JP2000304702A - Method and apparatus for discriminating grade of granular article - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method and apparatus capable of supporting analytical result even if the preservation of a sample to be analyzed is abolished and enhancing the reliability thereof in discriminating the grade of granular articles. SOLUTION: A plurality of sample granular articles are irradiated with light to receive image signals of reflected light and transmitted light by an imaging means 2 and the image signals are processed by an image processing means 3 to obtain the optical data of the granular articles. Shape data are calculated on the basis of this optical data and the granular articles are discriminated by grades including a perfect particle and an imperfect particle on the basis of the optical data and the shape data and the number of particles is counted at least by grades of the granular articles to calculate a number-of- particle ratio based on this counting and the optical data are processed to form the image of the sample granular articles and the calculated number of particles by grades of the granular articles, the number-of-particle ratio and the image of the sample granular articles are outputted to a color printer 5 or a color display 6 at the same time.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for discriminating granular article position for analyzing the quality (quality) of granular material such as agricultural and marine products, other foods, industrial materials and the like.

[0002]

2. Description of the Related Art Granules such as grains, pellets, chip capacitors, tablets and the like are judged by using a quality judging device to determine the degree of foreign matter or defective products in the sample or the degree thereof, and calculate the mixing ratio thereof to obtain a product quality rank. To determine or quality management standards.

[0003] As an example of an apparatus for judging the quality of particulate matter, there is a technique disclosed in Japanese Patent Application Laid-Open No. 9-292344. This is to calculate the number of grains based on the grades of rectification, immature grains, damaged grains, colored grains and the like contained in the brown rice sample of cereals as agricultural products. This rice grain quality discriminating device rotates a disk provided with a plurality of sampling holes on the outer periphery, irradiates light to each sample brown rice grain in the sampling hole, and receives the reflected light amount and transmitted light amount of brown rice. I have to do it. The discrimination data is calculated from the received light quantity, and the quality of each brown rice grain is determined by the discrimination data and a predetermined discrimination algorithm.

Further, by acquiring images of a plurality of sample brown rice images to obtain image data, the outline of the kernel is determined from the image data, and the color of the kernel image determined by the outline and the outline is further determined. There is a granular device which determines the grade of a grain by the determined algorithm.

[0005] In the conventional granular article quality discriminating apparatus including the rice grain quality discriminating apparatus, after the measurement is completed, an output device such as a printer is used to record a measurement date, a sample number or a lot number, a measured grain number, and the like, along with a record for each quality. The measurement results such as the number of grains and their ratio were printed and used as management data for the analysis results.

[0006]

However, it is difficult to prove that only the above-mentioned measurement result is the analysis result corresponding to the actually analyzed sample by using the printed analysis result alone, and some kind of support is provided. I want it. Or, there was no data to prove that the threshold for discriminating the analyzer was optimal.

For this reason, for example, in grain elevators and rice centers that handle grains, grain quality discriminating devices are used for voluntary inspection at the time of receiving goods. However, misunderstanding of the inspection results with producers has occurred here. Sometimes we store analysis samples to support the test results. That is,
Until the producers were paid, the analysis samples were kept cold for several months to one year so that the analysis results could be compared with the analysis samples at any time. However, it is necessary to carefully store granules that deteriorate or degrade under the influence of temperature and humidity.For example, grains need to be stored at low temperature, and for that purpose, the storage place and the labor of storage work,
Further, there is a problem that storage cost is increased.

As described above, even if storage of an analysis sample is abolished, it is possible to provide a method and apparatus for judging the quality of particulate matter that can support the analysis result and improve the reliability of the analysis result. Subject.

[0009]

In order to solve the above-mentioned problems, a plurality of sample granules are irradiated with light to receive image signals of reflected light and transmitted light, and the image signals are subjected to image processing to form the granules of the granules. Obtaining optical information, obtaining shape information based on the optical information, discriminating granules by quality including perfect grains and incomplete grains based on the optical information and the shape information, and counting the number of grains by at least the granular article position Then, the particle number ratio based on the count is obtained, the optical information is processed to create an image of the sample granular material, and the obtained particle number for each granular article position, the particle number ratio, and the image of the sample granular material are simultaneously displayed. Alternatively, the position of the granular article to be printed was determined.

[0010] Since the quality is determined based on the image signal obtained from the sample granular material, a sample image of the sample granular material is created and added based on the same image signal, and these are printed and displayed at the same time. Not only is the quality improved, but also the fact that the sample image added to the quality discrimination result is the same as the actual sample granular material.

[0011] Further, in determining the quality, the granular article position is obtained by obtaining optical information and shape information from a granular material having a known granular article position, and analyzing the granular article position as an objective variable and the optical information and shape information as explanatory variables. The quality of the unknown granular material is determined from the granular article position relational expression for obtaining, and the optical information and shape information of the granular material of unknown quality. As described above, since the quality is determined by the shape information and the optical information on the quality of the granular material obtained from the transmitted light amount and the reflected light amount, and the predetermined granular material position relational expression, it is introduced into the granular material position determination relational expression. The quicker the value is determined, the faster the quality can be determined. Since image processing has been speeded up with the improvement of image processing technology, it has become possible to speed up quality discrimination. That is, the granular article position determination relational expression is determined, and the image processing and the quality determination are performed separately.

Further, a sample image for each grain is prepared for each granular article from the optical information, and the number of grains for each grade is calculated based on a grain number ratio and a predetermined total number of grains. The images were arranged to create an image of the sample granules. Therefore, even if the number of grains of the sampled particulate matter photographed is larger than the total number of grains predetermined for the sample image, the quality of the grain according to the grade calculated based on the total grain number and the grain number ratio is determined. Another image is taken from the image of the sample granular material to create a sample image. The completed sample image is the same as the grade-specific particle number ratio of the sample granular material whose quality has been determined. Even if the number of particles differs from the sample granular material, the sample image has high reliability as the sample image.

The optical information includes the hue, color, and luminance of the granular material, and the shape information of the granular material is obtained by the luminance of the optical information. In particular, the difference in luminance obtained from the transmission information is different from that of the granular material. It can be detected as a shape and an inner shape corresponding to a different color portion or an inner material of the granular material, and can be information including various elements. The optical information based on the reflected light can clearly grasp the color of the granular material. By the optical information based on such transmission and reflection, it is possible to determine the outer shape, the inner quality, and the color. Further, the shape information includes the length, width, and area of the granular material, and is an essential item for specifying the shape of the granular material.

[0014]

FIG. 1 shows a preferred embodiment of the present invention.
This will be described below. FIG. 1 is a control block diagram of the granular article position determination device 1. The granular article position determining device 1
An imaging means comprising a camera 2 having a light receiving element for photographing a granular object for acquiring images of a plurality of sample granular objects based on transmitted light and images of a plurality of sample granular objects based on reflected light from the granular object Image processing means 3 (for example, a “PCI bus board”) that performs image processing such as converting a signal of a granular material obtained by photographing with the camera 2 to optical information related to the quality of the granular material. ")
And an arithmetic control unit 4 (e.g., “a particle image position is determined based on the optical information obtained by the image processing unit 3, and simultaneously outputs a sample image of the sample granular material and the number of particles based on the quality and the number ratio of particles”). Personal computer etc.))
And a printer 5 for printing the sample image output from the arithmetic control means 4, the number of grains, and a grain ratio, and a color display 6 for displaying these. The image processing means 3 may be a commercially available image processing boat, and the arithmetic control means 4 is provided with an image processing application for performing image processing using this board.

More specifically, a signal taken by a camera 2 having a light receiving element, for example, an area sensor (512 × 440 pixels) and taking an image of a sample granular material is input to an image processing means 3. The image processing means 3 includes an A / D converter 3a for converting the input signal (NTSC signal) from analog to digital, and optical information relating to the quality of the granular material such as YUV (brightness, The color difference signal and this YUV signal are further converted to HSI (hue, color,
(A luminance) signal, a storage unit 3c having a predetermined capacity, for example, a storage capacity of about 40 × 512 × 512, and storing a value processed by the processing unit 3b, and outputting an image. And an output port 3d. A color monitor 7 is connected to the output port 3d to visually display an input image or an image processed by the image processing means 3. The signal processing operation of the processing unit 3b is performed by an arithmetic control unit 4 described later.
Is controlled by the image processing application stored in the.

The arithmetic control means 4 includes a CPU (central processing element) 4a as a center, a PCI bus 4b as an input / output port of the image processing means 3, an output port 4c for outputting print data to a printer 5, a relational expression, Read-only storage element (hereinafter referred to as “ROM”) 4 storing programs and the like
d, a read / write storage element (hereinafter referred to as "RAM") for storing an image processing application, image data, and the like.
4e, input port 4f for inputting data from outside
Are connected to each other. Input means 8 such as a keyboard is connected to the input port 4f. By the way, as an image processing application, "Visual C ++" (Micros
oft, Inc.) can be used, and the application is stored in the RAM 4e when used. Therefore, after the data captured by the camera 2 is input to the signal processing unit 3, the processing unit 3b of the signal processing unit 3 is operated by the image processing application to change the signal form to NTS.
It converts a C signal into a YUV signal, and further converts a YUV signal into an HSI signal. In addition, the procedure of performing data processing using any part of the signal converted in this way is separately controlled by a program stored in the ROM 4d.

The photographing means 2 will be described with reference to FIGS. As shown in FIGS. 2 and 3, a feeder device 24 (hereinafter referred to as a “feeder”) is provided with a rotating disk 22 made of transparent glass and supported by a rotating shaft 21 of a stepping motor 20. ), The sample granules 25 are supplied onto the disk 22, and the disk 22 is rotated by the motor 20 to move the granules to the other photographing point 26 on the circumference of the disk 22. Feeder 2
A hopper 29 for storing sample particulates in connection with the fourth trough 28; The shooting point 26 includes the disk 22
A donut-shaped light source 30 and a camera 31 and a slit 32 between the light source 30 and the camera 31 are provided above the line of sight 27, assuming a line of sight 27 perpendicular to the line of sight 27. Similar light source 34, camera 35 and slit 36
And are arranged. The cameras 31 and 35 photograph the granular material supplied on the photographing point 26 through the respective slits 32 and 36. Similarly, the light sources 30 and 34 illuminate the granular material at the photographing point 26. Further, beside the light source 34, a surface light source 3 for obliquely illuminating the granular material on the disk 22
8 is provided.

As shown in FIGS. 2 and 3, a background plate 42 in which two types of a milky white plate 40 and a black plate 41 are integrated between the photographing point 26 and the light source 30 so as to block the line of sight 27.
And a background plate 45 in which two types of a milky white plate 43 and a black plate 44 are integrated so as to block the line of sight 27 between the photographing point 26 and the light source 34. That is, as shown in the plan view of FIG. 3, the background plates 42 and 45 are supported by one rotation shaft 47 of the stepping motor 46, and the background plate 42 (the milky white plate 4) is rotated by the rotation of the motor 46.
0, black plate 41), background plate 45 (milky white plate 43, black plate 44), and no background plate 48 so as to be rotatable. Further, as shown in FIGS. 2 and 5, an axis is attached to the rotation axis 51 of the stepping motor 50 between the light source 34 and the slit 36 so that a background plate 49 made of a black plate can be freely replaced so as to block the line of sight 27. It is supported and rotatable.

The photographing means 2 having the above configuration is controlled by a control device 60 shown in a block diagram as shown in FIG. The control device 60 includes an input / output port 62 and a read storage element (ROM) centered on a central processing element (CPU) 61.
63 read / write storage element 64 is connected.
The input / output port 62 includes a motor driving unit 64 and the feeder 2.
4 and the light source driving unit 65, and further the cameras 31, 35 are connected. The motor drive unit 64 includes the motors 20, 44,
49 is connected, and each motor is rotationally driven by a command from the CPU 61 according to a program stored in the ROM 63 in advance. By the rotational driving of the motor, the sample particulate matter 25 in the motor 20 is moved to the photographing point 26.
The background plates 42 and 45 are appropriately replaced in the motor 46, and the background plate 49 is appropriately replaced in the motor 50. The light source driving unit 65 includes the light source 3
The light sources 0, 34, and 38 are connected, and each light source is turned on and off according to a command from the CPU 61 according to a program stored in the ROM 63 in advance. The camera is the control device 60
The image data obtained by shooting is transmitted to the image processing means 3 according to a command from the control device 60.

The ROM 63 stores a program as shown in FIG. When the sample granular material is put into the hopper 29 and measurement is started, the feeder 24 is driven (7-1) and the motor 20 is driven (7-2), and the granular material from the feeder 24 becomes a single layer state. It is supplied to the disk 22. Stop feeder 24 after supplying a certain amount (7-3)
Then, the motor 20 is rotated by a predetermined amount so that the particulate matter reaches the photographing point 26 and stops (7-4). By rotating the motor 46 by a predetermined amount, the milky white plate 43 is arranged at the position of the viewpoint 27,
The lower light source 34 is turned on, the transmitted light is photographed from above the granular material by the upper camera 31 (7-5), and image data is transmitted. The image data obtained at this time includes, for example, 4
There are about 50 granular material images. Next, the motor 46
Is rotated by a predetermined amount, the black plate 44 is placed at the position of the viewpoint 27, the light source is switched to the upper light source 30, and the light source is turned on. The upper camera 31 captures the reflected light of the grain (7-6) and sends the image data. I do. Similarly, by rotating the motor 46 by a predetermined amount, the milky white plate 40 is disposed at the position of the viewpoint 27, and the light source is turned to the upper light source 30.
, And the lower camera 35 photographs the transmitted light from below the granular material (7-7), and sends out image data. Further, the motor 46 is rotated by a predetermined amount so that the black plate 41 is rotated.
Is positioned at the viewpoint 27, the light source is switched to the lower light source 34, and the lower light source 34 is turned on. The lower camera 35 captures the reflected light from below the granular material (7-8) and sends out image data. Finally, the motor 46 is rotated by a predetermined amount to place the background plate 48 at the viewpoint 27 position, the motor 50 is rotated by a predetermined amount to place the black plate 49 at the viewpoint position, and the light source is switched to the surface light source 38 to light up. Then, the transmitted light due to oblique light is photographed from above the granular material by the camera 31 (7-9), and the image data is transmitted. The photographed image data is sent to the image processing means 3. When the photographing of the five screens is completed, the granular material whose photographing is completed by rotating the motor 20 by a predetermined amount is discharged (7-10) by discharging means (not shown) and the processing is completed. It is preferable that the control device 60 of the photographing unit 2 and the arithmetic control unit 4 be electrically connected to each other, and by performing a program to repeatedly execute the above-described operation according to the image data request signal of the arithmetic control unit 4. Can be automated.

The image data transmitted as described above is subjected to image processing by the connected image processing means 3 in accordance with the program stored in the ROM 4d of the arithmetic control means 4. In the following, the transmitted light obtained from the upper camera 31 and the lower camera 35 when the milky white background plates 40 and 43 are used are both subjected to the same image processing, and thus only one description will be given. Similarly, the reflected light obtained from the upper camera 31 and the lower camera 35 when the black background plates 41 and 44 are used are subjected to the same image processing.
First, image processing of image data of transmitted light obtained from the upper camera 31 and the lower camera 35 when the milky white background plates 40 and 43 are used will be described with reference to FIGS.

First, image processing of transmitted image data will be described with reference to FIG. The signal arithmetic and control means 4 transmits the transmission image data (NTS
C signal) (8-1), image data (NTS
C) is converted into a YUV signal by the image processing means 3 (8-2) and stored in the storage section 3c. Further, the arithmetic control unit 4 instructs the image processing unit 3 to perform a binarization process (8-3) on the basis of a predetermined threshold value for each pixel using the luminance signal of the YUV signal of the storage unit 3c. By performing the binarization process, the outline of the granular material can be grasped as shown in FIG. Therefore, a command for extracting (8-4) the contour of the granular material is issued. When the outer shape of the granular material is obtained, the area is obtained from the number of pixels in the outer shape, and the width and length can be specified by determining the long axis and the short axis of the figure by image processing, Is performed later. Here, only one granular material is shown, but usually, since the image data includes a plurality of granular material data, labeling (8-5) for attaching a symbol for identifying each granular material is performed. Further, using the luminance signal among the YUV signals, an instruction is issued to extract (8-6) the edge image from the luminance signal. The edge image is an image obtained by differentiating a luminance signal, and is processed so as to extract a portion having a luminance gradient as a signal. For example, as shown in FIG. 10, when a part of the granular material is colored, or when there is an opaque part in the inner material, the gradient of the luminance of the contour part of the granular material or the boundary part with a different color from the others is used. Since these exist, they can be extracted as an image as shown in FIG. 11 by performing edge processing.

Next, in order to extract the characteristics of the granular material, a command is issued to calculate (8-7) the area, circularity, length, and width for each granular material from the contour of the shaped material. From the edge image, an instruction is made to create (8-8) a histogram of the signal of the edge image for each granular object for the luminance of each pixel. Further, from the luminance signal itself, the granular material 1
An instruction is made to create (8-9) a histogram of the luminance signal for each time. Here, the outline of the granular material is used as the shape information, and the histogram of the YUV signal, the luminance signal, the edge image, and the histogram of the luminance signal are used as the optical information. The above characteristic items are stored (8-10) in the RAM 4e of the arithmetic and control unit 4 for each label of the granular material. As described above, from the transmitted light image data, the diffused light transmitted through the milky white background plate is detected as light related to the shape of the granular material and the internal material of the granular material, and the individual shape and the amount of transmitted light of the sample granular material are detected. By doing so, it is possible to acquire characteristics relating to the shape of the granular material and characteristics of the amount of transmitted light. Note that the luminance signal to be processed here can be a monochrome signal.

Image Processing of Reflected Image Data FIG. 12
This will be described below. The arithmetic control unit 4 takes the reflected image data (NTSC signal) captured by the camera 2 (12-1), and converts the image data (NTSC) into a YUV signal by the image processing unit 3 (12-2). The storage unit 3c is instructed to store the information. Further, the arithmetic control unit 4 includes the storage unit 3
c) convert the YUV signal into an HSI signal (12-3) and store it. Further, it instructs to extract the edge image from the SI (color, luminance) signal (12-4). The contents of the edge image are as described above. Next, in order to extract the feature of the granular material, a histogram of the HSI signal is created for each granular material from the HSI signal (12-).
5) Command to do. From the edge image of the SI signal, an instruction is made to create (12-6) a histogram of the edge image for each granular object. Here, the granular YU
The histogram of the V signal, the HSI signal, the histogram of the HSI signal, and the histogram of the edge image are used as optical information. The above characteristic items are stored in the RAM 4e of the arithmetic and control unit 4. At this time, it is preferable to divert the label of each granular material in correspondence with the label attached at the time of transmission image processing. Alternatively, a label for reflection image processing may be attached separately from the transmission image processing, and the data may be stored so as to correspond to data of the same granular material. As described above, the image data based on the reflected light, that is, the reflected light obtained from the granular material with the black plate as the background is detected as light related to the color of the granular material, and the granular light is detected by detecting the reflected light of each sample granular material. Features related to the color of an object can be obtained. Note that the signal here is a color signal.

Image processing of oblique light transmission image data will be described with reference to FIGS. The arithmetic control means 4 takes the reflected image data (NTSC signal) captured by the camera 2 into the image processing means 3 (13-1), and converts the image data (NTSC) into a YUV signal by the image processing means 3 (13-1). -2) and instruct the storage unit 3c to store the data.
Further, the arithmetic and control unit 4 extracts an edge image from the luminance signal among the YUV signals in the storage unit 3c (13-3). This is because, as shown in FIG. 14, when oblique light is radiated to the granular material having a crack inside at almost right angles to the crack surface, the light irradiation side looks bright and the other dark at the crack surface, so that the brightness When the edge image which is the differential processing is extracted, as shown in FIG. 15, a crack portion can be extracted as a line that traverses (or longitudinally crosses) the granular material. Next, in order to extract the feature of the granular material, the arithmetic and control unit 4 instructs the Hough transform (13-4) of the edge image to specify a line accompanying the crack. The above characteristic items are stored in the RAM 4e of the arithmetic and control unit 4. Here, the YUV signal of the granular material, the edge image, and the value obtained by the buff transform are used as optical information. At this time, the granular material 1
It is preferable to use the labels attached at the time of the transmission image processing in association with each other.

Although the acquisition of the reference light data by the reference plate as the reference is omitted in the above-described image data by the transmitted light, the reflected light, and the oblique light, the brightness and the image of the reference plate are previously taken in as the reference data. It is also possible to correct each image data, more specifically, to average the luminance and color of the background plate as the background.

A granular article position relational expression is stored in the ROM 4d in advance. This granular article position relational expression is obtained as follows. In other words, the granular article position was specified in advance,
From the granular material of known quality, the histogram of the signal of the edge image of the granular material, the circularity, length, width, the edge image of the granular material, the histogram of the luminance signal of the granular material, and the granular material based on the reflected image A HSI signal histogram, a histogram of a granular object edge image, and a signal obtained by Hough transforming a granular object edge image based on an oblique light image,
Using these information as explanatory variables, the target variables are grading, immature grains, dead rice, etc., which are the grades of granular materials such as complete grains and uncompleted grains, and nonlinear analysis such as linear analysis such as multiple regression analysis and neural networks. The analysis is used to create a granular article position relational expression for obtaining a granular article position whose quality is unknown. Therefore, the quality of the unknown granular material can be specified by the information given by the transmitted light image, the reflected light image, or the oblique light image, and the granular material position relational expression, of the unknown granular material. . The above-described information is merely an example, and it is not a necessary condition to use all information. A known analysis method can be used for the linear analysis and the non-linear analysis.

The entire control program of the arithmetic control means 4 after image processing will be further described with reference to FIG. The image data of the sample granular material is obtained from the camera 2 (16-
1) Convert the image data into processable image data (16-2) and store it in the storage unit 3c. The image data obtained here is subjected to image processing (16-3) for each granular material by the arithmetic control means 4 and the image processing means 3 as described above. For example, 450 pieces of image-processed shape information and optical information are obtained. obtain. Based on the shape information and the optical information and the granular article position relational expression, the quality is calculated and specified for each label of the granular material (16-4), and the number of particles for each quality is calculated (16-5). Further, the grain number ratio is calculated (16-6) for each quality. The image processing unit instructs the image processing unit to obtain image data for each particle by dividing an image based on, for example, a YUV signal in the storage unit 3c obtained by processing the reflected image data and store the image data in the storage unit 3c (16-7). In this image processing, first, the outer shape of each grain is determined based on the transmitted light image data, as described above, and the reflected light image data of the same label is divided for each grain based on the outer shape. And finally sort them. When the sample image is created by using the reflected light image data, the color is clear and visually good. The arithmetic control means 4 simultaneously converts the obtained number of grains for each quality and the grain number ratio and a sample image of 450 pieces of image data for each grain into a predetermined format from the output port 4 c to the color printer 5 or the color display 6. (16-8). An example of printing at this time is shown in FIG. Thus, in the present invention, in addition to the grade and the number of grains by grade and the grain number ratio,
A sample image of the sample granular material obtained as an image can be provided additionally. The quality can be determined based on the photographing data of the sample granular material itself obtained for the quality determination of the sample granular material, and a sample image can also be created.

The case where all 450 grains are output as an image may be the same as described above. However, due to the size of the printing paper of the color printer 5 or the resolution of the display 6, one image is output.
When only about 00 particles can be printed and displayed, the processing is performed as shown in FIG. In other words, instead of (16-7) in FIG. 16, the particle number ratio for each quality and the number of printable / displayable particles 10
From the number of 0 grains, the number of grains for each quality is calculated (18-7). The corresponding image data is arbitrarily selected from the storage unit 3c according to the number of grains for each quality (18-8). The obtained number of particles and the ratio of the number of particles for each quality and the selected 100 image data are simultaneously output to the color printer 5 or the color display 6 from the output port 4c in a predetermined format (18-9). An example of printing at this time is shown in FIG.

Alternatively, as shown in FIG. 20, (1) in FIG.
Instead of 6-7), the number of particles for each quality is calculated from the particle number ratio for each quality and the number of 100 particles that can be printed and displayed (20-
7) Yes. From the image data in the storage unit 3c, one image representing quality is selected one by one for each quality (20-8). The number of grains and the grain number ratio for each quality, and the image data for the number of grains for each grade obtained by copying the selected image for each grade for the number of grains previously calculated are output to the output port 4 at the same time.
c to the color printer 5 or the color display 6 (20-9).

[0031]

According to the present invention, when simultaneously printing and displaying the quality of the granular material, the number of particles for each quality, and the particle number ratio, and the sample image of the sample granular material, the quality determination is performed using the photographing data acquired for the quality determination. A sample image can be created, and first, data for quality determination and second, data for sample image creation can be shared, and first and second data can be created.
The image acquisition can be realized by the same means and with a minimum device configuration.

Since the quality of the sample granular material is determined based on the photographing data of the sample granular material itself obtained for the purpose of determining the quality of the sample granular material, a sample image is also created.
In addition to displaying the results of the quality discrimination and the sample images on the same paper, the processing is performed in a series of predetermined procedures in the device, so that the sample granular material that is the source of the quality discrimination and the quality discrimination are displayed at the same time. The identity of the sample image with the particulate matter is reliable.

When the quality of sample granules is determined based on the transmitted light quantity and reflected light quantity obtained from the sample granules composed of a plurality of granules, and the quality discrimination relational expression determined by linear analysis or non-linear analysis, each grain is determined. The processing speed when processing image data is left to the processing speed of the image processing application and the image processing board, and the image processing has been improved with the increase in processing speed. Is also processed at a high speed, and by determining the quality discrimination relational expression in advance, these processes can be speeded up.

As described above, the reliability of the sample image can be improved by sharing the data of the sample image to be added and the data of the quality determination, and the quality determination result and the sample image of the sample granular material can be simultaneously displayed. Since it can be printed and displayed, it is not necessary to store the sample granules to confirm the reliability of the data, and a storage for the quality of the granules is not required.

[Brief description of the drawings]

FIG. 1 is a control block diagram of a granular article position determination device.

FIG. 2 is a simplified side sectional view of a photographing unit.

FIG. 3 is a plan view of a feeder and a glass disk of a photographing unit.

FIG. 4 is a plan view showing the arrangement and rotation of a background plate.

FIG. 5 is a plan view showing the arrangement and rotation of a background plate.

FIG. 6 is a control block diagram of a photographing unit.

FIG. 7 is a flowchart of a photographing unit.

FIG. 8 is a processing flowchart of image data of transmitted light.

FIG. 9 is a diagram illustrating an example of an image obtained by binarizing transmitted light image data.

FIG. 10 is a diagram illustrating an example of transmitted light image data before image processing.

11 is a diagram illustrating an example of an image obtained by performing edge processing on the image in FIG. 10;

FIG. 12 is a processing flowchart of image data of reflected light.

FIG. 13 is a processing flowchart of oblique image data.

FIG. 14 is a diagram illustrating an example of oblique light image data before image processing.

FIG. 15 is a diagram illustrating an example of an image obtained by performing image processing on oblique light image data.

FIG. 16 is a flowchart of the granular article position determination device.

FIG. 17 is an example of a measurement result of printed quality determination.

FIG. 18 is a flowchart illustrating another procedure for creating a sample image.

FIG. 19 is an example of a quality determination measurement result created and printed according to another flowchart.

FIG. 20 is a flowchart illustrating another procedure for creating a sample image.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Granular article position discriminating apparatus 2 Camera 3 Image processing means 4 Arithmetic control means 5 Printer 6 Color display 20 Stepping motor 21 Rotating shaft 22 Rotating disk 23 One of the circumferences 24 Feeder device 25 Sample granular material 26 Shooting point 27 Shooting gaze 28 Trough 29 Hopper 30 Light source 31 Camera 32 Slit 34 Light source 35 Camera 36 Slit 40 Milky white plate 41 Black plate 42 Background plate 43 Milky white plate 44 Black plate 45 Background plate 46 Stepping motor 47 Rotation axis 48 No background plate 49 Background plate 50 Stepping motor 51 Rotation axis

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G01B 11/30 G06M 11/00 D G06M 11/00 G01B 11/24 K F term (Reference) 2F065 AA12 AA23 AA45 AA49 AA51 AA58 AA61 BB05 CC00 DD06 EE00 FF02 FF42 FF61 GG17 GG18 HH12 HH14 HH15 JJ03 JJ05 JJ09 JJ26 LL00 LL28 LL30 NN02 NN20 PP13 QQ00 QQ03 QQ05 QQ13 Q02 QQ1 QQ1 QQQ QQQ QQQ CB02 CD07 DA01 DA08 EA11 EA12 EA14 EA17 EB01 EB09 EC01 EC02 ED07 ED14 ED21 FA01

Claims (12)

[Claims] An image signal of reflected light and transmitted light is received by irradiating light to a plurality of sample granules, and the image signals are subjected to image processing to obtain optical information of the granules, and a shape is formed by the optical information. Information is obtained, based on the optical information and the shape information, a complete grain, a granular material is determined for each granular article position including uncompleted grains, at least the number of grains is counted for each granular article position, and the grain number ratio based on the count is determined. Processing the optical information to create an image of the sample granular material, and simultaneously displaying or printing the image of the determined granular article position-based particle number and particle ratio and the sample granular material. Article position determination method. 2. A method for obtaining a granular article position obtained by obtaining optical information and shape information from a granular material having a known granular article position and analyzing the granular article position as an objective variable and the optical information and shape information as explanatory variables. 2. The granular article position determining method according to claim 1, wherein the quality of the unknown granular object is determined based on the article position relational expression and the optical information and the shape information of the granular object of unknown quality. 3. A sample image for each particle is created for each granular article position from optical information, and the number of particles for each grade is calculated based on a particle number ratio and a predetermined total number of particles. 3. The method according to claim 1, wherein the images are arranged to form an image of the sample granular material. 4. The granular article position discriminating method according to claim 1, wherein the optical information includes hue, color, and luminance of the granular material. 5. A method according to claim 4, wherein the shape information of the granular material is obtained from the optical information by the luminance. 6. The method according to claim 1, wherein the shape information includes a length, a width, and an area of the granular material. 7. A photographing means for acquiring images of a plurality of sample granules based on transmitted light and an image of a plurality of sample granules based on reflected light is connected to the imaging means, and a signal obtained by the imaging means is obtained. Image processing means for converting into optical information relating to the quality of the granular material, a determination process for determining the granular article position based on the optical information,
An arithmetic control unit comprising: an arithmetic process for calculating a granular article position-specific particle number and a particle number ratio; and an image generation process for combining and outputting an image of the granular article position-specific particle number, the particle number ratio, and the granular material, Display means for displaying or printing the number of granules, the particle number ratio, and the image output by the arithmetic control means. 8. A discrimination process in which optical information and shape information are obtained from a granular material having a known granular article position and the optical information and shape information are analyzed using the granular object position as an objective variable and an explanatory variable. 8. The granular article position discriminating apparatus according to claim 7, further comprising a storage unit for storing a granular article position relational expression for the arithmetic control unit. 9. An image generating process, wherein the image processing means creates a sample image for each grain based on the optical information from the optical information and determines the number of grains for each grade based on the grain number ratio and a predetermined total number of grains. 9. The granular article position discriminating apparatus according to claim 7 or 8, wherein the arithmetic processing is performed, and the sample images are arranged based on the calculation result to create an image of the sample granular material. 10. The granular article position discriminating apparatus according to claim 7, wherein the optical information includes hue, color and luminance of the granular material. 11. The granular article position discriminating apparatus according to claim 10, wherein the shape information of the granular material is obtained from the optical information by the luminance. 12. The granular article position discriminating apparatus according to claim 7, wherein the shape information includes a length, a width, and an area of the granular material.