JPH03134546A - Inspecting system of granular substance - Google Patents

Abstract

PURPOSE:To correctly and positively inspect the granular substance by providing an image processing device with a granular substance detecting means for detecting whether the image information includes groups of granular substances. CONSTITUTION:An image processing device is constituted by a granular substance detecting means 22 for detecting whether the image information includes groups of granular substances and an extraction practicing means 25 for extracting the checking information of the outer appearance on the basis of the detecting result of the detecting means 22 when the granular substance is judged to be included in the image information. The granular substance detecting means 22 is provided with a discriminating means 23 for discriminating the image information into the information of the transfer surface of a conveyor and the information of the granular substance per every pixel. When the whole of a predetermined number of pixels adjacent to each other within a preset region of the image information is found to be the information of the granular substance by the discriminating means 23, the extraction practicing means 25 detects that the granular substance is included in the image information. Accordingly, the inspecting information of the outer appearance can be positively extracted for all of the granular substance, thereby achieving correct checking of the granular substance.

Description

Detailed Description of the Invention [Industrial Field of Application] The present invention provides an image capturing means for capturing an image of a group of granular objects sequentially conveyed on a conveyor, and a method for detecting the granular objects from image information captured by the image capturing means. Regarding a grain inspection system that is equipped with an image processing device that obtains information on the appearance inspection of grains, for example, the appearance of grains after threshing is inspected to determine the ratio of twig-bearing rice, unhulled rice, and brown rice, and the threshing performance is determined. This invention relates to a particulate matter inspection system for evaluating.

[Conventional technology]

Conventionally, in this type of particulate matter inspection system, the image processing device extracts the visual inspection information of the particulate matter group based on image information captured a certain period of time after the particulate matter group is supplied to the conveyor. was.

[Problem to be solved by the invention]

However, in the conventional particulate matter inspection system described above, due to variations in the transport speed of the conveyor and variations in the initial position of the particulate matter supplied onto the conveyor, the image information to be processed by the image processing device may not include groups of particulates. However, there were disadvantages in that the particles were not included or only part of the particulate matter group was included.

The object of the present invention is to eliminate the above-mentioned conventional drawbacks.

[Means to solve the problem]

In order to achieve this object, the characteristic configuration of the particulate matter inspection system according to the present invention includes a particulate matter detection means for detecting whether or not the particulate matter group is included in the image information; Based on the detection results of the particulate detection means,
and extraction processing execution means for extracting the appearance inspection information when it is determined that the particulate matter is included.

Further, the particulate matter detection means has an identification means for identifying the image information into information corresponding to the conveyance surface of the conveyor and information corresponding to the particulate matter in pixel units, and the identification means uses the image information to It is preferable to detect that the image information includes the particulate matter when all of a predetermined number of adjacent pixels within a predetermined area are identified as information corresponding to the particulate matter.

[Effect]

In other words, the particulate matter detection means detects whether or not the particulate matter group is included in arbitrary image information captured by the imaging means, thereby detecting the image information including the particulate matter group. is identified as image information to be extracted and processed.

Thereafter, the extraction processing execution means performs the extraction processing of visual inspection information based on the image information specified by the particulate matter detection means.

Further, the particulate matter detection means is provided with an identification means for discriminating the image information into information corresponding to the conveying surface of the conveyor and information corresponding to the particulate matter, pixel by pixel, and the identification means Since it is identified that all of the group of granular objects on the conveying surface of the image information are present in the image information, the extraction process execution means can reliably perform the extraction process of the visual inspection information on all the granular objects. can.

〔Effect of the invention〕

Therefore, according to the particulate matter inspection system according to the present invention, image processing is performed on image information that definitely includes a group of particulate matter, so that inspection can be performed accurately and reliably.

〔Example〕

Embodiments of the present invention will be described below based on the drawings.

The particulate matter inspection system that is an embodiment of the present invention detects brown rice and twig stalks with a length longer than a set value, as shown in FIG. This is an image processing system that identifies and separates twig-busted rice from unhulled rice as defective threshing products, and intermittently supplies grains, which are grains, one by one as a group of grains, as shown in Figure 1. A granular material supplying means (1), a granular material transporting means (6) for transporting a group of granular materials supplied by the granular material supplying means (1), and a granular material group on the granular material transporting means (6). An imaging means (8) for taking an image, an image processing device (12) for obtaining predetermined appearance inspection information from the image information taken by the imaging means (8), and an appearance inspection extracted by the image processing device (12). Aggregation device (20) that aggregates information
It is composed of etc.

The granular material supply means (1) includes a hopper (
2), a conveying section (3), and a vibrating section (4),
The grains in the hopper (2) are mechanically vibrated by the vibrating section (4) and fed, and are then dropped and supplied to the granular material conveying means (6) from the conveyance end section (5).

The granular material conveying means (6) is a belt-type conveyor (7).
The granular material feeding means ((1) conveys the grains that are dropped and fed from the granular material feeding means (1).

The imaging means (8) includes an imaging optical system (9), a light source (10) consisting of a plurality of infrared LEDs as illumination light arranged around the imaging optical system (9), and the light source (lO). and a two-dimensional image sensor (11) that inputs the reflected light beam from the image forming optical system (9) through the imaging optical system (9), and the scanning direction of the scanning line of the two-dimensional image sensor (11) is It is installed above the conveyance surface of the conveyor (7) so as to be perpendicular to the conveyance direction of the granular material conveyance means (6).

As shown in FIG. 2, the image processing device (I2) includes an analog processing section (13) that processes the output signal from the imaging means (8), and converts the output signal of the analog processing section (13) into a digital value. an A/D converter (14) that converts the image data into digital values, and an image memory (14) that stores the image data converted into digital values.
5), a high-speed image processing unit (16) that analyzes and processes the image data at high speed, and a CPU (17) that appropriately controls them.
) etc.

The high-speed image processing unit (16) includes a binarization unit (18) that binarizes the image data, and a comparison unit (19) that performs processing such as contraction, expansion, and difference on the binarized image data.
).

The aggregation device (20) is configured by connecting a general-purpose personal computer to the image processing device (12), and as shown in FIG. 26) displays data such as the ratio of brown rice and twig stalk rice to hulled rice, and the distribution of the length of twig stalks.

The operation of the particulate matter inspection system will be explained below based on the flowchart shown in FIG.

First, the conveyor (7) is driven at a constant conveyance speed <#l>.

Next, the vibrating section (4) of the granular material supplying means (1) is driven for a certain period of time to transport the grains in the hopper (2), and the granular material is transported from the transport end section (5). Means (6)
〈I2〉. The driving time of the vibrating section (4) is determined from the amount of grains falling from the conveyance end section (5) and the conveyance speed of the conveyor (7). In other words, the grains supplied onto the conveyor (7) are set so that they do not overlap each other and are scattered within the field of view of the imaging means (8).

In this embodiment, the particles are driven for approximately 0.1 seconds at a conveying speed of 15 cm/s and a vibration frequency of the vibrating section (4) of 60 Hz to drop and supply particles of about 1O particle size.

<I3> The conveyance surface of the conveyor (7) is imaged by the image pickup means (8).

The image processing device (12) detects whether or not the grain is included in the image information captured in step <I3>, and if it is detected that the grain is not included, the image processing device (12) performs step <I4>. Return to I3> and return to the conveyor (7) again.
image the conveyance surface. Further, if it is detected that the grain is included in the image information, the process proceeds to the next step.

In step <I5>, the image processing device (12) extracts the proportions of brown rice, twig-bearing rice, and unhulled rice from the image information as visual inspection information, and uses the visual inspection information as the aggregating device (12).
20). Thereafter, the process returns to step <I2> in order to supply the next group of granules.

That is, the granular material supply means (1) is connected to the control box (21) in synchronization with the end of the operation of the image processing device (12).
By intermittently driving the granules through the , the granule group is intermittently supplied.

Note that the intermittent driving of the particulate matter supplying means (1) may be performed immediately after the start of the operation of the image processing device (12), or may be performed after a certain period of time has elapsed after the start of the operation.

The operations of steps <I4> and <I5> described above will be explained in detail below.

In step <I4>, the image information of the analog signal captured by the imaging means (8) is converted into a digital signal via the analog processing section (13) and the A/D conversion section (14). Among the image information of the digital signal, as shown in FIG. Whether or not pixels indicating data indicating brown rice, twig-roasted rice, and unhulled rice are recognized in the 30 scanning lines on the side is determined based on the level after A/D conversion.

That is, as shown in FIG. 6, identification is made based on the difference between the level indicating the conveying surface of the conveyor (7) and the level indicating the group of particles. If a difference in level is recognized, the next consecutive 8
It is determined whether or not a difference of 8 pixel levels is observed in consecutive pixels adjacent to the pixel in the scanning line of the book. In the case of this example,
One pixel represents approximately 0.27 mm, and 8 pixels or more, that is, approximately 2
．． When a level difference of 2 mm or more is observed, it is identified as particulate matter.

If a difference in level is recognized in this area, it is determined that the subsequent image area, ie, the angle of view of the imaging means (8), always includes all the particles.

That is, the CPU (17) and the execution program, which are the components of the image processing device (12),
22) and an identification means (23).

In step <#5>, as shown in FIG. 7, the binarization means (18) binarizes the image information of the digital signal using two different thresholds (thl) and (th2), and
From the two digitized image data ([Dl) and (ID2), the comparison means (19) extracts the number of brown rice, unhulled rice, and twig stalk rice and the length of twig stalks as appearance inspection information, and calculates the total number of brown rice, unhulled rice, and twig stalk length. to the device (20).

As shown in FIG. 6, the threshold value (thl), (th2
) is a first threshold value (thl) for extracting all brown rice, twig rotten rice, and unhulled rice from the conveyor surface of the conveyor (7), and a threshold value higher than the first threshold (thl) (extracting twig rotten rice and unhulled rice). This is the second threshold value (th2).

To explain in detail the extraction process of visual inspection information by the comparison means (19), <1> All twig stomas are The contraction process is performed until the twigs are erased from the rice, and then the expansion process is performed the same number of times as the contraction process to generate the third image data (ID3), and the first image data (IDI) and the third image data ( I
By taking the difference between D3), fourth image data (ID4) consisting only of twig stomas is generated, and the number of twig stomas is counted.

<2> For the second image data (ID2) that has been binarized using the second threshold (jh2), perform the contraction process in the same way as <1> until all the twig stomas are removed from the twig stomas. Then, the expansion process is performed the same number of times as the contraction process to generate fifth image data (ID5), and the number of unhulled rice is counted.

<3> The fifth image data (105) is further expanded so that the dogness of the unhulled rice included in the fifth image data (ID5) is equal to the size of the unhulled rice included in the third image data (103). to generate sixth image data (ID6),
Third image data ([03) and sixth image data (ID6)
By taking the difference, seventh image data (ID7) consisting only of brown rice is generated, and the number of pieces of brown rice is counted.

<4> Measure the length of each twig stalk from the fourth image data (104), count the number of twig stalks that have a length longer than a predetermined length as defective threshing rice, and determine the number of twig stalks that are less than the predetermined length. The twig stalk with the length of is considered as normal threshed paddy rice, <2>
Add it to the number of unhulled rice calculated in .

<5> The number of unhulled rice, the number of brown rice, the number of twig stalks, and their lengths are transmitted to the aggregation device (20).

In addition, in order to make the size of the unhulled rice included in the fifth image data (ID5) equal to the size of the unhulled rice included in the third image data (ID3), the third image data (103) is subjected to shrinkage processing. Alternatively, the third image data (103) may be contracted and the fifth image data (ID5) may be expanded.

That is, the binarization means (18) and the comparison means (19)
This constitutes an extraction processing execution means (25) that performs the extraction processing of the visual inspection information.

The aggregation device (20) is provided with an evaluation means (24), and the evaluation means (24) or the image processing device (12)
The image processing device (12) sequentially aggregates the visual inspection information from A signal to stop the imaging by the imaging means (8) is transmitted via the imaging means (8), and the imaging is stopped for a predetermined period of time in preparation for the next evaluation.

Incidentally, although reference numerals are written in the claims section for convenience of comparison with the drawings, the present invention is not limited to the groove structure shown in the attached drawings.

[Brief explanation of the drawing]

The drawings show an embodiment of the particulate matter inspection system according to the present invention, in which FIG. 1 is a system configuration diagram, FIG. 2 is a block diagram of an image processing device, and FIG. 3 is a diagram showing an image captured by an imaging means. , FIG. 11 is a display screen diagram of the aggregation device, FIG. 5 is a flowchart, FIG. 6 is a diagram showing the brightness of an image taken by the imaging means, and FIG. 7 is a diagram showing an algorithm for image processing.

Claims (1)

[Claims] 1. An imaging means (8) for imaging a group of granular objects sequentially supplied onto a conveyor (7), and an imaging means (8) for imaging the granular object group from the image information captured by the imaging means (8). A particulate matter inspection system is provided with an image processing device (12) for obtaining appearance inspection information of A particulate matter detection means (22) to be detected and a particulate matter detection means (22) to be detected.
A particulate matter inspection system comprising: an extraction process execution means (25) that performs an extraction process of the appearance inspection information when it is determined that the particulate matter is included based on the detection result of (2). 2. The particulate matter detection means (22) includes an identification means (23) that identifies the image information into information corresponding to the conveying surface of the conveyor (7) and information corresponding to the particulate matter, pixel by pixel.
), and when the identification means (23) identifies all of a predetermined number of adjacent pixels within a predetermined area of the image information as information corresponding to the granular material, the image information The particulate matter inspection system according to claim 1, wherein the particulate matter is detected as being contained in the particulate matter.