling.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an apparatus and method for identifying individual agricultural products. [Background technology]

[0002] Agricultural products such as vegetables and fruits are sometimes tracked from the production site to the end user, and the identity of each individual agricultural product is confirmed (individual identification). Such individual identification technology is disclosed, for example, in Patent Document 1. Specifically, the technology discloses an individual identification based on information from an identifier such as a contactless tag or barcode attached to each individual agricultural product, and unique information such as biometric information or scratches on the individual agricultural product. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-146570 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, by using the above-mentioned identifier, it is attempted to improve the identification accuracy compared to when only unique information such as biometric information or scars of an individual is used. However, in other words, it is difficult to identify an individual with high accuracy without an identifier or an identifier-like label (label-free), and there is room for improvement.

[0005] An object of the present invention is to provide an apparatus and method for identifying individual agricultural products that achieves label-free, highly accurate identification. [Means for solving the problem]

[0006] A first aspect of the present invention is a light source that irradiates agricultural products with light of a predetermined excitation wavelength of 700 nm or less; an imaging unit that captures an image of the agricultural produce illuminated by the light source; an extraction unit that extracts a pattern of the agricultural product from the fluorescent image of the agricultural product captured by the imaging unit; a storage unit that stores the pattern for each individual agricultural product; a matching unit that verifies the identity of the individual agricultural product by matching the pattern stored in the storage unit with the newly captured and extracted pattern; The present invention provides an individual identification device for agricultural products, comprising:

[0007] This configuration eliminates the need to assign identifiers such as contactless tags or barcodes to individual agricultural products, enabling label-free identification of individual agricultural products. Furthermore, the inventors discovered that capturing fluorescent images using light with an excitation wavelength of 700 nm or less and extracting and matching the variegation of individual agricultural product patterns in the fluorescent images provides higher accuracy in identifying individual agricultural products than extracting and matching the blemishes and shapes of individual agricultural products using light such as a typical white LED. Furthermore, the inventors discovered that individual-specific variegation appears in the fluorescent images. Here, variegation refers to the pattern that appears on the surface of individual agricultural products in the fluorescent images. This variegation varies depending on the growing environment of each individual agricultural product, even within the same species. This is due to differences in the thickness of the cuticle, the density of chlorophyll, the thickness of the cell wall, and other factors between individual agricultural products. These differences result in varying levels of fluorescence response, resulting in the distinctive variegation of each individual. In particular, when an excitation wavelength of 700 nm or less is used, the difference in these patterns becomes more pronounced. Therefore, by matching these patterns, individual agricultural products can be identified with high accuracy. Furthermore, while the target agricultural products are limited to those with distinctive surface shapes and patterns when using general white light, the above configuration is not limited to these and performs matching by generating patterns using a specified excitation wavelength, so a wide variety of agricultural products can be targeted. Note that the pattern matching technology used by the matching unit can utilize image recognition using artificial intelligence.

[0008] The predetermined excitation wavelength may be 500 nm or less.

[0009] This configuration allows for highly accurate identification of characteristic chlorophyll-derived mottle patterns. Chlorophyll-derived mottle patterns often appear strongly when the fluorescence wavelength is in the red region (e.g., 650 to 750 nm). Phenol-derived mottle patterns often appear when the fluorescence wavelength is in the blue to yellow region (e.g., 400 to 580 nm). Therefore, if light with an excitation wavelength longer than 500 nm is irradiated, the excitation wavelength and the fluorescence wavelength will exhibit the same or similar colors. In this case, it may be difficult to identify the mottle patterns in the fluorescence image, potentially reducing identification accuracy. Therefore, to avoid a reduction in identification accuracy, the excitation wavelength may be set to 500 nm or less.

[0010] The storage unit may store agricultural product information which is information regarding the growth of the individual agricultural product having the pattern, The agricultural product information storage device may further include an information reading unit that reads out the agricultural product information from the storage unit when the matching unit confirms the identity of the individual agricultural product.

[0011] This configuration not only identifies individual agricultural products, but also acquires agricultural product information for each identified individual agricultural product. By using such agricultural product information, for example, it is possible to classify agricultural products of the same quality from a mixture of different qualities, enabling sales at appropriate prices according to quality. It also makes it possible to identify production areas with high production capacity for high quality, and accurately reflect complaints about low-quality agricultural products on the production site. This helps strengthen the brand power of agricultural products.

[0012] The agricultural product information may include three-dimensional position information of a location where an individual piece of the agricultural product is growing.

[0013] This configuration makes it possible to pinpoint where agricultural produce was harvested based on three-dimensional location information. Here, the three-dimensional location information may be global location information such as latitude, longitude, and altitude, or local location information such as the distance from the edge of the ridges in the farmland or greenhouse where the produce is grown and the height from the ground. In particular, local location information allows pinpoint feedback to producers on the evaluation of the produce after harvest. Location information can be measured in any manner. For example, a Global Navigation Satellite System (GNSS) or a measuring device that measures horizontal and vertical distances on laid rails may be used.

[0014] The agricultural product information may include the amount of fertilizer applied to each individual agricultural product.

[0015] According to this configuration, the relationship between the quality evaluation of agricultural products after harvest and the amount of fertilizer application can be clarified, and feedback can be provided to producers.

[0016] The agricultural product information may include the amount of solar radiation on each individual agricultural product.

[0017] According to this configuration, the relationship between the quality evaluation of agricultural products after harvest and the amount of solar radiation can be clarified, and feedback can be provided to producers.

[0018] The agricultural product information may include the amount of water irrigation for each individual agricultural product.

[0019] According to this configuration, the relationship between the quality evaluation of agricultural products after harvest and the amount of irrigation water can be clarified, and feedback can be provided to producers.

[0020] The produce information may include a harvest date for the individual produce.

[0021] This configuration allows producers to receive pinpoint feedback on growth results based on harvest dates.

[0022] The matching unit may recognize and match at least one of plane symmetry, mosaic, bright spots, and rubbed patterns as the type of the pattern.

[0023] This configuration can further improve the accuracy of identifying agricultural products. There are several characteristic types of mottle patterns, including plane symmetry, mosaic, light spots, and rubbed patterns. Using these types for classification can improve the success rate of matching. Any method can be used to use these characteristic mottle patterns for classification. For example, weighting can be applied to increase the value of these characteristic mottle patterns in matching, or two-stage matching can be performed by extracting and matching only these characteristic mottle patterns and then matching the entire mottle pattern. Here, plane symmetry refers to mottle patterns that are contrasting on the front and back of the agricultural product, mosaic refers to mottle patterns in which some areas of the agricultural product appear dark, light spots refer to mottled, bright areas of the agricultural product, and rubbed patterns refer to mottle patterns that look like they have been rubbed.

[0024] A second aspect of the present invention is Irradiating agricultural products with light of a predetermined excitation wavelength of 700 nm or less, taking an image of the agricultural product illuminated by the light; extracting patterns of the agricultural product from the captured fluorescent image of the agricultural product; storing the pattern for each individual piece of the agricultural product; The identity of the individual agricultural product is confirmed by comparing the stored pattern with the newly captured and extracted pattern. The present invention provides a method for identifying individual agricultural products, including:

[0025] As mentioned above, this method enables label-free, highly accurate identification by extracting patterns from fluorescent images of agricultural products captured at a specific excitation wavelength.

[0026] The matching may be carried out within 16 days after harvesting of the individual pieces of produce.

[0027] This method allows for individual identification of produce after harvest before the markings change due to growth or deterioration. In particular, the inventors have experimentally confirmed that the markings remain for more than 16 days, making highly accurate identification possible by matching within 16 days. [Effects of the Invention]

[0028] According to the present invention, in an apparatus and method for identifying individual agricultural products, label-free, highly accurate identification can be achieved by extracting patterns from a fluorescent image of the agricultural product captured at a specific excitation wavelength. [Brief explanation of the drawings]

[0029] [Figure 1A] 1 is a schematic diagram of an individual identification device for agricultural products according to an embodiment of the present invention; [Figure 1B] 1B is a perspective view showing an example of how the agricultural product individual identification device of FIG. 1A is used in a farm. FIG. [Figure 2] FIG. 2 is a block diagram of the control unit in FIG. 1. [Figure 3] Fluorescence image of the pattern on agricultural produce illuminated with a light source with an excitation wavelength of 365 nm. [Figure 4] An image of agricultural produce illuminated with a white light source. [Figure 5] 1 is a contour diagram illustrating an excitation-emission matrix. [Figure 6] A contour map of an enlarged area of ​​Figure 5. [Figure 7] 1 is a flowchart of a method for identifying individual agricultural products according to one embodiment of the present invention. [Figure 8] 10 is a graph showing time series changes in the bright area ratio of mottle patterns in a fluorescent image. [Figure 9] Photograph and schematic diagram showing plane symmetry, an example of a type of pattern. [Figure 10] Photograph and schematic diagram showing mosaic, an example of a type of pattern. [Figure 11] Photograph and schematic diagram showing light spots, an example of a type of pattern. [Figure 12] Photographs and schematic diagrams showing rubbing, an example of a type of marking. DETAILED DESCRIPTION OF THE INVENTION

[0030] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

[0031] 1A is a schematic diagram of an individual agricultural product identification device 1 according to an embodiment of the present invention. As will be described in detail later, the individual agricultural product identification device 1 of this embodiment confirms the identity of an individual agricultural product by utilizing the pattern that appears on the agricultural product when illuminated with light of a predetermined excitation wavelength.

[0032] The agricultural product individual identification device 1 of this embodiment has a light source 10, a camera (imaging unit) 20, a control unit 30, a storage unit 40, and an output unit 50.

[0033] Light source 10 irradiates individual pieces of agricultural produce 2 (hereinafter simply referred to as agricultural produce 2) with light of a predetermined excitation wavelength of 700 nm or less. Details of the predetermined excitation wavelength will be described later. However, in practice, it is difficult for light source 11 to irradiate light having only a single wavelength (frequency). Therefore, light source 11 can irradiate light of wavelengths that follow a normal distribution with one predetermined wavelength as the mean wavelength, for example. In this embodiment, two light sources 10 are provided, and are installed symmetrically with respect to agricultural produce 2.

[0034] Camera 20 captures an image of agricultural produce 2. Camera 20 is installed vertically above agricultural produce 2, between light sources 10. Images of agricultural produce 2 may be captured multiple times by changing the orientation of agricultural produce 2.

[0035] In this embodiment, the relative positions of the agricultural produce 2, light source 10, and camera 20 are fixed. That is, the height of light source 10, the height of camera 20, and the illumination angle θ of light source 10 from the vertical direction relative to the agricultural produce 2 are all fixed. Such a fixed arrangement allows images to be captured under the same conditions with high reproducibility, but there are cases where a fixed arrangement is not necessary, such as in the example of use on a farm described below.

[0036] 1B is a perspective view showing an example of how the agricultural product individual identification device 1 is used in a farm. In FIG. 1B, Manganji peppers grown in multiple rows of furrows are shown as the agricultural product 2.

[0037] 1B, when agricultural product individual identification device 1 is used on a farm, it may be supported by a movable support mechanism 22 that runs on rails 21 laid on the ground. Support mechanism 22 may be extendable and adjustable in height. In the illustrated example, agricultural product individual identification device 1 also has a white light source 11 that emits white light in addition to a light source 10 that emits light with a predetermined excitation wavelength.

[0038] The device 1 for identifying individual agricultural products 2 moves on rails 21 while adjusting its height between multiple rows of ridges, and captures images of the growing agricultural products 2 while irradiating them with light of a predetermined excitation wavelength. Alternatively, the device 1 may capture images of the growing agricultural products 2 while irradiating them with white light, as needed. The captured fluorescent images and the like are transmitted to a control unit 30 installed in a separate location.

[0039] The control unit 30 performs arithmetic processing and controls the entire device. The control unit 30 is composed of hardware such as a CPU (Central Processing Unit), RAM (Random Access Memory), and ROM (Read Only Memory), and software such as programs installed on these. The control unit 30 can be composed of an information processing device such as a desktop computer, a laptop computer, a workstation, or a tablet terminal.

[0040] The storage unit 40 is a storage medium that stores programs, data, and the like required to realize the functions of the control unit 30. The storage unit 40 may be configured integrally with the control unit 30.

[0041] The output unit 50 is a component that displays the processing results of the control unit 30, and is configured by, for example, a liquid crystal display, an organic EL display, or a plasma display.

[0042] FIG. 2 is a block diagram of the control unit 30 in this embodiment.

[0043] The control unit 30 includes, as functional components, a light source operation unit 31, a camera operation unit 32, an extraction unit 33, and a matching unit 34. These are realized by the cooperation of the above hardware and software.

[0044] The light source control unit 31 controls the light source 10 so that it irradiates light of a predetermined excitation wavelength onto the agricultural produce 2. In this embodiment, as described above, the light source 10 irradiates light of a predetermined excitation wavelength, and therefore the light source control unit 31 simply controls the ON / OFF of the light source 10. However, if the excitation wavelength of the light source 10 is adjustable, the light source control unit 31 may also control the setting of the predetermined excitation wavelength.

[0045] Camera operation unit 32 controls camera 20 to capture an image of agricultural produce 2 illuminated by light source 10. In this way, a fluorescent image of agricultural produce 2 is acquired.

[0046] The extraction unit 33 extracts the mottle pattern of the agricultural produce 2 from the fluorescent image of the agricultural produce 2 captured by the camera 20. The extraction unit 33 extracts the outline of the agricultural produce 2 by image recognition and extracts the mottle pattern for each agricultural produce 2. Here, the mottle pattern refers to the pattern that appears on the surface of the agricultural produce 2 in the fluorescent image. The mottle pattern becomes distinctive for each individual produce due to various factors. For example, various factors can be considered, such as differences due to the growing environment of the agricultural produce 2, or the way pollen, petals, etc. adhere to the surface of the agricultural produce 2.

[0047] Fig. 3 is a fluorescent image of the mottle pattern of agricultural produce 2 illuminated by light source 10 with an excitation wavelength of 365 nm. Also, as a comparison example, although different from the present embodiment, Fig. 4 is an image of agricultural produce 2 illuminated by a white light source.

[0048] Figures 3 and 4 show manganji peppers as an example of agricultural product 2. Comparing Figures 3 and 4, it can be seen that the mottling of agricultural product 2, which cannot be seen with a general white light source in Figure 4, can be seen in Figure 3. For example, in Figure 3, characteristic bright spots can be seen as the mottling of agricultural product 2.

[0049] 3, the predetermined excitation wavelength of light source 10 for producing characteristic mottle patterns on agricultural produce 2 may vary for each agricultural product 2. In this embodiment, the predetermined excitation wavelength of light source 10 may be set to a predetermined value of 700 nm or less. This is because, as a result of conducting experiments using light sources 10 with various excitation wavelengths, it was found that mottle patterns could be observed relatively clearly when a light source 10 with an excitation wavelength of 700 nm or less was used.

[0050] Furthermore, the value of the excitation wavelength below 700 nm can be determined based on the excitation fluorescence matrix.

[0051] Fig. 5 is a contour diagram illustrating an excitation-emission matrix, and Fig. 6 is a contour diagram in which a partial area of ​​Fig. 5 is enlarged.

[0052] In the excitation fluorescence matrices in Figures 5 and 6, the horizontal axis represents the fluorescence wavelength (nm) and the vertical axis represents the excitation wavelength (nm), and the fluorescence intensity is indicated by the shading in the figures. Specifically, the darker the area, the lower the fluorescence intensity, and the whiter the area, the higher the fluorescence intensity.

[0053] The excitation wavelength of the light source 10 can be set to one that produces a relatively large fluorescence intensity in the excitation fluorescence matrix. In particular, the excitation wavelength may be set to 500 nm or less. This allows for highly accurate identification of characteristic chlorophyll-derived mottle patterns. Chlorophyll-derived mottle patterns often appear strongly in the red fluorescence wavelength range (e.g., 650 to 750 nm) (see white region A in Figure 5). Therefore, if light with an excitation wavelength longer than 500 nm is irradiated, the excitation wavelength and the fluorescence wavelength will exhibit the same or similar colors. In this case, it may be difficult to identify the mottle patterns in the fluorescence image, potentially reducing identification accuracy. Therefore, to avoid a reduction in identification accuracy, the excitation wavelength may be set to 500 nm or less.

[0054] 6, specifically, an excitation wavelength at point P1 (for example, about 350 nm) that exhibits a relatively high fluorescence intensity may be employed. By employing an excitation wavelength that exhibits a high fluorescence intensity in this manner, the mottle pattern becomes clearer, and an improvement in the success rate of matching is expected.

[0055] The markings produced by illumination with light of a predetermined excitation wavelength, which can be determined as described above, are extracted by extraction unit 33 and stored in memory unit 40 together with the fluorescent image. The markings and fluorescent images stored in memory unit 40 are those of agricultural produce 2 immediately after harvest or during growth and close to harvest. If the produce is growing, for example, markings (fluorescent images) from two directions, the front and back, of agricultural produce 2 may be acquired and stored. If the produce is immediately after harvest, for example, markings (fluorescent images) from four directions, the front, back, left side, and right side, of agricultural produce 2 may be acquired and stored. In this way, by acquiring images taken from multiple directions, it may be possible to identify individual organisms 2 later based on images taken from fewer directions (for example, one direction).

[0056] The matching unit 34 verifies the identity of the agricultural produce 2 by matching the newly captured and extracted pattern with the pattern stored in the memory unit 40. The newly captured image and extracted pattern can be captured and extracted at any time during the growth of the agricultural produce 2 or during the distribution process after harvest of the agricultural produce 2. For example, any time during the distribution process after harvest of the agricultural produce 2 could be while the agricultural produce 2 is stored in a warehouse before transportation, while in transportation, or while the agricultural produce 2 is stored or sold at a retail store after transportation. If the agricultural produce 2 is growing, for example, pattern (fluorescent images) may be acquired from two directions, the front and back of the agricultural produce 2. Furthermore, if the agricultural produce 2 is harvested, pattern (fluorescent images) may be acquired from four directions, for example, the front, back, left side, and right side of the agricultural produce 2. The matching unit 34's pattern matching technology may utilize image recognition using artificial intelligence.

[0057] Preferably, the memory unit 40 stores agricultural product information about the mottled agricultural product 2, and the control unit 30 includes an information reading unit 35. Here, agricultural product information broadly refers to information about the growth of the agricultural product 2, and includes, for example, the producer, the place of production, or environmental information related to quality. The information reading unit 35 reads the agricultural product information from the memory unit 40 when the matching unit 34 confirms the identity of the agricultural product 2.

[0058] The agricultural product information may include three-dimensional location information of the area where the agricultural product 2 is growing. This allows pinpointing the location where the agricultural product 2 was harvested based on the three-dimensional location information. Therefore, pinpoint feedback of the evaluation of the agricultural product 2 after harvest can be provided to the producer. Here, the three-dimensional location information may be global location information such as latitude, longitude, and altitude, or local location information such as the distance from the edge of the ridge in the farmland or greenhouse where the agricultural product 2 is produced and the height from the ground. In particular, the local location information allows pinpoint feedback of the evaluation of the agricultural product 2 after harvest to the producer. The location information can be measured in any manner. For example, a global positioning system (GPS) or a global navigation satellite system (GNSS) may be used, or a measuring device may be used to measure the horizontal distance on the installed rail 21 (see FIG. 1B) and the vertical distance from the ground of the support mechanism 22 (FIG. 1B).

[0059] The agricultural product information may include the amount of fertilizer applied to the agricultural product 2. This makes it possible to clarify the relationship between the quality evaluation of the agricultural product 2 after harvest and the amount of fertilizer applied, and provides feedback to the producer.

[0060] The agricultural product information may include the amount of solar radiation on the agricultural product 2. This makes it possible to clarify the relationship between the amount of solar radiation and the quality evaluation of the agricultural product 2 after harvest, and to provide feedback to the producer.

[0061] The agricultural product information may include the amount of water irrigated to the agricultural product 2. This makes it possible to clarify the relationship between the quality evaluation of the agricultural product 2 after harvest and the amount of water irrigated, and provides feedback to the producer.

[0062] The agricultural product information may include the harvest date of the agricultural product 2. This allows pinpoint feedback of growth results based on the harvest date to the producer.

[0063] 7 is a flowchart of the agricultural product individual identification method according to this embodiment. It can be said that the agricultural product individual identification device 1 according to this embodiment executes this method.

[0064] When the method is started, the light source control unit 31 controls the light source 10 to irradiate the agricultural product 2 with light of a predetermined excitation wavelength (step S7-1). This predetermined excitation wavelength is determined in advance by checking the excitation fluorescence matrix for each agricultural product 2 as described above. Next, the camera control unit 32 controls the camera 20 to capture a fluorescent image of the agricultural product 2 (step S7-2). Next, the extraction unit 33 extracts the pattern of the agricultural product 2 from the fluorescent image (step S7-3). Next, the comparison unit 34 compares the pattern with the pattern stored in the memory unit 40 to confirm the identity of the individual agricultural product 2 (step S7-4).

[0065] When the matching unit 34 confirms the identity of the agricultural produce 2 (Y: step S7-4), the information reading unit 35 reads the agricultural produce information from the memory unit 40 (step S7-5). Then, the matching result (the agricultural produce is the same) and the agricultural produce information are output to the output unit 50 (step S7-6). Note that the agricultural produce individual identification device 1 does not need to have the information reading unit 35, in which case the information reading process (step S7-5) is omitted and only the matching result is output to the output unit 50.

[0066] Furthermore, if the matching unit 34 does not confirm the identity of the agricultural produce 2 (N: step S7-4), the matching result (the agricultural produce is not identical) is output to the output unit 50 (step S7-6). When the above processing is completed, the method for identifying individual agricultural produce 2 of this embodiment ends.

[0067] Next, a simple comparative experiment between this embodiment and the conventional method will be described, using Manganji peppers as an example of agricultural product 2.

[0068] As a conventional method, shape matching using a general white LED light source was used for comparison. In the experiment, 50 Mangetsuji peppers were prepared and the matching results were confirmed. The success rate, which indicates correct matching, was 4% for the conventional method, while it was 58% for this embodiment. Because this was a simple experiment, there is room for further improvement in the success rate, but it at least confirmed the superiority of this embodiment. When the pattern matching technology of this embodiment and the conventional shape matching technology were used together, the success rate was 70%. Therefore, they may be used in combination.

[0069] We also explain an experiment conducted to confirm the time-series changes in the markings of agricultural products after harvest.

[0070] In the experiment, we calculated the bright area ratio in a fluorescence image taken by irradiating Manganji peppers (agricultural product 2) with light of an excitation wavelength of 365 nm. The bright area ratio is the area ratio of bright areas with strong fluorescence above a certain threshold to the total area of ​​the Manganji pepper in the fluorescence image.

[0071] FIG. 8 is a graph showing the time series change in the bright area ratio of the mottle pattern in the fluorescent image.

[0072] Referring to Figure 8, the horizontal axis represents time (days) and the vertical axis represents the bright area ratio. Experiments were conducted using 10 Manganji peppers, and it was found that there was almost no change in the bright area ratio until about 8 days after harvest, and that the variegation did not change significantly until at least about 8 days. However, after 16 days from harvest, some peppers showed changes in the bright area ratio. This suggests that the success rate of variegation matching may decrease if the time exceeds 16 days from harvest. Therefore, variegation matching should preferably be performed within 16 days after harvest, and more preferably within 8 days.

[0073] According to this embodiment, there is no need to attach an identifier such as a contactless tag or barcode to each individual piece of agricultural product 2; that is, each individual piece of agricultural product 2 can be identified label-free. Furthermore, the inventors discovered that when light with an excitation wavelength of 700 nm or less is used to extract and compare the markings of each individual piece of agricultural product 2, the individual pieces of agricultural product 2 can be identified with higher accuracy than when light such as a general white LED is used to extract and compare the damage and shape of each individual piece of agricultural product 2. These markings vary depending on the growing environment of each individual piece of agricultural product, even among the same species. This is due to differences in the thickness of the cuticle layer, the density of chlorophyll, the thickness of the cell wall, and other characteristics that vary from piece to piece. These differences result in stronger or weaker fluorescent reactions, resulting in the creation of distinctive markings for each individual piece of agricultural product. These differences are particularly pronounced when an excitation wavelength of 700 nm or less is used. Therefore, by comparing these markings, each individual piece of agricultural product 2 can be identified with high accuracy. Furthermore, when it comes to the target agricultural products 2, while typical white light is limited to those with distinctive surface shapes and patterns, in this embodiment, matching is performed by generating patterns using a specified excitation wavelength, without being limited to these, so a wide variety of agricultural products 2 can be targeted.

[0074] Furthermore, in this embodiment, not only can the individual agricultural products 2 be identified, but also agricultural product information for the identified individual agricultural products 2 can be obtained. By using the agricultural product information, for example, it is possible to classify individual agricultural products 2 of the same quality from a mixture of various qualities, and sell them at a fair price according to their quality. It is also possible to identify production areas with high production capacity for high quality, and accurately reflect complaints about low-quality agricultural products on the production site. This makes it possible to strengthen the brand power of the agricultural products 2.

[0075] Furthermore, the matching unit 34 may recognize and match at least one of the following types of mottle: plane symmetry, mosaic, bright spots, and rubbed.

[0076] Figures 9 to 12 are photographs and schematic diagrams showing examples of the types of markings: symmetry, mosaic, bright spots, and rubbing. In each figure, the left side shows the photograph, and the right side shows the schematic diagram. The photographs in each figure were taken from two directions, the front and the back, and the characteristic markings are particularly evident in the areas enclosed by rectangles. Figures 9 to 12 use Manganji chili peppers as an example of agricultural product 2.

[0077] Planar symmetry refers to contrasting patterns on the front and back of the produce 2, mosaic refers to a pattern in which some areas of the produce 2 appear dark, light spots refers to a pattern in which parts of the produce 2 appear bright in spots, and rubbed refers to a pattern that looks like it has been rubbed. These are characteristic patterns and can be information that can be useful in identifying patterns.

[0078] Identifying the above-mentioned characteristic types of markings can further improve the accuracy of identifying the agricultural products 2. The method of using these characteristic types of markings for classification is arbitrary, but for example, weighting may be applied to increase the value of matching these characteristic types of markings, or two-stage matching may be performed in which only these characteristic markings are extracted and matched, and then the entire markings are matched.

[0079] The agricultural product individual identification device 1 of the above embodiment may take various forms. For example, it may be configured as a mobile device equipped with the above-described components, or may be configured to be built into a home appliance such as a refrigerator. It may also be configured as an optional part that can be attached to a smartphone.

[0080] While specific embodiments and variations of the present invention have been described above, the present invention is not limited to the above embodiments and can be implemented with various modifications within the scope of the present invention. For example, agricultural product 2 may be fruit vegetables, beans, or fruits in general, in addition to manganji peppers. Since these are expected to develop characteristic markings on individual individuals, similar to manganji peppers, they can be broadly included as agricultural product 2.

[0081] The agricultural product information may also include the following: For example, greenhouse identification number, agricultural product variety, planted area, number of plants planted, number of plants trained, harvest yield, plowing date, ridge making date, mulching date, planting date, fertilization date, pesticide application date, pruning date, fruit thinning date, topping date, soil quality, soil hydrogen ion concentration (pH), soil electrical conductivity (EC), soil moisture, soil temperature, ambient temperature, relative humidity, saturation deficit, carbon dioxide concentration, air pressure, wind speed, wind direction, agricultural product diseases, pest information, leaf color, internode length, and number of nodes. Agricultural product information may include number of branches, flowering date, number of flowers, fruit set date, number of fruits, fruit color, fruit length, fruit shape, photosynthetic activity, transpiration, xylem flow, water content, row identification number, harvest time, blemishes on the agricultural product, hardness, sugar content, acidity, acceleration, transport container, means of transport, packing method, transport time, transport distance, quantity received, quantity sold, quantity discarded, temperature during transport, weather during transport, shelf temperature, shelf time, sale date, price, taste, or freshness. [Explanation of symbols]

[0082] 1. Agricultural product individual identification device 2. Agricultural products (individual agricultural products) 10 light source 11 White light source 20 Camera (imaging unit) 21 Rail 22 Support mechanism 30 Control Unit 31 Light source operation section 32 Camera control section 33 Extraction part 34 Matching unit 35 Information reading section 40 Storage section 50 Output section

Claims

1. a light source that irradiates agricultural products with light of a predetermined excitation wavelength of 260 nm or more and 700 nm or less, the wavelength of which follows a normal distribution with one predetermined wavelength as an average wavelength; an imaging unit that captures an image of the agricultural produce illuminated by the light source; an extraction unit that extracts a pattern of the agricultural product from the fluorescent image of the agricultural product captured by the imaging unit; a storage unit that stores the pattern for each individual agricultural product; a matching unit that verifies the identity of the individual agricultural product by matching the pattern stored in the storage unit with the newly captured and extracted pattern; Equipped with The average wavelength is set to be shorter than the fluorescent wavelength of the agricultural product and to be such that the fluorescent intensity of the agricultural product exhibits a relatively large value.

2. The agricultural product individual identification device according to claim 1 , wherein the predetermined excitation wavelength is 500 nm or less.

3. the storage unit stores agricultural product information that is information regarding the growth of the individual agricultural product having the pattern; 3. The agricultural product individual identification device according to claim 1, further comprising an information reading unit that reads the agricultural product information from the storage unit when the matching unit confirms the identity of the individual agricultural product.

4. The agricultural product individual identification device according to claim 3 , wherein the agricultural product information includes three-dimensional position information of a location where the individual agricultural product is growing.

5. The agricultural product individual identification device according to claim 3 or 4, wherein the agricultural product information includes an amount of fertilizer applied to the individual agricultural product.

6. The agricultural product individual identification device according to claim 3 , wherein the agricultural product information includes an amount of solar radiation applied to the individual agricultural product.

7. The agricultural product individual identification device according to claim 3 , wherein the agricultural product information includes an amount of water irrigation for the individual agricultural product.

8. The agricultural product individual identification device according to claim 3 , wherein the agricultural product information includes a harvest date of the individual agricultural product.

9. The agricultural product individual identification device according to claim 1 , wherein the matching unit recognizes and matches at least one of the following types of pattern: plane symmetry, mosaic, bright spots, and rubbed.

10. Irradiating the agricultural produce with light having a predetermined excitation wavelength of 260 nm or more and 700 nm or less, the wavelength of which follows a normal distribution with one predetermined wavelength as the mean wavelength; taking an image of the agricultural product illuminated by the light; extracting patterns of the agricultural product from the captured fluorescent image of the agricultural product; storing the pattern for each individual piece of the agricultural product; The identity of the individual agricultural product is confirmed by comparing the stored pattern with the newly captured and extracted pattern. This includes: A method for identifying individual agricultural products, wherein the average wavelength is set to be shorter than the fluorescent wavelength of the agricultural product and to be such that the fluorescent intensity of the agricultural product exhibits a relatively large value.

11. The method for identifying individual agricultural products according to claim 10, wherein the matching is performed within 16 days after the individual agricultural products are harvested.

Images