JP3112736B2 - Device for calculating thickness of plate by image processing - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus for calculating the thickness of a plate by image processing.

[0002]

2. Description of the Related Art In a production line for a plate-like body such as a wall panel, the thickness of a measurement portion defined on the plate-like body is measured, and a pass / fail judgment on a standard size is performed. At this time, in the prior art,
The thickness measurement is performed manually using a caliper or the like.

[0003] Japanese Patent Application Laid-Open No. 2-77607 proposes a method for measuring the shape and dimensions using an image processing technique. This prior art makes it possible to measure the dimensions of an object to be measured by binarizing an image signal.

[0004]

However, the prior art has the following problems ( a ) to ( f ) . The measurement operation speed using (i) calipers, etc. is limited and requires a great deal of measuring time.

( B ) When the measurement site of the plate-shaped body has a step such as unevenness, a contact portion such as a caliper is not constant, and it is difficult to maintain measurement accuracy.

( C ) In a dimension measuring apparatus using image processing described in Japanese Patent Application Laid-Open No. 2-77607, a step of an object to be measured is improved in order to improve the accuracy of image processing based on a density difference of the object to be measured. There is no consideration to clarify the density difference occurring at the boundary of the shape.

( D ) In the dimension measuring device based on image processing described in Japanese Patent Application Laid-Open No. 2-77607,
It merely uses experience value as a price level. For this reason, when the object to be measured has uneven color (discoloration) or the like, the binarization level is not appropriate, and as a result, high dimensional measurement accuracy cannot be expected.

( E ) When there is a defect in a part of the edge of the measurement portion of the plate-like body, a large thickness error occurs when the contact portion such as a caliper is brought into contact with the defective portion. Therefore, it is essential for the measurement operator to pay attention to make sure that the contact portion such as a caliper is in contact with a healthy portion having no defect.

( F ) In the dimension measuring device using image processing described in Japanese Patent Application Laid-Open No. 2-77607, if a part of the edge of the measurement site of the measured object has a defect, the defect part It is difficult to perform stable dimension measurement, for example, calculating a dimension value that does not include.

An object of the present invention is to enable the thickness of a plate to be measured in a short time and with high accuracy.

[0011]

According to the present invention, there is provided an apparatus for calculating the thickness of a plate-shaped body by image processing, which calculates the thickness of a measurement site defined by a step-shaped boundary portion of the plate-shaped body. There is provided an imaging device that illuminates an oblique direction of a convex portion forming a step-shaped boundary portion of a plate-like body and captures an image including a shadow created by the illumination, and the step-shaped boundary of an image captured by an imaging device. A threshold value is determined from the density difference of the shadow generated in the portion, the image is binarized, and the number of pixels of the measurement site divided by the binarization process is measured. And an image processing device for calculating the thickness of the measurement site by multiplying the dimension per pixel.

According to a second aspect of the present invention, in the first aspect of the present invention, the shadow is linear.

According to a third aspect of the present invention, in the first aspect of the present invention, when the shadow is planar, a width dimension of the shadow is obtained in advance, and the image processing apparatus includes:
The width dimension of the shadow is added as a correction value to the thickness value obtained from the number of pixels at the measurement site.

The invention according to claim 4, serial to claim 1
In the present invention described above, the image processing apparatus determines a threshold value from a density difference of an image captured by the imaging device, binarizes the image, and performs measurement including a measurement site partitioned by the binarization process. A target image is obtained, the area (A1) of the measurement target image is calculated by multiplying the number of pixels of the measurement target image by a predetermined area per pixel, and the measurement is performed based on the contour shape of the measurement target image. The area (A2) of the target image is calculated, and the above-mentioned threshold value is changed until the values of A1 and A2 substantially match to obtain the optimum threshold value. the image processing those were Unishi by that to calculate the thickness of the measurement site.

According to a fifth aspect of the present invention, there is provided an apparatus for calculating a thickness of a plate-like body by image processing for calculating a thickness of a measurement portion defined on the plate-like body, wherein an image including the measurement site of the plate-like body is obtained. A threshold value is determined based on a density difference between an image capturing device to be captured and an image captured by the image capturing device, and the image is binarized.
The number of pixels of a rectangular portion having one side as a measurement site partitioned by the binarization processing is measured, and the number of pixels of the rectangular portion is multiplied by a predetermined area per pixel to obtain an area of the rectangular portion ( A) is calculated, and the area (A) is divided by a predetermined side length (Y) of the rectangular portion in a direction orthogonal to the measurement site, thereby obtaining a thickness (X) of the measurement site. And an image processing device for calculating the image.

[0016]

According to the present invention, there are the following effects ( a ) to ( f ) . (B) measuring operation speed can optimize by electrically shortening the image processing time can be measured in a short time the thickness of the plate.

( B ) The thickness is measured by image processing based on the density difference generated at the step-shaped boundary portion of the plate-like body. If the step shape (step height, gradient angle, etc.) is constant,
Stable thickness accuracy can be secured. At this time, by forming a shadow on the step-shaped boundary by illumination, the density difference at the step-shaped boundary can be clarified, and the measurement accuracy can be improved.

( C ) By making the shadow in ( b ) linear, the position of the step-shaped boundary can be made clearer, and the measurement accuracy can be further improved.

( D ) Even if the shadow of ( b ) is planar, the measurement accuracy can be further improved by determining the width of the shadow in advance and correcting this.

( E ) Since a procedure for optimizing the binarization level for image processing is provided, image processing is performed using the optimal binarization level (optimal threshold), and color unevenness (discoloration) High thickness measurement accuracy can be ensured even for a plate-like body having the same.

( F ) Image processing is performed by capturing a rectangular portion having a measurement site as one side. Even if there is a defect at a part of the edge of the measurement site, the presence of the defect is diluted and This prevents the detection of a local abnormal dimension corresponding to the defective portion. Therefore, even if there is a defect, the thickness of the plate-shaped body can be measured stably with high accuracy.

[0022]

FIG. 1 is a schematic view showing a thickness measurement state, FIG. 2 is a schematic view showing an image processing procedure, and FIG. 3 is a schematic view showing a defect measurement state.

The dimension measuring system 10 measures the thickness of the measurement site defined on the plate-like body 1 and judges whether the thickness is acceptable or not.

The plate-like body 1 is a wall panel being manufactured in a wall panel manufacturing line, and its thickness is measured by a dimension measuring system 10 installed in the line.

Here, the plate-like body 1 is provided with a convex portion 1A at the center and a peripheral portion 1B, and each measurement site of the total thickness X, the convex portion height t _a , and the peripheral portion thickness t _b is defined. ing.

The dimension measuring system 10 can measure the thickness of the plate-like bodies 1 of all 170 types. In the plate-like body 1, the standard dimensions of the above-described measurement sites are different for each type.

The dimension measuring system 10 has an imaging device 11, an image processing device 12, and a control device 13.

The imaging device 11 captures an image of each measurement site of the plate-shaped body 1 positioned at the dimension measurement position. As the imaging device 11, a CCD camera is used.

The image device 12 performs image processing on an image picked up by the image pickup device 11 and calculates the thickness of each measurement site.

The control device 13 transmits the dimension measurement information (type, standard size, etc.) of the plate-like body 1 to the image processing device 12.

Then, the image device 12 determines whether or not the calculated size of each measurement site is acceptable based on the size measurement information of the plate-shaped body 1 transmitted from the control device 13.

Hereinafter, an image processing procedure by the image processing apparatus 12 will be described. (A) Total thickness (see FIG. 1 (A)) (1) Raw image capture (see FIGS. 2 (A) and 2 (B)) Illumination (high-frequency fluorescent lamp) 31 is applied from the side of the end face of plate-like body 1, A raw image of the entire thickness measurement site is taken into the imaging device 11.

(2) Search for binarization level (see FIG. 2C) A threshold value is determined from the density difference of the raw image picked up by the image pickup device 11. Specifically, it is based on the following ( a ) and ( b ) .

[0034] The raw image captured in the imaging device 11 at (a) the density histogram creation above (1) cut out at a predetermined width (Y), each 512 divided rectangle (in pixels)
A density histogram (density level: 255 levels)
(See FIG. 2C).

( B ) Determination of Threshold From the histogram of (a), the level for binarizing the image (to distinguish between white and black) is determined by the mountain-valley method (binary level = threshold). ).

In (2), since the density distribution is checked for all the objects to be measured, it is possible to flexibly cope with a change in the illuminance of the illumination.

(3) Optimum binarization (see FIG. 2 (D)) ( a ) Binary conversion of the raw image taken in the imaging device 11 in the above (1) by the threshold value obtained in the above (2) To process.

[0038] (b) the measurement target image (white) that contains a measurement site that is defined by the binarization processing (total thickness) of (b) 33
Is calculated by multiplying the number of pixels of the image 33 to be measured by a predetermined area per pixel to calculate the area (A1) of the image 33 to be measured.
3 to the area of the image 33 to be measured (A2
) Is calculated, and the above-mentioned threshold value is changed until A1 and A2 substantially match to obtain an optimum threshold value.

Here, the above ( b ) is specifically as follows:
Perform as in (a) or (b). (a) When the inclination θ of the main axes (short axis and long axis) of the measurement target image 33 is obtained by the moment of inertia theorem

The image 33 to be measured passes through the center of gravity and X
Coordinate system using the moment of inertia Mxx on a straight line parallel to the axis, the moment of inertia Myy on a straight line passing through the center of gravity and parallel to the Y axis, and the moment of inertia Mxy on a straight line passing through the center of gravity and parallel to the X and Y axes. And the intersection angle (slope) θ between the X-axis and the long axis of the inertia ellipse equivalent to the measurement target image 33 is determined.

[0041]

(Equation 1)

The XY coordinates having the inclination direction as the main axis direction are set in the image 33 to be measured, and A2 = XY is obtained from the length X of the short axis and the length Y of the long axis. Then, 0.9 × A2 ≦ A1 ≦ 1.1 × A2 ... until (5) five thresholds of (a) above (in 255 steps)
Change (maximum number of changes: 20).

(B) When there is no inclination in the main axis of the image 33 to be measured A2 = XY is obtained from the maximum length X of the image 33 to be measured and the cutout width Y of the raw image. Then, the threshold value of the above ( a ) is incremented by 5 each time (250 steps ) until A1 ≒ A2 (6).
Change (maximum number of changes: 20).

In the above (3), the threshold value change time for obtaining the optimum binarization level is changed by 20 times.
On the order of seconds.

[0045] (4) at the optimum threshold determined calculating the total thickness (see FIG. 2 (E)) (b) above (3), binarizes the raw image of the above. ( B ) Measurement site (total thickness) calculated by binarization processing
Is measured as the number of pixels of the rectangular portion 34 having the one side.

( C ) The area (A) of the rectangular section 34 is calculated by multiplying the number of pixels of the rectangular section 34 by a predetermined area per pixel. By dividing by the cutout width Y, the dimension X of the measurement site is calculated (see FIG. 3).

As a result, since the measurement site (total thickness) is captured by the rectangular portion 34, the appearance of abnormal dimensions due to the presence of the defective portion 35 as shown in FIG. 3 can be prevented.

(B) Height of convex portion and thickness of ear (see FIG. 1B) (1) Raw image capture Height of convex portion 1A defined by step-shaped boundary portion between plate-shaped body 1 and ear 1B t _a and the thickness t _b of the ear 1B are calculated.

The illumination 31 is applied from obliquely below the ear 1 B constituting the stepped boundary portion, and a raw image including a shadow 32 created by the illumination 31 is taken into the imaging device 11.

The shadow 32 can be made linear by adjusting the installation state of the illumination 31.

When the shadow 32 is planar, the shadow 32
32 width t_awIs obtained in advance. And image processing
The size obtained by the device 12 from the raw image by image processing described later
Law t _a0And t_awIs added as a correction value.

(2) Search for Binarization Level A threshold value is determined from the density difference of the shadow 32 generated at the step-like boundary portion of the raw image picked up by the image pickup device 11. Specifically, it is the same as the above (A) and (2).

(3) Optimum binarization The threshold value in the above (2) is optimized. Specifically,
Same as (A) and (3).

(4) Calculation of the height of the projection and the thickness of the ear Using the optimum threshold value obtained in the above (3), the height t of the projection is calculated.
_a, to calculate the Mimiatsumi t _b. Specifically, the above (A),
Same as (4). At this time, when the shadow 32 of the raw image has the width dimension t _aw , as described above, the value obtained by adding t _aw as a correction value to the dimension t _a0 obtained from the raw image is used as the projection height t. _a .

Next, the operation of the present embodiment will be described. (B) measuring operation speed can optimize by electrically shortening the image processing time can be measured in a short time the thickness of the plate-like body 1.

( B ) The thickness is measured by image processing based on the density difference generated at the step-like boundary portion of the plate-like body 1.
If the step shape (step height, gradient angle, etc.) is constant, stable thickness accuracy can be ensured. At this time, lighting 3
By forming the shadow 32 on the step-like boundary by using 1, the density difference at the step-like boundary can be clarified, and the measurement accuracy can be improved.

( C ) By making the shadow 32 in ( b ) linear, the position of the step-like boundary can be made clearer, and the measurement accuracy can be further improved.

( D ) Even if the shadow 32 of ( b ) is planar,
By measuring the width of the shadow 32 in advance and correcting the width, the measurement accuracy can be further improved.

( E ) Since the procedure for optimizing the binarization level for image processing is included, image processing is performed using the optimal binarization level (optimum threshold), and color unevenness (discoloration) High thickness measurement accuracy can be ensured even for a plate-like body having the same.

( F ) Image processing is performed by capturing a rectangular portion 34 having a measurement site as one side. Even if a portion of the edge of the measurement site has a defect, the presence of the defect 35 is diluted. Thus, detection of a local abnormal dimension corresponding to the defective portion 35 is prevented. Therefore, even if there is a missing portion 35,
The thickness of the plate-like body 1 can be measured stably with high accuracy.

[0061]

As described above, according to the present invention, the thickness of a plate can be measured in a short time and with high accuracy.

[Brief description of the drawings]

FIG. 1 is a schematic diagram showing a thickness measurement state.

FIG. 2 is a schematic diagram illustrating an image processing procedure.

FIG. 3 is a schematic diagram showing a measurement state of a defective portion.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Plate-shaped body 10 Dimension measurement system 11 Imaging device 12 Image processing device 13 Control device 31 Lighting 32 Shadow

Claims (5)

(57) [Claims] An apparatus for calculating the thickness of a measurement portion defined by a step-shaped boundary portion of a plate-shaped body by image processing, wherein the thickness-calculating device comprises a step-shaped boundary portion of the plate-shaped body. An imaging device that illuminates the projection from an oblique direction and captures an image including a shadow created by the illumination; and a threshold value is determined from a density difference of a shadow generated at the step-shaped boundary portion of the image captured by the imaging device. The image is binarized, the number of pixels of the measurement region partitioned by the binarization process is measured, and the number of pixels of the measurement region is multiplied by a predetermined dimension per pixel to perform the measurement. An image processing apparatus for calculating a thickness of a part, the apparatus for calculating a thickness of a plate-shaped body by image processing. 2. The apparatus according to claim 1, wherein the shadow is linear. 3. When the shadow is planar, a width dimension of the shadow is obtained in advance, and the image processing apparatus converts the width dimension of the shadow to a thickness value obtained from the number of pixels of the measurement site. 2. The plate thickness calculating apparatus according to claim 1, wherein the thickness is calculated as a correction value. 4. An image processing apparatus which determines a threshold value from a density difference of an image picked up by an image pickup device, binarizes the image, and includes a measurement target including a measurement region partitioned by the binarization process An image is obtained, the area (A1) of the measurement target image is calculated by multiplying the number of pixels of the measurement target image by a predetermined area per pixel, and the measurement target image is calculated from the contour shape of the measurement target image. Image area (A2)
The optimum threshold value is obtained by changing the above-described threshold value until A1 and A2 substantially match, and the image of the measurement target is binarized by the optimum threshold value. 4. The method according to claim 1, wherein the thickness is calculated.
An apparatus for calculating the thickness of a plate-like body by the image processing described in the above . 5. An apparatus for calculating a thickness of a plate-like body by image processing for calculating a thickness of a measurement site defined on a plate-like body, comprising: an imaging device for capturing an image including a measurement site of the plate-like body; A threshold value is determined from the density difference of the captured image, the image is binarized, and the number of pixels of a rectangular portion having one side as a measurement site partitioned by the binarization process is measured. Is multiplied by a predetermined area per pixel to calculate the area (A) of the rectangular portion, and the area (A) is determined in advance in a direction orthogonal to the measurement site of the rectangular portion. An image processing device for calculating the thickness (X) of the measurement site by dividing the measured length by the length (Y) of the side.