Plant quality evaluation support program, plant quality evaluation support device, plant quality evaluation support method, and recording medium, as well as plant selection program, plant selection device, plant selection method, and recording medium

Abstract

To provide a plant quality evaluation support program that allows easy estimation of plant quality grades.SOLUTION: A plant quality evaluation support program disclosed herein includes a plant image acquisition step, a part detection step, a part score estimation step, and a quality grade evaluation step. The plant image acquisition step acquires a plant image of the plant. The part detection step detects at least one plant part from the plant image. The part score estimation step estimates a part score for the plant part. The quality grade evaluation step evaluates the quality grade of the plant based on the part score and an evaluation criterion.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a plant quality evaluation support program, a plant quality evaluation support device, a plant quality evaluation support method, a recording medium, a plant sorting program, a plant sorting device, a plant sorting method, and a recording medium.

Background Art

[0002] In the shipment of foliage plants, the foliage plants are classified into grades based on information such as weight and length, and sorting and bundling are performed. At this time, for example, a flower selection unit that sorts flowers by grade, a conveyor for carrying out flowers on which the selected flowers are accumulated by a predetermined number, a transfer means that holds and picks up the flowers carried out by this conveyor with a holding arm that can be opened and closed, a bundling device that bundles the flowers transferred by the transfer means, and a moving mechanism that moves the transfer means between the conveyor and the bundling device. A flower processing device is provided with a stopper at the front of the conveyor against which the tip of the flower carried out by the conveyor hits, and a hitting member that reduces the distribution width of the flowers carried out by the conveyor. A flower processing device is known in which a bundle of flowers with a reduced distribution width by this hitting member is held and picked up by the holding arm of the transfer means (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the flower processing device of Patent Document 1, flowers can be sorted by weight, but in the sorting of flowers, in addition to weight, it is necessary to select a quality grade by evaluating the appearance of the flowers. Such appearance evaluation depends on the judgment of an expert at the flower selection site, and there are problems such as high personal dependence and time-consuming.

[0005] Therefore, the present disclosure aims to provide a plant quality evaluation support program, a plant quality evaluation support device, a plant quality evaluation support method, a recording medium, a plant sorting program, a plant sorting device, a plant sorting method, and a recording medium that can easily estimate the quality grade of plants.

Means for Solving the Problems

[0006] To achieve the above object, the plant quality evaluation support program of the present disclosure includes a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure, the plant image acquisition procedure acquires a plant image obtained by imaging a plant, the part detection procedure detects at least one type of plant part for the plant from the plant image, the part score estimation procedure estimates the part score of the plant part, the quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and an evaluation criterion, and is a plant quality evaluation support program for causing a computer to execute each of the above procedures.

[0007] The plant quality evaluation support device of the present disclosure includes a plant image acquisition unit, a part detection unit, a part score estimation unit, and a quality grade evaluation unit, the plant image acquisition unit acquires a plant image obtained by imaging a plant, the part detection unit detects at least one type of plant part for the plant from the plant image, the part score estimation unit estimates the part score of the plant part, and the quality grade evaluation unit evaluates the quality grade of the plant based on the part score and an evaluation criterion.

[0008] The plant quality evaluation support method of the present disclosure includes a plant image acquisition step, a part detection step, a part score estimation step, and a quality grade evaluation step, The plant image acquisition step acquires a plant image obtained by imaging a plant, The part detection step detects at least one type of plant part for the plant from the plant image, The part score estimation step estimates the part score of the plant part, The quality grade evaluation step evaluates the quality grade of the plant based on the part score and evaluation criteria, Each of the above steps is a method executed by a computer.

[0009] The recording medium of the present invention includes a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure, The plant image acquisition procedure acquires a plant image obtained by imaging a plant, The part detection procedure detects at least one type of plant part for the plant from the plant image, The part score estimation procedure estimates the part score of the plant part, The quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and evaluation criteria, It is a computer-readable recording medium recording a plant quality evaluation support program for causing a computer to execute each of the above procedures.

[0010] The plant sorting program of the present disclosure includes a quality evaluation procedure and a sorting procedure, The quality evaluation procedure is a procedure for evaluating the quality grade of a plant and includes each procedure of the plant quality evaluation support program of the present disclosure, The sorting procedure sorts the plants based on the quality grade, It is a plant sorting program for causing a computer to execute each of the above procedures.

[0011] The plant sorting device of the present disclosure includes a quality evaluation unit and a sorting unit, The quality evaluation unit evaluates the quality grade of a plant and includes the plant quality evaluation support device of the present disclosure, The sorting unit sorts the plants based on the quality grade.

[0012] The plant sorting method of the present disclosure includes a quality evaluation step and a sorting step, wherein the quality evaluation step is a step of evaluating the quality grade of the plant, and includes each step of the plant quality evaluation support method of the present disclosure, and the sorting step sorts the plants based on the quality grade.

[0013] The recording medium of the present disclosure includes a quality evaluation procedure and a sorting procedure, wherein the quality evaluation procedure is a procedure for evaluating the quality grade of the plant, and includes each procedure of the plant quality evaluation support program of the present disclosure, and the sorting procedure sorts the plants based on the quality grade, and is a computer-readable recording medium recording a plant sorting program for causing a computer to execute each of the procedures.

Advantages of the Invention

[0014] According to the present disclosure, the quality requirements of plants can be easily estimated.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Mode for Carrying Out the Invention

[0016] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The present disclosure is not limited to the following embodiments. In the following figures, the same parts are denoted by the same reference numerals. Also, unless otherwise specified, the descriptions of the respective embodiments can be mutually referred to, and the configurations of the respective embodiments can be combined unless otherwise specified. Note that in the present disclosure, each drawing may apply to one or more embodiments.

[0017] In the present disclosure, the “plant” is not particularly limited, and for example, it may be a flower mainly for ornamental purposes, or an ornamental plant mainly for viewing leaves. The plant may be, for example, a terrestrial plant or an aquatic plant (so-called waterweed). Also, the plant may, for example, contain an edible part or may not contain it. The plant may be, for example, a plant that is not included in at least one of vegetables and fruits.

[0018] [Embodiment 1] The plant quality evaluation support program of the present disclosure is a program for causing a computer to execute a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure. The plant quality evaluation support program of the present disclosure can also be said to be a program that causes a computer to function as a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure. Further, the plant quality evaluation support program of the present disclosure can also be said to be a program for causing a computer to execute each step of the plant quality evaluation support method described later, for example.

[0019] The plant image acquisition procedure acquires a plant image obtained by imaging a plant, The part detection procedure detects at least one type of plant part for the plant from the plant image, The part score estimation procedure estimates the part score of the plant part, The quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and the evaluation criteria.

[0020] Each of the above procedures can be read as "processing" instead of "procedure", for example. Also, the plant quality evaluation support program of the present disclosure may be recorded on a computer-readable recording medium, for example. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples include random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., solid state drive (SSD), USB flash memory, SD / SDHC card, etc.), optical disk (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy (registered trademark) disk (FD), etc. Further, the plant quality evaluation support program of the present disclosure (also referred to as a programming product or a program product, for example) may be in a form distributed from an external computer, for example. The "distribution" may be, for example, distribution via a communication line network or distribution via a device connected by wire. The plant quality evaluation support program of the present disclosure may be installed and executed on the distributed device, or may be executed without being installed. The information processing device capable of executing the plant quality evaluation support program of the present disclosure can be referred to as the plant quality evaluation support device of the present disclosure, for example.

[0021] Next, a configuration example of the plant quality evaluation support device of the present disclosure will be described with reference to FIG. 1. FIG. 1 is a block diagram showing a configuration example of the plant quality evaluation support device 10 (hereinafter also referred to as the present device 10) of the present disclosure. As shown in FIG. 1, the present device 10 includes a plant image acquisition unit 11, a part detection unit 12, a part score estimation unit 13, and a quality grade evaluation unit 14. Further, although not shown, the present device 10 may include, for example, an input unit, an output unit, a display unit, and / or a storage unit. The plant image acquisition unit 11, the part detection unit 12, the part score estimation unit 13, and the quality grade evaluation unit 14 can each execute, for example, the plant image acquisition procedure, the part detection procedure, the part score estimation procedure, and the quality grade evaluation procedure in the plant quality evaluation support program of the present disclosure.

[0022] The device 10 may be, for example, one device including the above-described respective parts, or the respective parts may be devices connectable via a communication line network. Further, the device 10 can be connected to an external device described later via the communication line network. The communication line network is not particularly limited, and a known network can be used. For example, it may be wired or wireless. Examples of the communication line network include an Internet line, WWW (World Wide Web), a telephone line, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (local 5G), and the like. Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), local 5G, LPWA, and the like. The wireless communication may be in a form in which each device communicates directly (Ad Hoc communication), infrastructure communication, indirect communication via an access point, or the like. The device 10 may be incorporated into a server as a system, for example. Further, the device 10 may be, for example, a personal computer (PC, for example, a desktop type or a notebook type) installed with the program of the present disclosure, a smartphone, a tablet terminal, or the like. The device 10 may be in a form such as cloud computing or edge computing, for example, in which at least one of the above-described respective parts is on a server and the other respective parts are on a terminal.

[0023] FIG. 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, an output device 106, a communication device 107, and the like. Each part of the device 10 is mutually connected via the bus 103 by respective interfaces (I / F).

[0024] The central processing unit 101 cooperates with other components under the control of a controller (such as a system controller, an I / O controller, etc.) to undertake the overall control of the apparatus 10. In the apparatus 10, the central processing unit 101 executes, for example, the program of the present disclosure (the plant quality evaluation support program) and other programs, and reads and writes various information. Specifically, for example, the central processing unit 101 functions as a plant image acquisition unit 11, a part detection unit 12, a part score estimation unit 13, and a quality grade evaluation unit 14. The apparatus 10 may be equipped with other arithmetic units such as a CPU, a GPU (Graphics Processing Unit), and an APU (Accelerated Processing Unit) as arithmetic units, or may be equipped with a combination thereof.

[0025] The bus 103 can be connected to, for example, an external device. Examples of the external device include an external storage device (such as an external database), a printer, an external input device, an external display device, an external imaging device, etc. The apparatus 10 can be connected to an external network (the communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0026] The memory 102 is, for example, a main memory (primary storage device). When the central processing unit 101 performs processing, for example, the memory 102 reads various operation programs such as the program of the present disclosure stored in the storage device 104 described later, and the central processing unit 101 receives data from the memory 102 and executes the program. The main memory is, for example, a RAM (Random Access Memory). Also, the memory 102 may be, for example, a ROM (Read Only Memory).

[0027] The memory device 104 is, for example, also referred to as a so-called auxiliary storage device with respect to the main memory (primary storage device). As described above, an operation program including the program of the present disclosure is stored in the memory device 104. The memory device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited, and may be, for example, an internal type or an external type, and examples include an HD (hard disk), a CD-ROM, a CD-R, a CD-RW, an MO, a DVD, a flash memory, a memory card, and the like. The memory device 104 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, and a solid state drive (SSD). When the apparatus 10 includes the storage unit, for example, the memory device 104 functions as the storage unit. The storage unit can record information such as plant images, plant attribute information, reference evaluation points, stem score evaluation models, flower score evaluation models, leaf score evaluation models, and evaluation criteria, which will be described later.

[0028] In the present apparatus 10, the memory 102 and the memory device 104 can also store various types of information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present apparatus 10, and information used when the present apparatus 10 executes processing. In this case, the memory 102 and the memory device 104 may store, for example, information of the user of the present apparatus described above. Note that at least a part of the information may be stored in an external server other than the memory 102 and the memory device 104, or may be distributed and stored in a plurality of terminals using blockchain technology or the like.

[0029] The device 10 further includes, for example, an input device 105 and an output device 106. The input device 105 includes, for example, pointing devices such as a touch panel, a track pad, and a mouse; a keyboard; imaging means such as a camera and a scanner; card readers such as an IC card reader and a magnetic card reader; voice input means such as a microphone; and the like. The output device 106 includes, for example, display devices such as an LED display and a liquid crystal display; voice output devices such as a speaker; a printer; and the like. In the first embodiment, the input device 105 and the output device 106 are separately configured, but the input device 105 and the output device 106 may be integrally configured like a touch panel display.

[0030] An example of the processing by the plant quality evaluation support program of the present disclosure will be further specifically described with reference to FIG. 3. FIG. 3 is a flowchart showing an example of each step of the plant quality evaluation support program of the present disclosure.

[0031] The plant image acquisition unit 11 acquires a plant image obtained by imaging a plant (S1, plant image acquisition procedure). The plant image acquisition unit 11 may, for example, acquire a plant image by imaging the plant with an imaging device such as a camera included in the present apparatus 10, may acquire the plant image from an imaging device outside the present apparatus, or may acquire the plant image from a recording medium on which the plant image is recorded. The plant image acquisition unit 11 may acquire, for example, one plant image or may acquire two or more plant images. The plant image may be, for example, a moving image or a still image. The plant image may be an image that has already been imaged or a preview image of imaging. The plant image acquisition unit 11 may record the acquired plant image in the storage unit of the present apparatus 10. An example of a method for imaging a plant image will be described with reference to FIG. 4, but the present disclosure is not limited to the example shown in FIG. 4. As shown in FIG. 4(A), first, the plant (flowering plant) 2 is arranged at an angle close to horizontal with respect to the imaging location, and the entire plant 2 is imaged by the imaging device 1 from above the plant 2, whereby a plant image can be imaged. FIG. 4(B) shows an example of the imaged plant image. The plant image may be, as described above, an image obtained by imaging a plant, and the imaging angle, imaging method, imaging distance, etc. are not particularly limited. The imaging device 1 is not particularly limited as long as it is a device capable of imaging a plant image. For example, it may be a general camera that uses visible light, may be a camera that uses light rays other than visible light (e.g., infrared rays, X-rays, etc.), or may be a device that includes a plurality of these functions.

[0032] The plant part detection unit 12 detects at least one type of plant part for the plant from the plant image (S2, plant part detection procedure). The plant part detection unit 12 can detect at least one type of plant part from the plant image by using, for example, a known object identification and detection method. The object identification and detection method is not particularly limited, and examples include various image segmentations such as semantic segmentation, instance segmentation, and panoptic segmentation; HOG (Histogram of Oriented Gradients); YOLO (You Only Look Once); R-CNN (Regions with Convolutional Neural Network); SSD (Single Shot MultiBox Detector); DCN (Deformable Convolution Network); and the like. The plant part detection unit 12 can detect at least one type of plant part selected from the group consisting of the stem, flower, and leaf of the plant by detecting the region of the plant part in the plant image in pixel units using an object detection method such as the image segmentation. The plant part detection unit 12 may, for example, display the detected plant part in an identifiable manner. Specifically, for example, in the plant image, pixel regions indicating the stem region, flower region, and leaf region may be separated by a bounding box or the like.

[0033] The plant part score estimation unit 13 estimates the part score of the plant part (S3, part score estimation procedure). The plant part score estimation unit 13 can estimate, for example, at least one score selected from the group consisting of a stem score, a flower score, and a leaf score as the part score. The stem score is, for example, an index indicating the quality of the stem part of the plant. The flower score is, for example, an index indicating the quality of the flower part of the plant. The stem score, the flower score, and the leaf score can be expressed, for example, in multiple levels from 0 to n (n is an integer of 1 or more). In the following description, as a specific example, the case where the stem score, the flower score, and the leaf score are evaluated in 11 levels from 0 to 10 will be described as an example, but the present disclosure is not limited to the following examples. The leaf score is, for example, an index indicating the quality of the leaf part of the plant. The method for estimating the stem score, the flower score, and the leaf score will be described later.

[0034] In S2, when the stem is detected as the plant part, the plant part score estimation unit 13 estimates, for example, the stem score of the stem of the plant as the part score. In this case, the plant part score estimation unit 13 estimates, for example, at least one selected from the group consisting of a stem shape score, a stem size score, and a stem damage score, and can estimate the stem score based on the shape score, the size score, and the damage score. The plant part score estimation unit 13 may estimate, for example, the average value of the shape score, the size score, and the damage score as the stem score. At this time, the plant part score estimation unit 13 may estimate the stem score by weighted average for the shape score, the size score, and the damage score. The weights of the shape score, the size score, and the damage score are not particularly limited, and for example, any value can be set. The weights of the shape score, the size score, and the damage score may be recorded, for example, in the storage unit of the present device 10, or may be recorded in an external storage device outside the device.

[0035] The shape score of the stem is, for example, an index for evaluating the shape of the stem. The shape may include, for example, the degree of bending of the stem. As the method for evaluating the degree of bending, an appropriate evaluation method according to the type of the plant can be adopted. The shape score may, for example, give a high evaluation when the stem is close to a straight line, or may give a high evaluation when the shape of the stem is close to a predetermined shape. Further, the shape score of the stem may be calculated, for example, by a point addition method or a point deduction method.

[0036] Using FIG. 5, a specific example of the method for estimating the stem score will be described, but the present disclosure is not limited to the following examples in any way. The part score estimation unit 13, for example, arranges the coordinate points 3 at predetermined intervals for the region where the stem is detected in the plant image as shown in FIG. 5(A). Then, the part score estimation unit 13, for example, generates line segments connecting adjacent coordinate points 3, and evaluates the shape (degree of bending) of the stem by evaluating the angle between the line segments at the points (coordinate points 3) where adjacent line segments are connected. The part score estimation unit 13 may, for example, evaluate the angle of the line segment connecting between consecutive coordinate points, or may evaluate the angle of the line segment connecting between non-consecutive coordinate points. Specifically, when evaluating the angle of the line segment connecting between consecutive coordinate points, the part score estimation unit 13, for example, generates a line segment AB connecting the coordinate point 3A and the coordinate point 3B, and a line segment BC connecting the coordinate point 3B and the coordinate point 3C as shown in FIG. 5(B). Then, the part score estimation unit 13 can evaluate the degree of bending from the position of the coordinate point 3A to the position of the coordinate point 3C by evaluating, for example, the value of the angle ABC between the line segment AB and the line segment BC. Also, when evaluating the angle of the line segment connecting between non-consecutive coordinate points, the part score estimation unit 13, for example, generates a line segment AC connecting the coordinate point 3A and the coordinate point 3C, and a line segment CD connecting the coordinate point 3C and the coordinate point 3D. Then, the part score estimation unit 13 can evaluate the degree of bending from the position of the coordinate point 3A to the position of the coordinate point 3D by evaluating, for example, the value of the angle ACD between the line segment AC and the line segment CD. The evaluation of the angle is not particularly limited. For example, for the angle X, the degree of bending (bending level) can be determined according to the criteria shown in Table 1 below. The part score estimation unit 13, for example, determines the degree of bending for all of the coordinate points 3 shown in FIG. 5(A), and subtracts the total value of the subtraction values associated with the degree of bending between each coordinate point 3 from the reference evaluation point, thereby calculating the shape score of the stem of the plant. The angle, degree of bending (bending level) and subtraction value in Table 1 below, as well as the reference evaluation point, may be recorded in the storage unit of the present apparatus 10, or may be recorded in an external storage device outside the apparatus.

Table 1

[0037] The stem size score is, for example, an index for evaluating the size of the stem. The size may be, for example, length or thickness. The part score estimation unit 13 can estimate the size (length or thickness) of the stem based on, for example, the number of pixels indicating the stem region in the plant image. When the part score estimation unit 13 estimates the thickness as the size, for example, it may estimate the thickness at the thickest part of the stem, or the thickness at the thinnest part, or the average thickness of the thicknesses at a plurality of locations. Next, the part score estimation unit 13 can estimate the stem size score based on, for example, comparing the estimated stem size with the size reference information and based on the difference between the estimated stem size and the size reference information. The size reference information can be set to an arbitrary value based on, for example, the type of plant, the shipping period, etc. The size reference information may be recorded, for example, in the storage unit of the present apparatus 10, or may be recorded in an external storage device outside the apparatus.

[0038] The damage score is, for example, an index related to the damage of the stem. The part score estimation unit 13 can estimate the damage score based on, for example, the presence or absence of stem damage, the number of damages, and / or the size of the damage. Specifically, as shown in FIG. 6, for example, the part score estimation unit 13 determines the presence or absence of damage in the stem region by further using an object identification and detection method for the region where the stem is detected in the plant image. When damage is detected in the stem, the part score estimation unit 13 can estimate the size of the damage based on, for example, the number of pixels indicating the damage region. Also, the part score estimation unit 13 can estimate the number of stem damages based on, for example, the number of the damage regions. Then, the part score estimation unit 13 can calculate the damage score of the stem of the plant by subtracting a subtraction value associated with the presence or absence, size, or number of damages from a reference evaluation point. The subtraction value and the reference evaluation point may be recorded in the storage unit of the present apparatus 10, or may be recorded in an external storage device outside the apparatus.

[0039] Note that the estimation of the stem score by the part score estimation unit 13 is not limited to the above examples. The part score estimation unit 13 may estimate the stem score using, for example, a pre-trained machine learning model. The pre-trained machine learning model is, for example, a stem score evaluation model generated to output a stem score when a plant image is input. The stem score evaluation model may be constructed by the present apparatus 10, may be stored in advance in the storage unit of the present apparatus 10, or may be acquired from outside the present apparatus 10 via a communication network.

[0040] The stem score evaluation model includes, for example, an input layer for inputting a plant image, an output layer for outputting the stem score, and at least one intermediate layer provided between the input layer and the output layer. The stem score evaluation model may be a program module that is part of artificial intelligence software. Examples of the multi-layer network include a neural network. Examples of the neural network include a Convolution Neural Network (CNN), but it is not limited to CNN, and may be a pre-trained model constructed by other learning algorithms such as neural networks other than CNN, Support Vector Machine (SVM), Bayesian network, and regression tree.

[0041] The stem score evaluation model can be generated, for example, by machine learning using the combination of the plant image and the stem score as teacher data for stem score evaluation. Note that the stem score evaluation model may be, for example, a pre-generated pre-trained model. Further, the pre-trained model may be a pre-trained model (derived model) re-trained using the teacher data for stem score evaluation and an already generated pre-trained model. Furthermore, the pre-trained model may be a pre-trained model obtained by transfer learning using a pre-trained model generated using teacher data for stem score evaluation, or a pre-trained model generated by compressing a pre-trained model generated using teacher data for stem score evaluation.

[0042] In S2, when a flower is detected as the plant part, the part score estimation unit 13 estimates, for example, the flower score of the flower of the plant as the part score. The part score estimation unit 13 can estimate the flower score using, for example, a pre-trained machine learning model. The pre-trained machine learning model is, for example, a flower score evaluation model generated to output a flower score when a plant image is input. The flower score evaluation model may be constructed by the apparatus 10, may be stored in advance in the storage unit of the apparatus 10, or may be acquired from outside the apparatus 10 via a communication network.

[0043] The flower score evaluation model includes, for example, an input layer for inputting a plant image, an output layer for outputting the flower score, and at least one intermediate layer provided between the input layer and the output layer. The flower score evaluation model may be a program module that is part of artificial intelligence software. Examples of the multi-layer network include a neural network. Examples of the neural network include a Convolution Neural Network (CNN), but it is not limited to CNN, and may be a pre-trained model constructed by other learning algorithms such as neural networks other than CNN, Support Vector Machine (SVM), Bayesian network, and regression tree.

[0044] The flower score evaluation model can be generated, for example, by machine learning using the combination of the plant image and the flower score as teacher data for flower score evaluation. Note that the flower score evaluation model may be a pre-generated pre-trained model. Further, the pre-trained model may be a pre-trained model (derived model) re-trained using the teacher data for flower score evaluation and an already generated pre-trained model. Furthermore, the pre-trained model may be a pre-trained model obtained by transfer learning using a pre-trained model generated using teacher data for flower score evaluation, or a pre-trained model generated by compressing a pre-trained model generated using teacher data for flower score evaluation.

[0045] In S2, when a leaf is detected as the plant part, the part score estimation unit 13 estimates, for example, the leaf score of the leaf of the plant as the part score. The part score estimation unit 13 can estimate the leaf score by using, for example, a pre-trained model. The pre-trained model is, for example, a leaf score evaluation model generated to output a leaf score when a plant image is input. The leaf score evaluation model may be constructed by the apparatus 10, may be stored in advance in the storage unit of the apparatus 10, or may be acquired from outside the apparatus 10 via a communication network.

[0046] The leaf score evaluation model includes, for example, an input layer for inputting a plant image, an output layer for outputting the leaf score, and at least one intermediate layer provided between the input layer and the output layer. The leaf score evaluation model may be a program module that is part of artificial intelligence software. Examples of the multi-layer network include a neural network. Examples of the neural network include a Convolution Neural Network (CNN), but are not limited to CNN, and may be a pre-trained model constructed by other learning algorithms such as a neural network other than CNN, Support Vector Machine (SVM), Bayesian network, or regression tree.

[0047] The leaf score evaluation model can be generated, for example, by machine learning using the plant image and the set of the leaf scores as teacher data for leaf score evaluation. Note that the leaf score evaluation model may be, for example, a pre-generated learned model. Further, the learned model may be a learned model (derived model) re-learned using the teacher data for leaf score evaluation and an already generated learned model. Furthermore, the learned model may be a learned model obtained by transfer learning using a learned model generated using teacher data for leaf score evaluation, or may be a learned model generated by compressing a learned model generated using teacher data for leaf score evaluation.

[0048] The quality grade evaluation unit 14 evaluates the quality grade of the plant based on the part score and the evaluation criteria (S4, quality grade evaluation procedure). The quality grade is, for example, an index indicating the overall quality of the plant, and can be in any unit and at any stage. Specific examples of the quality grade include, for example, indicators such as "excellent product", "superior product", "good product", "off-specification product" in descending order of quality. The quality grade is not limited to this, and may be, for example, a step notation using any numerical value or character. The evaluation criteria are, for example, information in which the corresponding quality grade of the plant is associated with each of the part scores. Examples of the evaluation criteria include, for example, the combinations shown in Table 2 below, but the present disclosure is not limited to the following examples at all.

Table 2

[0049] The quality grade evaluation unit 14 may output, for example, the evaluated quality grade. The quality grade evaluation unit 14 may output the quality grade to, for example, the output device 106 of the present apparatus 10, or may output it to an external device. Further, the quality grade evaluation unit 14 may output the quality grade to, for example, the imaging device that captured the plant image and cause the quality grade to be displayed on the display of the imaging device. At this time, the quality grade evaluation unit 14 may, for example, AR-display the quality grade on the display of the imaging device. Further, the quality grade evaluation unit 14 may output the quality grade to a projection device such as a projector and project the quality grade on a wall surface, a desk surface, or the like.

[0050] The plant quality evaluation support method of the present disclosure is, for example, a method implemented by reading each "procedure" in the plant quality evaluation support program of the present disclosure as a "step". Specifically, the plant quality evaluation support method of the present disclosure includes a plant image acquisition step, a part detection step, a part score estimation step, and a quality grade evaluation step. The plant image acquisition step acquires a plant image obtained by imaging a plant. The part detection step detects at least one type of plant part for the plant from the plant image. The part score estimation step estimates the part score of the plant part. The quality grade evaluation step evaluates the quality grade of the plant based on the part score and an evaluation criterion. The plant quality evaluation support method of the present disclosure can be implemented, for example, using the plant quality evaluation support apparatus 10 of the present disclosure shown in FIG. 1 or FIG. 2. Note that the plant quality evaluation support method of the present disclosure is not limited to, for example, a method using the plant quality evaluation support apparatus 10. The plant quality evaluation support method of the present disclosure can incorporate the descriptions in, for example, the plant quality evaluation support program and the plant quality evaluation support apparatus of the present disclosure.

[0051] According to the plant quality evaluation support program of the present disclosure, a plant image obtained by imaging a plant through a plant image acquisition procedure is acquired, at least one type of plant part of the plant is detected from the plant image through a part detection procedure, a part score of the plant part is estimated through a part score estimation procedure, and a quality grade of the plant can be evaluated based on the part score and an evaluation criterion through a quality grade evaluation procedure. Therefore, according to the present disclosure, the quality grade of a plant can be easily estimated only by imaging an image of the plant. In the process of preparing plants, especially flowers, for shipment, for appearance evaluation, it relies on the judgment of experts in the flower selection field, which is highly personnel-dependent and time-consuming. According to the plant quality evaluation program of the present disclosure, for example, effects such as reduction of dependence on experts, elimination of personnel-dependence, suppression of variations in evaluations by individual evaluations, and inheritance of know-how through the formation and intellectualization of tacit knowledge regarding evaluation criteria can be expected.

[0052] [Embodiment 2] Another example of the plant quality evaluation support program of the present disclosure will be described.

[0053] The plant quality evaluation support program of the present embodiment is, for example, the same as the plant quality evaluation support program of Embodiment 1 except that it includes a plant attribute information acquisition procedure and an evaluation criterion selection procedure in addition to the configuration of the plant quality evaluation support program of Embodiment 1, and the description thereof can be incorporated by reference. The plant quality evaluation support program of the present embodiment includes, for example, a plant attribute information acquisition procedure and an evaluation criterion selection procedure. The plant attribute information acquisition procedure acquires the plant attribute information of the plant, the evaluation criterion selection procedure selects the evaluation criterion of the plant based on the plant attribute information, and the quality grade evaluation procedure evaluates the quality grade based on the selected evaluation criterion and the part score.

[0054] Next, with reference to FIG. 7, the plant quality evaluation support device of the present embodiment will be described. The plant quality evaluation support device 10A of the present disclosure is the same as the plant quality evaluation support device 10 of the first embodiment, except that it includes a plant attribute information acquisition unit 15 and an evaluation criterion selection unit 16, and the description thereof can be incorporated herein. The plant quality evaluation support device 10A of the present embodiment includes, for example, a plant attribute information acquisition unit 15 and an evaluation criterion selection unit 16. The plant attribute information acquisition unit 15 acquires the plant attribute information of the plant, and the evaluation criterion selection unit 16 selects the evaluation criterion of the plant based on the plant attribute information. The quality grade evaluation unit 14 evaluates the quality grade based on the selected evaluation criterion and the part score.

[0055] As shown in FIG. 7, the plant quality evaluation support device 10A includes a plant attribute information acquisition unit 15 and an evaluation criterion selection unit 16 in addition to the configuration of the plant quality evaluation support device 10 of the first embodiment. The hardware configuration of the plant quality evaluation support device 10A is the same as that of the plant quality evaluation support device 10 in FIG. 2, except that the central processing unit 101 has the configuration of the plant quality evaluation support device 10A in FIG. 7 instead of the configuration of the plant quality evaluation support device 10 in FIG. 1.

[0056] An example of the processing by the plant quality evaluation support program of the present disclosure will be further specifically described with reference to FIG. 8. FIG. 8 is a flowchart showing an example of each step of the plant quality evaluation support program of the present disclosure. In the following description, the case where the plant quality evaluation support program of the present disclosure is executed by a device (the plant quality evaluation support device 10A of the present disclosure) in which the plant quality evaluation support program of the present disclosure is installed will be described as an example, but the plant quality evaluation support program of the present disclosure is not limited to being executed by the plant quality evaluation support device 10A of the present disclosure.

[0057] First, S1 to S3 are performed in the same manner as S1 to S3 in the first embodiment.

[0058] The plant attribute information acquisition unit 15 acquires, for example, the plant attribute information of the plant (S11, plant attribute information acquisition procedure). The plant attribute information is information on the plant related to the selection of evaluation criteria described later, and examples thereof include information such as the variety, production area, shipping area, shipping time, and producer of the plant. In FIG. 8, the form in which S11 is implemented as a subsequent process of S3 is taken as an example for explanation, but the implementation order of S11 is not limited to the subsequent process of S3. S11 may be implemented separately, for example, independently of S1 to S3, or may be implemented simultaneously with S1 to S3.

[0059] The evaluation criterion selection unit 16 selects the evaluation criterion for the plant based on the plant attribute information (S12, evaluation criterion selection procedure). The evaluation criterion selection unit 16 can select the evaluation criterion based on the plant attribute information, for example, by referring to the shipping standard master. The shipping standard master stores, for example, the plant attribute information and the evaluation criterion linked as a set. The evaluation criterion selection unit 16 selects, for example, the evaluation criterion linked to the plant attribute information acquired in S11 by referring to the shipping standard master. Table 3 below shows an example of the shipping standard master, but the present disclosure is not limited to the following examples at all.

Table 3

[0060] Then, the quality grade evaluation unit 14 evaluates the quality grade based on the selected evaluation criterion and the part score (S4, quality grade evaluation procedure). S4 in the present embodiment can be implemented in the same manner as S4 in the first embodiment except that the evaluation criterion selected in S12 is used.

[0061] The plant quality evaluation support method of the present disclosure is, for example, a method implemented by reading each "procedure" in the plant quality evaluation support program of the present disclosure as a "process". The plant quality evaluation support method of the present disclosure can refer to the descriptions in the plant quality evaluation support program and the plant quality evaluation support device of the present disclosure.

[0062] Even for plants of the same variety, the shipping standards for flowers may require different qualities of the parts to be inspected depending on the place of shipment or the type of agricultural cooperative. The plant quality evaluation support program of the present disclosure acquires the plant attribute information of the plant by, for example, a plant attribute information acquisition procedure, selects the evaluation criteria for the plant based on the plant attribute information by an evaluation criteria selection procedure, and evaluates the quality grade based on the selected evaluation criteria and the part score by a quality grade evaluation procedure. Therefore, according to the plant quality evaluation support program of the present disclosure, the evaluation criteria can be changed based on information such as quality, place of production, shipment, and type of agricultural cooperative. Thus, according to the plant quality evaluation support program of the present disclosure, the quality grade can be estimated according to appropriate evaluation criteria corresponding to the plant attribute information of the plant.

[0063] [Embodiment 3] The plant sorting program of the present disclosure is a program for causing a computer to execute a quality evaluation procedure and a sorting procedure. The plant sorting program of the present disclosure can also be said to be a program for causing a computer to function as a plant quality evaluation procedure and a sorting procedure. Further, the plant sorting program of the present disclosure can also be said to be a program for causing a computer to execute each step of the plant sorting method described later, for example.

[0064] The quality evaluation procedure includes each procedure of the plant quality evaluation support program of the present disclosure. The sorting procedure sorts the plants based on the quality grade.

[0065] Each of the above procedures can be read as "processing" instead of "procedure", for example. Also, the plant sorting program of the present disclosure may be recorded on a computer-readable recording medium, for example. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited and includes, for example, random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., solid state drive (SSD), USB flash memory, SD / SDHC card, etc.), optical disk (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy (registered trademark) disk (FD), and the like. Further, the plant sorting program of the present disclosure (also referred to as a programming product or a program product, for example) may be in a form distributed from an external computer, for example. The "distribution" may be, for example, distribution via a communication network or distribution via a device connected by wire. The plant sorting program of the present disclosure may be installed and executed on the distributed device or may be executed without installation. The information processing device capable of executing the plant sorting program of the present disclosure can be referred to as the plant sorting device of the present disclosure, for example.

[0066] Next, a configuration example of the plant sorting device of the present disclosure will be described with reference to FIG. 9. FIG. 9 is a block diagram showing a configuration example of the plant sorting device 20 (hereinafter also referred to as the present device 20) of the present disclosure. As shown in FIG. 9, the present device 20 includes a quality evaluation unit 10 and a sorting unit 21. Further, although not shown, the present device 20 may include, for example, an input unit, an output unit, a display unit, and / or a storage unit. The quality evaluation unit 10 and the sorting unit 21 can each execute, for example, the quality evaluation procedure and the sorting procedure in the plant sorting program of the present disclosure.

[0067] The device 20 may be, for example, one device including the above-described respective parts, or the respective parts may be devices connectable via a communication line network. Further, the device 20 can be connected to an external device described later via the communication line network. The communication line network is not particularly limited, and a known network can be used. For example, it may be wired or wireless. Examples of the communication line network include an Internet line, the World Wide Web (WWW), a telephone line, a local area network (LAN), a storage area network (SAN), a delay tolerant networking (DTN), a low power wide area (LPWA), a local 5G, etc. Examples of the wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), local 5G, LPWA, etc. The wireless communication may be in a form in which each device communicates directly (Ad Hoc communication), infrastructure communication, indirect communication via an access point, or the like. The device 20 may be incorporated into a server as a system, for example. Further, the device 20 may be, for example, a personal computer (PC, for example, a desktop type or a notebook type), a smartphone, a tablet terminal, etc. in which the program of the present disclosure is installed. The device 20 may be in a form such as cloud computing or edge computing in which at least one of the above-described respective parts is on a server and the other respective parts are on a terminal, for example.

[0068] FIG. 10 illustrates a block diagram of the hardware configuration of the device 20. The device 20 includes, for example, a central processing unit (CPU, GPU, etc.) 201, a memory 202, a bus 203, a storage device 204, an input device 205, an output device 206, a communication device 207, etc. Each part of the device 20 is interconnected via the bus 203 by respective interfaces (I / F).

[0069] The central processing unit 201 cooperates with other components under the control of a controller (such as a system controller, an I / O controller, etc.) to undertake the overall control of the present device 20. In the present device 20, the central processing unit 201 executes, for example, the program of the present disclosure (the plant sorting program) and other programs, and reads and writes various information. Specifically, for example, the central processing unit 201 functions as the quality evaluation unit 10 and the sorting unit 21. The present device 20 may be provided with other arithmetic units such as a CPU, a GPU (Graphics Processing Unit), and an APU (Accelerated Processing Unit) as an arithmetic unit, or may be provided with a combination thereof.

[0070] The bus 103 can be connected to, for example, an external device. Examples of the external device include an external storage device (such as an external database), a printer, an external input device, an external display device, an external imaging device, etc. The present device 20 can be connected to an external network (the communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0071] The memory 102 is, for example, a main memory (main storage device). When the central processing unit 201 performs processing, for example, the memory 102 reads various operation programs such as the program of the present disclosure stored in the storage device 204 described later, and the central processing unit 201 receives data from the memory 102 and executes the program. The main memory is, for example, a RAM (Random Access Memory). Further, the memory 102 may be, for example, a ROM (Read Only Memory).

[0072] The memory device 204 is, for example, also referred to as a so-called auxiliary storage device with respect to the main memory (primary storage device). As described above, an operation program including the program of the present disclosure is stored in the memory device 204. The memory device 204 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited, and may be, for example, an internal type or an external type, and examples include an HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The memory device 204 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, and a solid state drive (SSD). When the present device 20 includes the storage unit, for example, the memory device 204 functions as the storage unit. The storage unit can record information such as the aforementioned plant images, plant attribute information, reference evaluation points, stem score evaluation models, flower score evaluation models, leaf score evaluation models, and evaluation criteria.

[0073] In the present device 20, the memory 102 and the memory device 204 can also store various information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present device 20, and information used when the present device 20 executes processing. In this case, the memory 102 and the memory device 204 may store, for example, information of the user of the present device described above. Note that at least a part of the information may be stored in an external server other than the memory 102 and the memory device 204, for example, or may be distributed and stored in a plurality of terminals using blockchain technology or the like.

[0074] The apparatus 20 further includes, for example, an input device 205 and an output device 206. The input device 205 includes, for example, pointing devices such as a touch panel, a track pad, and a mouse; a keyboard; imaging means such as a camera and a scanner; card readers such as an IC card reader and a magnetic card reader; voice input means such as a microphone; and the like. The output device 206 includes, for example, display devices such as an LED display and a liquid crystal display; voice output devices such as a speaker; a printer; and the like. In the first embodiment, the input device 205 and the output device 206 are separately configured, but the input device 205 and the output device 206 may be integrally configured, such as a touch panel display.

[0075] An example of the processing by the plant sorting program of the present disclosure will be further specifically described with reference to FIG. 11. FIG. 11 is a flowchart showing an example of each step of the plant sorting program of the present disclosure.

[0076] The quality evaluation unit 10 evaluates the quality grade of the plant (S21, quality evaluation procedure). The quality evaluation unit 10 includes the plant quality evaluation support apparatus 10(10A) of the present disclosure. The processing of the quality evaluation unit 10 can refer to the description of the first or second embodiment.

[0077] The sorting unit 21 sorts the plant based on the quality grade (S22, sorting procedure). For example, when the apparatus 20 has each part of the plant sorting apparatus, the sorting unit 21 may sort the plant by the sorting function of the apparatus 20, or may transmit a sorting command based on the quality grade to a sorting apparatus outside the apparatus 20 to cause the external sorting apparatus to sort the plant.

[0078] The plant sorting method of the present disclosure is, for example, a method implemented by reading each "procedure" in the plant sorting program of the present disclosure as a "step". Specifically, the plant sorting method of the present disclosure includes a quality evaluation step and a sorting step. The quality evaluation step is a step of evaluating the quality grade of a plant, includes each step of the plant quality evaluation support method of the present disclosure, and the sorting step sorts the plant based on the quality grade. The plant sorting method of the present disclosure can be implemented, for example, using the plant sorting device 20 of the present disclosure shown in FIG. 1 or FIG. 2. Note that the plant sorting method of the present disclosure is not limited to, for example, the method using the plant sorting device 20. The plant sorting method of the present disclosure can refer to the descriptions in, for example, the plant sorting program and the plant sorting device of the present disclosure.

[0079] Since the plant sorting program of the present disclosure includes each procedure of the plant quality support program of the present disclosure, for example, the quality grade of a plant can be easily estimated, and the plant can be sorted based on the estimated quality grade. Therefore, according to the plant sorting program of the present disclosure, for example, effects such as improvement of work efficiency, labor saving, elimination of labor shortage, and reduction of labor costs in the horticulture field, flower wholesale industry, etc. can be expected.

[0080] As described above, the present disclosure has been described with reference to the embodiments, but the present disclosure is not limited to the above-described embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. And each embodiment can be combined with other embodiments as appropriate.

[0081] <Supplementary Note> Some or all of the above embodiments can be described as follows, but are not limited thereto. (Supplementary Note 1) It includes a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure, The plant image acquisition procedure acquires a plant image obtained by imaging a plant, The part detection procedure detects at least one type of plant part for the plant from the plant image, The part score estimation procedure estimates the part score of the plant part, The quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and the evaluation criteria, A plant quality evaluation support program for causing a computer to execute each of the above procedures. (Appendix 2) Including a plant attribute information acquisition procedure and an evaluation criterion selection procedure, The plant attribute information acquisition procedure acquires the plant attribute information of the plant, The evaluation criterion selection procedure selects the evaluation criteria for the plant based on the plant attribute information, The quality grade evaluation procedure evaluates the quality grade based on the selected evaluation criteria and the part score. The plant quality evaluation support program according to Appendix 1. (Appendix 3) The plant attribute information includes at least one of the production area information and the shipping area information of the plant, The evaluation criterion selection procedure selects the evaluation criteria based on at least one of the production area information and the shipping area information. The plant quality evaluation support program according to Appendix 2. (Appendix 4) The part detection procedure detects the stem of the plant as the plant part, The part score estimation procedure estimates the stem score of the stem of the plant as the part score. The plant quality evaluation support program according to any one of Appendices 1 to 3. (Appendix 5) The part score estimation procedure estimates at least one selected from the group consisting of a stem shape score, a stem size score, and a stem damage score as the stem score. The plant quality evaluation support program according to Appendix 4. (Appendix 6) The part detection procedure detects the flower of the plant as the plant part, The part score estimation procedure estimates the flower score of the flower of the plant as the part score. The plant quality evaluation support program according to any one of Appendices 1 to 5. (Appendix 7) The above-described part detection procedure detects the leaf of the plant as the plant part, The above-described part score estimation procedure is a plant quality evaluation support program according to any one of Appendices 1 to 6 that estimates the leaf score of the leaf of the plant as the part score. (Appendix 8) including a plant image acquisition unit, a part detection unit, a part score estimation unit, and a quality grade evaluation unit, The plant image acquisition unit acquires a plant image obtained by imaging a plant, The part detection unit detects at least one type of plant part for the plant from the plant image, The part score estimation unit estimates the part score of the plant part, The quality grade evaluation unit is a plant quality evaluation support device that evaluates the quality grade of the plant based on the part score and an evaluation criterion. (Appendix 9) including a plant attribute information acquisition unit and an evaluation criterion selection unit, The plant attribute information acquisition unit acquires the plant attribute information of the plant, The evaluation criterion selection unit selects the evaluation criterion of the plant based on the plant attribute information, The quality grade evaluation unit is the plant quality evaluation support device according to Appendix 8 that evaluates the quality grade based on the selected evaluation criterion and the part score. (Appendix 10) The plant attribute information includes at least one of the production area information and the shipping area information of the plant, The evaluation criterion selection unit is the plant quality evaluation support device according to Appendix 9 that selects the evaluation criterion based on at least one of the production area information and the shipping area information. (Appendix 11) The part detection unit detects the stem of the plant as the plant part, The part score estimation unit is the plant quality evaluation support device according to any one of Appendices 8 to 10 that estimates the stem score of the stem of the plant as the part score. (Appendix 12) The part score estimation unit estimates, as the stem score, at least one selected from the group consisting of a stem shape score, a stem size score, and a stem damage score, for the plant quality evaluation support device according to Supplementary Note 11. (Supplementary Note 13) The part detection unit detects, as the plant part, a flower of the plant, The part score estimation unit estimates, as the part score, a flower score of a flower of the plant, for the plant quality evaluation support device according to any one of Supplementary Notes 8 to 12. (Supplementary Note 14) The part detection unit detects, as the plant part, a leaf of the plant, The part score estimation unit estimates, as the part score, a leaf score of a leaf of the plant, for the plant quality evaluation support device according to any one of Supplementary Notes 8 to 13. (Supplementary Note 15) including a plant image acquisition step, a part detection step, a part score estimation step, and a quality grade evaluation step, The plant image acquisition step acquires a plant image obtained by imaging a plant, The part detection step detects, from the plant image, at least one type of plant part for the plant, The part score estimation step estimates a part score of the plant part, The quality grade evaluation step evaluates the quality grade of the plant based on the part score and an evaluation criterion, A plant quality evaluation support method in which each of the above steps is executed by a computer. (Supplementary Note 16) including a plant attribute information acquisition step and an evaluation criterion selection step, The plant attribute information acquisition step acquires plant attribute information of the plant, The evaluation criterion selection step selects an evaluation criterion for the plant based on the plant attribute information, The quality grade evaluation step evaluates the quality grade based on the selected evaluation criterion and the part score, for the plant quality evaluation support method according to Supplementary Note 15. (Supplementary Note 17) The plant attribute information includes at least one of production area information and shipping area information of the plant, The evaluation criterion selection step is the method for supporting plant quality evaluation according to Appendix 16, which selects the evaluation criterion based on at least one of the production area information and the shipping area information. (Appendix 18) In the part detection step, as the plant part, the stem of the plant is detected. The part score estimation step is the method for supporting plant quality evaluation according to any one of Appendices 15 to 17, which estimates the stem score of the stem of the plant as the part score. (Appendix 19) The part score estimation step is the method for supporting plant quality evaluation according to Appendix 18, which estimates at least one selected from the group consisting of a stem shape score, a stem size score, and a stem damage score as the stem score. (Appendix 20) In the part detection step, as the plant part, the flower of the plant is detected. The part score estimation step is the method for supporting plant quality evaluation according to any one of Appendices 15 to 19, which estimates the flower score of the flower of the plant as the part score. (Appendix 21) In the part detection step, as the plant part, the leaf of the plant is detected. The part score estimation step is the method for supporting plant quality evaluation according to any one of Appendices 15 to 20, which estimates the leaf score of the leaf of the plant as the part score. (Appendix 22) It includes a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure. The plant image acquisition procedure acquires a plant image obtained by imaging a plant. The part detection procedure detects at least one type of plant part for the plant from the plant image. The part score estimation procedure estimates the part score of the plant part. The quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and the evaluation criterion. A computer-readable recording medium recording a plant quality evaluation support program for causing a computer to execute each of the above procedures. (Supplementary Note 23) including a plant attribute information acquisition procedure and an evaluation criterion selection procedure, wherein the plant attribute information acquisition procedure acquires plant attribute information of the plant, the evaluation criterion selection procedure selects an evaluation criterion for the plant based on the plant attribute information, the quality grade evaluation procedure evaluates the quality grade based on the selected evaluation criterion and the part score, the recording medium according to Supplementary Note 22. (Supplementary Note 24) wherein the plant attribute information includes at least one of production area information and shipping area information of the plant, the evaluation criterion selection procedure selects the evaluation criterion based on at least one of the production area information and the shipping area information, the recording medium according to Supplementary Note 23. (Supplementary Note 25) the part detection procedure detects the stem of the plant as the plant part, the part score estimation procedure estimates a stem score of the stem of the plant as the part score, the recording medium according to any one of Supplementary Notes 22 to 24. (Supplementary Note 26) the part score estimation procedure estimates at least one selected from the group consisting of a stem shape score, a stem size score, and a stem damage score as the stem score, the recording medium according to Supplementary Note 25. (Supplementary Note 27) the part detection procedure detects the flower of the plant as the plant part, the part score estimation procedure estimates a flower score of the flower of the plant as the part score, the recording medium according to any one of Supplementary Notes 22 to 26. (Supplementary Note 28) the part detection procedure detects the leaf of the plant as the plant part, the part score estimation procedure estimates a leaf score of the leaf of the plant as the part score, the recording medium according to any one of Supplementary Notes 22 to 27. (Supplementary Note 29) including a quality evaluation procedure and a sorting procedure, The quality evaluation procedure is a procedure for evaluating the quality grade of plants, and includes each procedure of the plant quality evaluation support program described in any one of Appendices 1 to 7. The sorting procedure sorts the plants based on the quality grade. A plant sorting program for causing a computer to execute each of the above procedures. (Appendix 30) Including a quality evaluation unit and a sorting unit. The quality evaluation unit evaluates the quality grade of plants and includes the plant quality evaluation support device described in any one of Appendices 8 to 14. The sorting unit is a plant sorting device that sorts the plants based on the quality grade. (Appendix 31) Including a quality evaluation process and a sorting process. The quality evaluation process is a process for evaluating the quality grade of plants, and includes each process of the plant quality evaluation support method described in any one of Appendices 15 to 21. The sorting process is a plant sorting method that sorts the plants based on the quality grade. (Appendix 32) Including a quality evaluation procedure and a sorting procedure. The quality evaluation procedure is a procedure for evaluating the quality grade of plants, and includes each procedure of the plant quality evaluation support program described in any one of Appendices 1 to 7. The sorting procedure sorts the plants based on the quality grade. A computer-readable recording medium recording a plant sorting program for causing a computer to execute each of the above procedures.

Industrial Applicability

[0082] According to the present disclosure, the quality grade of plants can be easily estimated. Therefore, the present disclosure can be widely and usefully applied in the horticulture field, the flower wholesale industry, etc.

Explanation of Signs

[0083] 10 Plant quality evaluation support device (quality evaluation unit) 11 Plant image acquisition unit 12 Part detection unit 13 Site Score Estimation Unit 14 Quality Grade Evaluation Unit 15 Plant Attribute Information Acquisition Unit 16 Evaluation Criterion Selection Unit 101 Central Processing Unit 102 Memory 103 Bus 104 Storage Device 105 Input Device 106 Output Device 107 Communication Device 20 Plant Sorting Device 21 Sorting Unit 201 Central Processing Unit 202 Memory 203 Bus 204 Storage Device 205 Input Device 206 Output Device 207 Communication Device

Claims

1. A plant quality evaluation support program including a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure, wherein the plant image acquisition procedure acquires a plant image obtained by imaging a plant, the part detection procedure detects at least one type of plant part for the plant from the plant image, the part score estimation procedure estimates a part score of the plant part, the quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and an evaluation criterion, and causes a computer to execute each of the above procedures.

2. A plant quality evaluation support program including a plant attribute information acquisition procedure and an evaluation criterion selection procedure, wherein the plant attribute information acquisition procedure acquires plant attribute information of the plant, the evaluation criterion selection procedure selects an evaluation criterion for the plant based on the plant attribute information, and the quality grade evaluation procedure evaluates the quality grade based on the selected evaluation criterion and the part score. The plant quality evaluation support program according to claim 1.

3. The plant quality evaluation support program according to claim 2, wherein the plant attribute information includes at least one of production area information and shipping area information of the plant, and the evaluation criterion selection procedure selects the evaluation criterion based on at least one of the production area information and the shipping area information.

4. The plant quality evaluation support program according to any one of claims 1 to 3, wherein the part detection procedure detects the stem of the plant as the plant part, and the part score estimation procedure estimates a stem score of the stem of the plant as the part score.

5. The plant quality evaluation support program according to claim 4, wherein the part score estimation procedure estimates at least one selected from the group consisting of a stem shape score, a stem size score, and a stem damage score as the stem score.

6. The plant quality evaluation support program according to any one of claims 1 to 3, wherein the part detection procedure detects the flower of the plant as the plant part, and the part score estimation procedure estimates a flower score of the flower of the plant as the part score.

7. The plant quality evaluation support program according to any one of claims 1 to 3, wherein the part detection procedure detects the leaf of the plant as the plant part, and the part score estimation procedure estimates a leaf score of the leaf of the plant as the part score.

8. A plant quality evaluation support program including a plant image acquisition unit, a part detection unit, a part score estimation unit, and a quality grade evaluation unit. The plant image acquisition unit acquires a plant image obtained by imaging a plant, The part detection unit detects at least one type of plant part for the plant from the plant image, The part score estimation unit estimates the part score of the plant part, The quality grade evaluation unit is a plant quality evaluation support device that evaluates the quality grade of the plant based on the part score and evaluation criteria.

9. Including a plant image acquisition step, a part detection step, a part score estimation step, and a quality grade evaluation step, The plant image acquisition step acquires a plant image obtained by imaging a plant, The part detection step detects at least one type of plant part for the plant from the plant image, The part score estimation step estimates the part score of the plant part, The quality grade evaluation step evaluates the quality grade of the plant based on the part score and evaluation criteria, A plant quality evaluation support method in which each of the above steps is executed by a computer.

10. Including a plant image acquisition procedure, a part detection procedure, a part score estimation procedure, and a quality grade evaluation procedure, The plant image acquisition procedure acquires a plant image obtained by imaging a plant, The part detection procedure detects at least one type of plant part for the plant from the plant image, The part score estimation procedure estimates the part score of the plant part, The quality grade evaluation procedure evaluates the quality grade of the plant based on the part score and evaluation criteria, A computer-readable recording medium recording a plant quality evaluation support program for causing a computer to execute each of the above procedures.

11. Including a quality evaluation procedure and a sorting procedure, The quality evaluation procedure is a procedure for evaluating the quality grade of a plant, and includes each procedure of the plant quality evaluation support program according to any one of claims 1 to 3, The sorting procedure sorts the plants based on the quality grade, A plant sorting program for causing a computer to execute each of the above procedures.

12. Including a quality evaluation unit and a sorting unit, The quality evaluation unit evaluates the quality grade of a plant and includes the plant quality evaluation support device according to claim 8, The sorting unit is a plant sorting device that sorts the plants based on the quality grade.

13. Including a quality evaluation step and a sorting step, The quality evaluation step is a step for evaluating the quality grade of a plant and includes each step of the plant quality evaluation support method according to claim 9, A plant sorting method, wherein the sorting step sorts the plants based on the quality grade, and each of the steps is executed by a computer.

14. Including a quality evaluation procedure and a sorting procedure, The quality evaluation procedure is a procedure for evaluating the quality grade of plants, and includes each procedure of the plant quality evaluation support program according to any one of Claims 1 to 3. The sorting procedure sorts the plants based on the quality grade. A computer-readable recording medium recording a plant sorting program for causing a computer to execute each of the procedures.

Images