JPH0363553A - Inspection device of grain in threshing treatment - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention provides an imaging means for imaging grains after threshing and extracting a region corresponding to the grain based on imaging information of the imaging means. The present invention relates to an inspection device for threshed grains, which includes an image processing means and a determining means for determining the presence or absence of twig stalks based on information on the extracted region.

[Conventional technology]

If grains with twig stalks are included in the grain after threshing, there is a risk that the grains will be damaged by the twig stalks when dried in a dryer. Thresher performance tests are being conducted to check the grain contamination rate. By the way, if the threshing process is insufficient, twigs will develop. And the contamination rate of twigs with stems is 3
% or less. Therefore, in order to check whether the threshing process is being carried out properly,
Approximately 4,000 to 5,000 grains are removed from the grains after threshing.
It is necessary to take samples and determine the presence or absence of twigs in each grain.

However, if each small grain is checked manually, it will take time to inspect, and there is a risk that the inspection accuracy will vary depending on the skill level of the worker. desired.

By the way, if a grain has a twig stalk attached to it, the area of the grain imaged increases by the amount of the twig inspection, so conventionally, image processing is used to extract the area of the region corresponding to the grain. A means for determining the presence or absence of twig stinks based on the size has been proposed (see, for example, Japanese Patent Application No. 1-125662, previously proposed by the present applicant).

[Problem to be solved by the invention]

However, there are individual differences in the size of grains, and in order to make accurate determinations, it is desirable to be able to determine the length of twig stalks.

However, if the twig stoma is long, the twig stoma may be imaged in a curved state. In order to accurately determine the length of a curved twig, there is a disadvantage that image processing becomes complicated and processing time becomes long. Of course, if image processing is simplified in order to shorten processing time, the risk of misjudgment increases.

The present invention has been made in view of the above-mentioned circumstances, and an object of the present invention is to shorten the processing time required for the discrimination without reducing the accuracy of discrimination of twigs with stems.

[Means to solve the problem]

The inspection device for threshed grain according to the present invention includes: an imaging means for imaging the grain after the threshing process; an image processing means for extracting a region corresponding to the grain based on imaging information of the imaging means; The present invention is equipped with a discriminating means for discriminating the presence or absence of a twig stoma based on the information of the detected region, and its characteristic structure is as follows.

That is, a twig stoma extracting means for extracting a twig stoma region corresponding only to the twig stoma from the region, and a length determining means for determining the length of the twig stoma based on information of the twig stoma extracting means are provided. , when the area of the region is larger than a set value, and when the length of the twig stalk determined by the length determining means is larger than the set value,
The problem lies in that it is configured to determine that there are twigs and stems.

[For production]

When the twig stalk is long and curved, even if the grain is small, the area corresponding to the extracted grain is larger than when the twig stalk is short or when there is no twig stalk attached. becomes significantly larger.

Therefore, if the area of the extracted region is larger than the set value, even if the area is determined to have twig stumps without determining the length of twig stumps, the region without twig stumps will be There is no risk of misjudgment.

However, since there are individual differences in the size of grains, if the area of the extracted area is smaller than the set value, the length of the twig area corresponding to only the twig stoma will be determined. However, as image processing for determining the length, since errors may occur in length determination for long curved twig stomas, processing that can accurately determine the length of relatively short twig stomas is required. A simple process that takes less time can be used.

As a result, the overall processing time can be reduced compared to when image processing is used to accurately determine the length of the twig stalk for the entire grain.

〔Effect of the invention〕

As a result, without reducing the accuracy of identifying twigs with stems,
It has now become possible to reduce the processing time required for the determination.

〔Example〕

EMBODIMENT OF THE INVENTION Hereinafter, an embodiment in which the present invention is applied to a device for inspecting paddy after being threshed will be described based on the drawings.

If the paddy grains after threshing contain brown rice or grains with twig stalks, there will be a high incidence of shell cracking and damage to the grains when drying in a dryer. Because of the disadvantages, this inspection device will be used as a performance test of the threshing device to check the contamination rate of brown rice and twig stalks in the paddy after threshing.

By the way, if the threshing process is excessive, the husks will be removed and the rice will become brown rice, and if it is insufficient, the paddy will be left with twigs and stalks. The contamination rate of brown rice is less than 0.5%, and the contamination rate of twig stalks is 3%.
It is desired that the following be done. Therefore, in order to check whether the threshing process is being carried out properly, samples of approximately 4,000 to 5,000 grains are taken from the grains after the threshing process, and these samples are divided into paddy, brown rice, and grains with twig stalks. It is necessary to determine for each grain which one it is.

As shown in Fig. 1O and Fig. 11, the threshing processing grain inspection device includes a vibrating grain feeding device (1) as a grain feeding means and a conveying terminal of the grain feeding device (L). A belt-type conveyor (2) as a grain conveying means for conveying grains that are dropped and supplied from a section, and a two-dimensional image as an imaging means that repeatedly images the grains conveyed by the conveyor (2) from above. Sensor (3) and the supply device (1)
and a microcomputer-based control device (4) that controls the operation of the conveyor (2) and discriminates defective items based on the image information of the image sensor (3).

As will be described in detail later, the control device (4) is used to binarize the imaging information of the image sensor (3) based on its brightness value to correspond to the grain (A). Image processing means (100
), a twig stoma extraction means (102) for extracting a twig stoma region (Xb) corresponding only to the twig stoma based on the information of the extracted region (X); Length determination means for determining the length of twig stalks (
103), and a discriminating means (101) for discriminating the presence or absence of a twig stoma based on the information of each of these means.

By the way, the conveyance surface of the conveyor (2) is painted black to prevent the influence of reflected light, and the imaging range of the image sensor (3) is controlled by the illumination device (5) to achieve the set brightness. It is illuminated. In addition, in order to be able to capture the state in which the grain (A) is located within the image sensor (3), the image sensor (3),
It is configured so that the image capturing process is repeated at a cycle faster than the conveyance speed of the conveyor (2).

However, the control device (4) does not control the image sensor (
3) every imaging cycle, capturing the imaging information and determining whether the grain (A) is within the imaging field of view (B);
If a grain (A) is present, processing of the captured image information is automatically started.

In addition to the luminance signal (Y) corresponding to the brightness of imaged information, the image sensor (3) also outputs a red signal (R), a green signal (G), and a blue signal (corresponding to the three primary color components). It is configured in color so that it can output each of B). However, image processing will be described later.

To explain the determination of the presence or absence of grains (A), since the conveyance surface of the conveyor (2), which is the background of the imaging field of view (B), is black, there are no grains (
When there is no A), the brightness of the imaging information is low, and when the grain (A) enters the imaging field of view (B), the brightness becomes dog.

Therefore, if it is determined that there is a grain whose brightness is higher than the set threshold based on the imaging information, the grain (
As the set time required for A) to move from the edge of the imaging field of view (B) to near the center elapses, the imaging information is taken in and image processing is started.

Therefore, the grains (A) conveyed by the conveyor (2) are arranged in a line along the conveyance direction, and each grain is spaced apart from each other along the conveyance direction. There is a need to.

Therefore, the vibrating type feeding device (1) uses a structure similar to that of a so-called vibrating parts feeder, etc., to align the supplied grain group in a line while reaching the end of the conveyance. From the conveyance terminal end to the conveyor (
The conveyor (2) is configured to drop and feed the grains to the conveyance start end, and in order to separate the grains that are fed by the fall into individual grains, the conveyor speed of the conveyor (2) is set to be lower than the feed speed of the feeder (1). Also set it to large. In other words, the conveyor (2)
The intervals between the grains conveyed by the conveyor (2) correspond to the difference between the conveyance speed of the conveyor (2) and the supply speed of the feeder (1).

As shown in FIGS. 10 and 11, the vibrating feeding device (1) has a main body (6
), and a drive section (7) that drives the main body section (6) in a micro-vibration state along the circumferential direction.

As shown in FIGS. 12 and 13, the main body (6)
is formed into a cylindrical container whose bottom surface slopes downward from the center toward the inner circumferential wall and whose top end is open.

A spiral shelf (8) rising from the lower bottom surface toward the upper opening is formed on the inner circumferential wall of the main body (6), and from the upper end of the spiral shelf (8) A 7-shaped guide groove (9) is formed in a portion of the conveyor (2) that extends from the conveyance start end to the conveyance end.

The 7-shaped guide groove (9) is formed so that the width changes stepwise from large to small and the depth changes from large to small toward the conveyance terminal end.

That is, the main body part (6) is given microvibrations by the drive part (7), so that the grains (A) introduced into the main body part (6) are moved along the inner circumferential wall part to the spiral shelf. Department (
8) from below to above, and continues to the spiral shelf (8).
By conveying along the 7-shaped guide groove (
By utilizing the change in shape (9) and the vibration of the main body (6), the supplied grains are arranged in a line while reaching the end of the conveyance.

Incidentally, the grains (A) overflowing from the V-shaped guide groove (9) are collected through a grain recovery opening (10 ) to the inner bottom surface of the main body (6) and transported again.

As shown in FIGS. 14 and 15, the supply device (1
), the grains (
A relay member (12) serving as a guide body is formed with a 7-shaped guide groove (11) that takes the receiver and guides it to the starting end of the conveyance surface of the conveyor (2). Said 7
A letter-shaped guide groove (11) is provided in an attitude that is inclined toward the conveyance surface of the conveyor (2).

Then, the relay member (
A reflective optical sensor (13) is provided to detect the presence or absence of grains (A) falling from the optical sensor (12).
13) detects the falling grains (A), the vibration of the feeding device (1) is controlled to be weakened for a set time, so that a plurality of grains (A) This prevents them from being fed to the conveyor (2) at the same time. By setting the conveying speed of the conveyor (2) higher than the feeding speed of the feeding device (1), the grains (A) arranged in rows are transferred to the conveyor (2). The grains are transported at intervals along the transport direction.

In addition, if the grains (A) supplied from the feeding device (1) contain dust or dirt, there is a risk of misjudgment. so that it can be removed automatically.

To explain further, the terminal end of the 7-shaped guide groove (9) of the feeding device (1) is formed to be inclined downward in the conveying direction so that the depth thereof gradually increases, and ,
The terminal end of the 7-shaped guide groove (9) and the relay member (1
2), a distance (K) smaller than the width of the grain (A) is provided between the grain and the starting end of the grain (A). In other words, the dust and dirt transported by the 7-shaped guide groove (9) is
Only the grains (A) are delivered to the relay member (12).

Further, even if dust or dirt is accidentally passed to the relay member (I2), in order to prevent the dust or dust from falling onto the conveyor (2), the relay member (12) A slit-shaped opening (14) is formed at the bottom of the V-shaped guide groove (I1) to allow dust to fall and be removed. A plate-shaped member (
15) is provided.

The driving section (7) will not be described in detail, but it vibrates the main body section (6) at a frequency proportional to the driving frequency and an amplitude proportional to the driving power. ing. In other words, the grain feeding speed of the feeding device (1) is configured to increase as the driving frequency or driving power increases. Therefore, when the optical sensor (13) detects falling grains (A),
By changing the driving frequency or driving power to a smaller side, the supply speed is changed.

In Fig. 10, (16) is the electric motor for driving the conveyor (2), and (17) is the electric motor for driving the conveyor (2), and (17) is the electric motor for driving the conveyor (2). A guide member that guides the device to prevent it from falling laterally outward,
They are provided on both left and right sides of the conveyance start end of the conveyor (2).

Image processing will be explained below.

As mentioned above, the grain (A) is connected to the image sensor (3).
First, based on the value of the luminance signal (Y), the captured image information is displayed at a density of 32 x 32 pixels per screen. The image is converted into binary image information, and the region (X) corresponding to the grain (A) is extracted (see FIG. 3).

However, since the twig stalk is much narrower than the grain (A),
As shown in Fig. 6, when an image is captured in a focused state, the image information is relatively coarsely quantized into 32x32 pixels, so the extracted area (X) becomes grainy due to quantization errors in image processing. There is a possibility that the grain region (Xa) corresponding to the grain (A) and the twig stalk region (Xb) corresponding to the twig stalk are divided, leading to misidentification.

Therefore, by purposely causing the image sensor (3) to take an image in an out-of-focus state, the image signal components corresponding to the grains and twig stalks are expanded, and the quantization error is reduced. This is to make it less likely to occur.

That is, based on the value of the luminance signal (Y), the captured image information is converted into binarized image information at a density of 32 x 32 pixels per screen, and the area (X
) corresponds to the image processing means (100).

Next, image processing for determining whether the grain (A) is brown rice, paddy, or grain with twig stalks will be described.

As mentioned above, if the threshing process is insufficient, twigs will be attached. As a result, the extracted area (X) is
The area of the twig area (Xb) corresponding to the twig stoma is larger than when no twig stump is attached. On the other hand, if the threshing process is excessive, the grains (A) are hulled and become brown rice, which is smaller in size than unhulled paddy.

Therefore, basically, if the area of the area (X) is larger than the size of properly threshed paddy without twig stumps, it is determined that the paddy has twig stumps. It's like letting them do it. Incidentally, since the size of the region (X) is proportional to the number of pixels belonging to the region (X), it is determined that the larger the number of pixels, the larger the area.

However, the size of grains (A) varies due to individual differences even if they are of the same type, so it is difficult to distinguish between paddy and brown rice based only on the size of the area (X). There is a risk of inaccuracy.

Therefore, the color signal information output from the image sensor (3) is used to distinguish between paddy and brown rice.

To explain, if we pay attention to the difference in color between the grains (A) when they are paddy and when they are brown rice, brown rice appears whiter than paddy because it has been hulled.

Therefore, when comparing the distribution states of the three primary color components, the eighth
As shown in the figure, the value of the red light (R) is not much different between paddy and brown rice, but the value of the blue light (B) is significantly greater for brown rice than for paddy. Becomes large.

Although not shown, the value of the green signal (G) is similar to the red signal (R), and there is no significant difference between paddy and brown rice, so the green signal (G) is used instead of the red signal (R). G) may also be used.

Therefore, the red signal (R) of the pixel belonging to the region (X)
When extracting a region where the value obtained by subtracting the blue signal (B) from the above value is larger than the set value for noise removal, the area will be larger in the case of paddy than in the case of brown rice, regardless of individual differences. The size is significantly larger, and the difference between paddy and brown rice is approximately 1
It can be determined with a probability of 00% (see Figure 9).

In other words, the area of the region where the value obtained by subtracting the blue signal (B) from the red signal (R) is larger than the set value for noise removal is larger than the set threshold for distinguishing between brown rice and paddy. By determining whether the grain is large or not, it is possible to simultaneously normalize the brightness of color information and determine whether it is paddy or brown rice.

However, in order to speed up the image processing, when capturing the imaging information of the image sensor (3), in parallel with the quantization of the luminance signal (Y), the red signal (R) is quantized to the blue signal. The value obtained by subtracting the signal (B) is the luminance signal (Y).
Image memory (not shown) is quantized with the same pixel density as
This will be stored in advance.

If it is determined to be paddy, then re-extract the twig stalk region (Xb) (see Figure 3) that corresponds only to the twig stalk from the region (X), calculate its length, and If the length is longer than a set value, it is determined to have twigs and stems.

Next, a process for extracting the twig-stem region (Xb) and determining its length will be described.

Since the twig stalk is much narrower than the main body of the grain (A),
The number of pixels belonging to the twig area (Xb) is smaller than the number of pixels belonging to the grain area (Xa).

Therefore, as shown in FIG. 3, when the frequency distribution of pixels having the same coordinate values on the X and y axes of the imaging field of view (B) is determined, the grain area ( The number of pixels is approximately the maximum at the center of Xa), and the number of pixels gradually decreases toward the outer end of the area (X), and on the side that is along the long plane direction of the twig-stem. The distribution width becomes large.

Therefore, on the side where the distribution width of the frequency distribution of pixels having the same coordinate value on each of the X and y axes is larger, the frequency is smaller than the set frequency corresponding to the size of the paddy, and the width is The center value of the coordinates where is maximum is determined as the grain area (
The value is determined as a value corresponding to the center of Xa).

Next, from the center of the grain region (Xa) toward the outer end of the distribution, which is the far side, a point where the frequency is first smaller than the set frequency set corresponding to the width of the twig stalk. is determined as the boundary (a) between the grain area (Xa) and the twig area (Xb).

By the way, if the twig stoma is extremely long, the end portion may be imaged in a curved state, as shown in FIG. In this way, if the end of the twig stoma is curved,
From the frequency distribution alone, it is not only difficult to distinguish between the upper boundary (a) and the false boundary (C) having the same coordinate values, but also There is a risk of losing sight of the end (b) of the region (Xb).

However, on both the obtained X-axis and y-axis, the obtained boundary (
If you check the adjacency state of pixels for a or C),
It is possible to determine whether it is a correct boundary (a) or a false boundary (c), but the processing becomes complicated, the processing time increases, and the transport speed of the grain (A) There is a risk that it will not be possible to follow.

By the way, when the ends of the twig stalks are long and curved, the area of the region (X) extracted based on the luminance signal (Y) is even larger than when the rice grains are large and have no twig stalks. It's getting bigger.

Therefore, the area (
Simplification of the process for determining the length of a twig with the condition that if the area of This makes it possible to simplify and speed up the entire process.

To explain the length determination of the twig stoma, after finding the starting point of the twig stoma region (Xb),
By sequentially differentiating the pixel to which belongs the pixel in the direction away from the starting point (in the length direction of the twig stump), the line is thinned to a width of one pixel, and the number of pixels, that is, the length of the thinned pixel is found. It's Nishide.

However, as shown in Figure 4, if the extracted pixels are adjacent in a direction parallel to the X-axis or y-axis, l corresponding to one pixel is added as a unit distance, and If they are adjacent, 1 or 4, which corresponds to the diagonal distance of a square, is added as a unit distance. In other words, when pixels belonging to the twig-stem area (Xb) are adjacent to each other diagonally on the image, the length per pixel is made larger than when they are adjacent to each other in the vertical or horizontal direction. By determining the length of the twig, it is possible to accurately determine the length even if the twig is bent or the twig is captured obliquely in the image. -ing

Further, if the twig stoma is bent or extended in a direction intersecting the coordinate direction to be searched, it is determined that the adjacency of pixels belonging to the twig stoma area (Xb) is interrupted by the thinning process by the differentiation. In that case, a value (n) corresponding to the difference in the number of interrupted pixels is added to the unit distance (1 or 1.4). In addition, if the adjacency of pixels belonging to the twig area (Xb) is interrupted due to the thinning process by the differentiation or the quantization error, a straight line approximation is applied between the interrupted pixels when calculating the length. You can.

Based on the determined length of the twig stalk, for example, select a length of less than 8 mm (1 pixel), which is a range that does not affect the drying process.
If it is (equivalent to 5 dots), it is determined that it is a twig infarction.

In other words, the process of determining the boundary (a) between the grain region (Xa) and the twig stalk region (Xb) based on the frequency distribution of pixels having the same coordinate values on the X and y axes is Corresponding to the extraction means (102), the extracted twig stalk region (X
The process of thinning the line b) and determining its length as the number of pixels corresponds to the length determining means (103).

Next, the operation of the control device (4) will be explained based on the flowchart shown in FIG.

A luminance signal (
The image captured in order to separate the grain (A) from the background upon determining that the grain (A) is within the imaging field of view (B) based on the value of Y). sensor
The imaging information in (3) is quantized at the set pixel density, and the region (X) corresponding only to the grain (A) is extracted (see FIG. 3).

After extracting the region (X), first, in order to prevent misclassification due to foreign matter such as dust, the number of pixels belonging to the region (X) is significantly smaller than the size of the grain (A). If the area is smaller than the value corresponding to the set pixel count (set to 20 dots), the imaged object is considered to be dust. It is determined that it is a foreign object such as a foreign object, and is removed from the processing target.

After removing foreign matter such as dust from the processing target, as described above, the number of pixels belonging to the region (X) is set to a value larger than the size when there is no twig stalk (140
It is determined whether the number of pixels is greater than or equal to the set number of pixels, and if the number of pixels is greater than or equal to the set number of pixels, it is determined that the pixel has twigs.

When the area of the region (X) is less than the set number of pixels, the difference between the red signal (R) and the blue signal (B) of the three primary color information output from the image sensor (3) Based on whether the area of the area extracted based on the value is less than or equal to the set value (set to 15 dots), if it is less than the set value, it is determined as brown rice, and if it is larger than the set value. A certain case is determined to be paddy.

If it is determined that it is paddy, next, if the length of the twig stalk obtained as described above is less than the set value (15 dots), it is determined that there is no twig stalk, and the set value is If it is larger, it is determined that it is paddy.

That is, when the area of the region (X) is equal to or larger than the set value, and when the calculated length of the twig stump is greater than the set value, the process of determining that the region (X) has a twig stump is carried out by the discriminating means (101
).

Although not described in detail, the process explained above is performed automatically based on information such as the presence or absence of grains (A) determined based on imaging information until the number of processed samples reaches a set value. It will be repeated.

[Another example]

In the above embodiment, in order to convey the grains (A) to be inspected in a state where each grain is separated from each other, a vibrating feeding device (1) with different conveying speeds and a belt conveyor (1) are used.
2), but the grain (A
) can be changed in various ways, such as means for imaging each particle.

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

[Brief explanation of drawings]

The drawings show an embodiment of the threshed grain inspection apparatus according to the present invention, in which FIG. 1 is a block diagram of the control configuration, FIG. 2 is a flowchart of control operation, and FIGS. 3 to 9 are explanations of image processing. 10 is a schematic plan view of the entire device, FIG. 11 is a schematic side view of the entire device, FIG. 12 is a view taken along the ■-■ arrow in FIG. 10, and FIG. 13 is a schematic plan view of the entire device. 14 is an enlarged perspective view of the conveyance end portion of the supply device, and FIG. 15 is an enlarged side view thereof. (3)...imaging means, (X)...area corresponding to the grain, (Xb)...twig stalk area, (
100)... Image processing means, (101)...
... Discrimination means, (102) ... Twig stalk extraction means, (103) ... Length discrimination means. Figure 5 1111χ

Claims (1)

[Claims] an imaging means (3) for imaging the grain after threshing; an image processing means (100) for extracting a region (X) corresponding to the grain based on the imaging information of the imaging means (3); A discriminating means (101) for determining the presence or absence of twig stumps based on the information of the area (X) that has been detected, the apparatus for inspecting threshed grains, which corresponds only to twig stumps from the area (X). Twig stoma extraction means (10
2) and a length determining means (103) for determining the length of the twig stoma based on the information of the twig stoma extracting means (102).
and the discriminating means (101) is provided with the area (
If the area of Inspection equipment for threshed grain.