TWI608230B - Image generation device, defect inspection apparatus and defect inspection method - Google Patents

Description

Image generating device, defect inspection device, and defect inspection method

The present invention relates to an image generating apparatus that generates image data for inspecting defects of a sheet-like molded body such as a polarizing film or a retardation film, a defect inspecting apparatus including the image generating apparatus, and a defect inspecting method.

As a first prior art defect inspection device for inspecting defects of a sheet-like molded body such as a polarizing film or a retardation film, there is a device using a one-dimensional camera called a line sensor. 12A and 12B are views for explaining the operation in the case where the defect map image L is generated by the one-dimensional image K1 to K19 obtained by the line sensor in the defect inspection device of the first prior art.

The defect inspection apparatus of the first prior art illuminates the sheet-shaped formed body with a linear light source such as a fluorescent tube, and scans the surface of the sheet-shaped formed body with a line sensor from one end to the other end in the longitudinal direction of the sheet-shaped formed body. A plurality of one-dimensional images (still images) K1 to K19 as shown in FIG. 12A are obtained. Furthermore, the one-dimensional image K1 to K19 shown in FIG. 12A performs processing for emphasizing the defective portion (for example, image processing such as binarization) on the image photographed by the line sensor, in each image. The black portion indicates the defect-free portion, and the white portion indicates the defective portion. Further, as shown in FIG. 12B, the defect inspection apparatus of the first prior art generates the defect map image L as a two-dimensional image by spreading a plurality of one-dimensional images K1 to K19 in order of acquisition time, and based on This defect map image L and inspects the defect of the sheet-shaped formed body. Furthermore, in the defect map image L shown in FIG. 12B, the black portion indicates no In the part of the defect, the white part indicates the defective part. Further, the defect map image L is created by fetching the one-dimensional image K1 to K19 before the defect enhancement processing (the original image obtained by the line sensor) in the chronological order, and the defect map is created. The case where the processing of the defect portion is emphasized is performed like L.

In the area observed by the line sensor, a linear light source image is usually included. When the linear light source and the line sensor are disposed on one side of the sheet-shaped formed body, the linear light source image is emitted from the linear light source and is unidirectionally emitted by the sheet-shaped formed body to reach the line sensor. In the case of a light-like image, when a sheet-like formed body is disposed between the linear light source and the line sensor, the linear light source image is emitted from the linear light source and transmits the sheet-shaped formed body to reach the light of the line sensor. Like. In the defect inspection apparatus of the first prior art, when the width of the sheet-like formed body is wide, the plurality of line sensors are arranged in the width direction so that the entire width direction of the sheet-shaped formed body can be inspected. And use.

The defect inspection apparatus of the first prior art examines defects of the sheet-shaped formed body based on the defect map image L which is a two-dimensional image generated by spreading a plurality of one-dimensional images K1 to K19, and thus constitutes a defect. The positional relationship between the inspection target pixel and the linear light source image of each of the one-dimensional images K1 to K19 of the defect map image L has a fixed positional relationship. The defect sometimes appears on the one-dimensional images K1 to K19 only when the positional relationship between the inspection target pixel and the linear light source image is in a specific positional relationship. For example, most of the bubbles which are defects are present on the one-dimensional images K1 to K19 only when they are located at or near the periphery of the linear light source image. As such, defects are sometimes not detected due to their location. Therefore, the defect of the above-mentioned first prior art which inspects the defect of the sheet-shaped formed body using the defect map image L which is a two-dimensional image composed of a plurality of one-dimensional images K1 to K19 obtained by the line sensor is used. The inspection device has only limited defect detection capabilities.

As a second prior art defect inspection device that solves such a problem, there is a device using a two-dimensional camera called an area sensor (see Patent Documents 1 and 2). The defect inspection device of the second prior art illuminates the sheet-shaped molded body with a linear light source such as a fluorescent tube, and will The sheet-shaped formed body is continuously conveyed in a specific conveyance direction, and a two-dimensional image (moving image) is obtained using the area sensor, and the defect of the sheet-shaped formed body is inspected based on the two-dimensional image.

According to the defect inspection apparatus of the second prior art, it is possible to determine whether or not there is a defect based on a plurality of two-dimensional images in which the inspection target pixel and the linear light source image are different in position, so that the first prior art using the line sensor can be used. The defect inspection device more reliably detects the defect. Therefore, the defect inspection apparatus of the second prior art using the area sensor can improve the defect detection capability compared to the defect inspection apparatus of the first prior art using the line sensor.

[Previous Technical Literature]

[Patent Document 1] Japanese Patent Laid-Open Publication No. 2007-218629

[Patent Document 2] Japanese Patent Laid-Open Publication No. 2010-122192

13A and 13B are views for explaining the operation of the defect inspection image device in the second prior art in which the defect map image N is generated by using the two-dimensional images M1 to M6 obtained by the area sensor. In the defect inspection device according to the second prior art, the area sensor performs an imaging operation on the sheet-shaped molded body that is continuously conveyed at predetermined time intervals, and as shown in FIG. 13A, at least partially overlaps with each imaging operation. A plurality of two-dimensional images M1 to M6. Furthermore, the two-dimensional images M1 to M6 shown in FIG. 13A perform processing for emphasizing defective portions (for example, image processing such as binarization) on the image photographed by the area sensor, for each image. In the middle, the black portion indicates the defect-free portion, and the white portion indicates the defective portion.

In the defect inspection apparatus of the second prior art, the two-dimensional images M1 to M6 obtained by the area sensor are between the two-dimensional image M1 and the two-dimensional image M2, the two-dimensional image M2 and the two-dimensional image. Between the M3, between the two-dimensional image M3 and the two-dimensional image M4, between the two-dimensional image M4 and the two-dimensional image M5, and between the two-dimensional image M5 and the two-dimensional image M6 Overlapping overlaps. Therefore, in the defect inspection apparatus of the second prior art, when the two-dimensional images M1 to M6 are successively spread in the order of acquisition time to generate the defect map image N, As shown in FIG. 13B, in one defect map image N, there are a plurality of defective pixels (for example, defective pixel N1 of FIG. 13B) which display the same defect. When the defect of the sheet-like formed body is inspected using such a defect map image N, it is difficult to accurately grasp the position of the defect of the sheet-shaped formed body. Also, the same defect is repeatedly detected.

The present invention is an image generating apparatus for producing an image for inspecting a defect of a sheet-shaped formed body, and an object thereof is to provide a position capable of accurately inspecting a defect of a sheet-shaped formed body with a high detection ability, and preventing duplicate detection from being the same Defect image generating device, defect inspection device, and defect inspection method.

The present invention provides an image generating apparatus that generates an image for inspecting a defect of a sheet-shaped formed body, and includes a conveying unit that conveys the sheet-shaped formed body in a longitudinal direction at a predetermined conveying speed; The light-irradiating portion irradiates the sheet-shaped molded body to be conveyed with light, and the image-forming portion is disposed to face the surface of the sheet-shaped formed body to be conveyed, and the sheet-shaped formed body is imaged at predetermined time intervals. a plurality of two-dimensional images are generated on one of the surfaces, and the time interval is set such that one of the imaging regions captured by the two consecutive imaging operations partially overlaps; the feature amount calculation unit is determined in advance The algorithm processing calculates the feature amount of each pixel constituting each of the two-dimensional images based on the luminance value of each pixel, and the processed image data generating unit divides each pixel constituting each of the two-dimensional images into the above-described features a defective pixel having a predetermined value or more and a residual pixel having the feature amount not reaching the threshold value, and generating a processed image corresponding to each two-dimensional image, the processing map The image system assigns a tone value corresponding to the feature amount to the defective pixel, and assigns a zero-order tone value to the residual pixel; and a defect map image generation unit that is generated by the processed image data generation unit a plurality of processed images, thereby producing a distribution indicating defects of the sheet-shaped formed body a defect map image, comprising: a defect map image coordinate value calculation unit that calculates a defect map for constructing the defect map based on a coordinate value of each pixel constituting each processed image, the transport speed, and the time interval a coordinate value of each pixel of the image; an accumulation unit that performs either one of the following (1) or (2), or both (1) and (2) below: (1) Each pixel of the defect mapping image counts the number of defective pixels in the corresponding pixel in the processed image; (2) calculating, for each pixel of the defect mapping image, the corresponding pixel assigned to the processed image And a luminance value setting unit that calculates the value based on the total number of defective pixels obtained by the above (1) and/or the total of the gradation values obtained by the above (2), as the defect The luminance value of each pixel of the image is mapped and set, thereby generating a defect map image.

Further, in the image generating apparatus of the present invention, the time interval is preferably such that a length of the longitudinal direction of the image capturing area partially overlapped is 1/2 of a length of the longitudinal direction of each of the two-dimensional images. Set more than the above.

Moreover, the present invention provides a defect inspection apparatus including: the image generation device; and a display unit that displays a defect map image generated by the defect map image generation unit of the image generation device.

Moreover, the present invention provides a defect inspection method for inspecting a defect of a sheet-shaped molded body, and includes a transfer step of transporting the sheet-shaped formed body to a longitudinal direction thereof at a predetermined transport speed by the transport unit. In the light irradiation step, the sheet-shaped molded body to be conveyed is irradiated with light, and the image capturing step is arranged to face the surface of the sheet-like formed body to be conveyed. The imaging unit captures a part of the surface of the sheet-shaped formed body at a predetermined time interval to generate a plurality of two-dimensional images, and partially overlaps one of the imaging regions captured by the two consecutive shooting operations. Setting the time interval; the feature amount calculating step calculates the feature amount of each pixel constituting each of the two-dimensional images based on the luminance value of each pixel by a predetermined algorithm processing; and processes the image data generating step to construct Each pixel of each of the two-dimensional images is divided into a defective pixel having a feature amount equal to or greater than a predetermined threshold value, and a residual pixel having the feature amount not reaching the threshold value, and a processed image is generated corresponding to each two-dimensional image. The processed image is provided with a tone value corresponding to the feature quantity to the defective pixel, and a zero-order key value is added to the residual pixel; a defect mapping image generating step is generated by the processing image data generating step a plurality of processed images, thereby generating a defect map image indicating a distribution of defects of the sheet-shaped formed body, and comprising: a defect map image holder The scalar value calculation step calculates a coordinate value of each pixel constituting the defect map image based on a coordinate value of each pixel constituting each processed image, the transport speed, and the time interval, and an accumulation step performs the following steps (1) or either of the following (2) or both of the following (1) and (2): (1) for each pixel of the defect map image, the correspondence in the processed image is counted The number of defective pixels in the pixel; (2) calculating, for each pixel of the defect mapping image, a total of the tone values assigned to the corresponding pixels in the processed image; and the brightness value setting step, based on utilizing the above (1) The number of defective pixels obtained and/or the value calculated by the total of the gradation values obtained in the above (2) is set as the luminance value of each pixel of the defect map image, thereby generating a defect map An image; and a display step of displaying the defect generated in the step of generating the defect map image Shoot the image.

According to the present invention, the image generating apparatus generates a device for inspecting an image of a defect of the sheet-shaped formed body, and includes a transport unit, a light-irradiating unit, an imaging unit, a feature amount calculating unit, a processed image data generating unit, and Defect map image generation unit. In the image generating apparatus, the image pickup unit generates a plurality of two-dimensional images by photographing the surface of the sheet-shaped molded body conveyed by the transport unit at a predetermined time interval while irradiating light by the light-irradiating portion. The imaging unit sets the time interval such that one of the imaging regions captured by the two consecutive imaging operations partially overlaps. When a plurality of two-dimensional images generated in this manner are observed by two two-dimensional images generated in two consecutive shooting operations, the images are partially overlapped in a direction parallel to the longitudinal direction of the sheet-shaped formed body. .

The feature amount calculation unit calculates the feature amount based on the luminance value of each pixel constituting each two-dimensional image by processing each of the two-dimensional images by a predetermined algorithm.

The processed image data generating unit divides each of the pixels constituting each of the two-dimensional images into a defective pixel whose feature amount is equal to or greater than a predetermined threshold value, and a residual pixel whose feature amount does not reach the threshold value, and each two-dimensional map A processed image is generated correspondingly, and the processed image is given a tone value corresponding to the feature amount to the defective pixel, and a zero-order key value is given to the residual pixel.

The defect map image generating unit generates a portion of the defect map image by synthesizing a plurality of processed images generated by the processed image data generating unit, and has a defect map image coordinate value calculating unit, an accumulating unit, and a luminance value setting. unit.

The defect map image coordinate value calculation unit calculates the coordinates for constituting the defect map based on the coordinate value of each pixel constituting each processed image, the transport speed of the sheet-shaped molded body, and the time interval set for the image pickup unit. The coordinate value of the pixel.

The accumulating unit performs either one of the following (1) or the following (2), or both of the following (1) and the following (2).

(1) Counting the corresponding pixels in the processed image for each pixel of the defect map image The number of defective pixels in the middle.

(2) For each pixel of the defect map image, the total of the tone values assigned to the corresponding pixels in the processed image is calculated.

Further, the luminance value setting unit calculates a value based on the total number of defective pixels obtained by (1) in the accumulation unit and/or the gradation value obtained by (2), and is used as each pixel of the defect map image. The luminance value is set, thereby generating a defect map image.

In the image generating apparatus of the present invention configured as described above, a defect map for detecting an image of a defect of the sheet-shaped formed body is generated based on a two-dimensional image of the sheet-like formed body produced by the image pickup unit. For example, a higher defect detection capability can be maintained compared to a case where an image for checking a defect is generated based on a plurality of one-dimensional images obtained by, for example, a line sensor.

Further, in the image generating apparatus of the present invention, the defect map is calculated based on the coordinate value of each pixel constituting each processed image, the transport speed of the sheet-shaped molded body, and the time interval set for the imaging unit. The coordinate value of each pixel. Further, since the luminance values of the pixels corresponding to the calculated coordinate values are set based on the total number of defective pixels in the pixels in which the pixels in the image are processed and the same coordinate value are calculated, Since the defect map image is generated, the defect of the sheet-like formed body can be inspected by using the defect map image, and the position of the defect of the sheet-shaped formed body can be accurately inspected with high detection capability. In the defect mapping, since the same defect occurs in one portion, repeated detection of the same defect can be prevented.

Moreover, according to the present invention, the defect inspection device includes the image generation device and the display unit of the present invention described above. The display unit displays a defect map image generated by the defect map image generating unit of the image generating device. By observing the defect map image displayed on the display unit by the user, the position of the defect of the sheet-shaped formed body can be confirmed.

Moreover, according to the present invention, the defect inspection method is a method for inspecting a defect of a sheet-shaped formed body, and includes a conveying step, a light irradiation step, an image capturing step, and a feature amount calculation step. And processing the image data generating step, the defect mapping image generating step, and the displaying step.

In the imaging step, a plurality of two-dimensional images are generated by imaging the surface of the sheet-shaped formed body conveyed by the imaging unit at a predetermined time interval while irradiating light. In the imaging step, the time interval is set such that one of the imaging regions captured by the two consecutive imaging operations partially overlaps. When a plurality of two-dimensional images generated in this manner are observed by two two-dimensional images generated in two consecutive shooting operations, the images are partially overlapped in a direction parallel to the longitudinal direction of the sheet-shaped formed body. .

In the feature amount calculation step, the feature amount based on the luminance value of each pixel constituting each two-dimensional image is calculated by processing each of the two-dimensional images by a predetermined algorithm. In the processed image data generating step, each pixel constituting each of the two-dimensional images is divided into a defective pixel having a feature amount equal to or greater than a predetermined threshold value, and a residual pixel having the feature amount not reaching the threshold value, and each of the pixels The two-dimensional image correspondingly generates a processed image that gives a tone value corresponding to the feature amount to the defective pixel, and assigns a zero-order tone value to the residual pixel.

In the defect map image generating step, the defect map image is generated by synthesizing a plurality of processed images generated in the image generating step. The defect map image generation step includes a defect map image coordinate value calculation step, a calculation number accumulation step, and a luminance value setting step.

In the defect map image coordinate value calculation step, the defect map is calculated based on the coordinate value of each pixel constituting each processed image, the transport speed of the sheet-shaped molded body, and the time interval set for the imaging unit. The coordinate value of each pixel.

In the accumulation step, either one of the following (1) or the following (2) or both of the following (1) and the following (2) are performed.

(1) Counting the number of defective pixels in the corresponding pixels in the processed image for each pixel of the defect map image.

(2) Calculate the correspondence given to the processed image for each pixel of the defect map image The sum of the gradation values of the pixels.

In the luminance value setting step, the value calculated based on the total number of defective pixels obtained by (1) in the accumulation step and/or the gradation value obtained by using (2) is used as each pixel of the defect map image. The brightness value is set, thereby generating a defect map image.

Moreover, in the displaying step, the defect map image generated in the defect map image generating step is displayed.

In the defect inspection method of the present invention thus constituted, a defect map image for inspecting a defect of the sheet-shaped formed body, that is, a defect map image, is generated based on a two-dimensional image of the sheet-like formed body generated in the image pickup step. Therefore, a higher defect detection capability can be maintained as compared with a case where an image for checking a defect is generated based on a plurality of one-dimensional images obtained by, for example, a line sensor.

Further, in the defect inspection method of the present invention, in the defect map image generating step, the coordinate value of each pixel constituting each processed image, the transport speed of the sheet-shaped molded body, and the time interval set for the imaging unit are The coordinate values of the pixels used to form the defect map image are calculated. Further, since the luminance values of the pixels corresponding to the calculated coordinate values are set based on the total number of defective pixels in the pixels in which the pixels in the image are processed and the same coordinate value are calculated, Since the defect map image is generated, the defect of the sheet-shaped formed body is inspected by observing the defect map image displayed in the display step, whereby the position of the defect of the sheet-shaped formed body can be accurately inspected with a high detection capability. In the defect mapping, since the same defect occurs in one portion, repeated detection of the same defect can be prevented.

1‧‧‧Image generating device

2‧‧‧Sheet shaped body

3‧‧‧Transporting device

4‧‧‧Lighting device

5‧‧‧ camera

6‧‧‧Image processing device

7‧‧‧Image analysis device

21‧‧‧Display Department

61‧‧‧Processing Image Generation Department

71‧‧‧Processing image input section

72‧‧‧Defect mapping image generation unit

73‧‧‧Control Department

100‧‧‧ Defect inspection device

721‧‧‧ coordinate value calculation unit

722‧‧‧Accumulate

723‧‧‧Brightness value setting unit

A‧‧‧ two-dimensional image

A1‧‧‧ illumination image

A3‧‧‧ upper limit edge

A4‧‧‧ lower edge

A21‧‧‧1st defective pixel group

A22‧‧‧2nd defective pixel group

A‧‧‧data point

B‧‧‧2D image

B1‧‧‧ illumination image

B21‧‧‧1st defective pixel group

B22‧‧‧2nd defective pixel group

B‧‧‧data points

C‧‧‧2D image

C1‧‧‧ illumination image

C21‧‧‧1st defective pixel group

C22‧‧‧2nd defective pixel group

C31‧‧‧ core

C‧‧‧data points

D‧‧‧ two-dimensional image

D1‧‧‧ illumination image

D3‧‧‧ edge

D21‧‧‧1st defective pixel group

D22‧‧‧2nd defective pixel group

D‧‧‧data points

E1~E6‧‧‧Processing images

F‧‧‧Defect mapping image

F‧‧‧ forecast data points

G1~G13‧‧‧Processing images

H‧‧‧Defect mapping image

J‧‧‧ Defect map image

K1~K19‧‧‧1D image

L‧‧‧ Defect map image

M1~M6‧‧‧2D image

N‧‧‧ Defect map image

N1‧‧‧ Defective pixels

P1‧‧‧ edge distribution

P2‧‧‧ differential distribution

P3‧‧‧Brightness distribution

P4‧‧‧Brightness value difference distribution

P5‧‧‧ Smoothing distribution

P6‧‧‧ edge distribution

P7‧‧‧ edge distribution

P11‧‧‧ peak

P21‧‧‧ peak

P22‧‧‧Characteristics

P31‧‧‧ trough part

P41‧‧‧ peak

P42‧‧‧Characteristics

P51‧‧‧ peak

P52‧‧‧Characteristics

P61‧‧ points

P62‧‧‧ points

P63‧‧‧ area

P71‧‧ points

P72‧‧ points

P73‧‧‧ imaginary straight line

P74‧‧‧Arc

P711‧‧‧ tangent

P721‧‧‧ tangent

R‧‧‧ radius of curvature

S1~s7‧‧‧ steps

S6-1~s6-3‧‧‧Steps

X‧‧‧ direction

Y‧‧‧ direction

Z‧‧‧Transfer direction

11‧‧‧ angle

22‧‧‧ angle

33‧‧‧ angle

Fig. 1A is a flow chart showing the steps of a defect inspection method according to an embodiment of the present invention.

Fig. 1B is a view showing the steps of a defect map image generating step in an embodiment of the present invention.

Fig. 2 is a schematic view showing the configuration of a defect inspection apparatus 100 according to an embodiment of the present invention.

FIG. 3 is a block diagram showing the configuration of the defect inspection apparatus 100.

4A is a diagram for explaining an edge distribution method which is an example of a defect detection algorithm, and is a view showing an example of a two-dimensional image A corresponding to two-dimensional image data generated by the imaging device 5.

FIG. 4B is a view showing an example of the edge distribution P1 created by the processed image generating unit 61.

4C is a view showing an example of the differential distribution P2 created by the processed image generating unit 61.

5A is a view for explaining another example of the defect detection algorithm, that is, a peak method, and is a view showing an example of a two-dimensional image B corresponding to two-dimensional image data generated by the imaging device 5.

FIG. 5B is a view showing an example of the luminance distribution P3 created by the processed image generating unit 61.

Fig. 5C is a diagram for explaining a procedure for setting a particle point to be moved from one end of the data point to the other end by the processed image generating unit 61.

FIG. 5D is a view showing an example of the luminance value difference distribution P4 created by the processed image generating unit 61.

6A is a view for explaining a smoothing method which is still another example of the defect detecting algorithm, and is a view showing an example of a two-dimensional image C corresponding to the two-dimensional image data generated by the image pickup device 5.

FIG. 6B is a view showing an example of the smoothing distribution P5 generated by the processed image generating unit 61.

FIG. 7A is a view for explaining a second edge distribution method which is another example of the defect detection algorithm, and shows a two-dimensional image D corresponding to the two-dimensional image data generated by the imaging device 5. A picture of an example.

FIG. 7B is a view showing an example of the edge distribution P6 created by the processed image generating unit 61.

FIG. 7C is a view showing an example of the edge distribution P7 created by the processed image generating unit 61.

8A and 8B are views showing an example of processed images E1 to E6 generated by the image processing device 6.

FIG. 9 is a view showing an example of the defect map image F generated by the image analysis device 7.

FIG. 10A is a view showing an example of the processed images G1 to G13 which is another example of the processed image generated by the image processing device 6.

FIG. 10B is a view showing an example of the defect map image H which is another example of the defect map image generated by the image analysis device 7.

Fig. 11A is a view showing an example of processed images G1 to G13 including a one-dimensional image generated by the image processing device 6.

Fig. 11B is a view showing an example of the defect map image J generated by successively spreading the processed images G1 to G13.

Fig. 12A is a view showing an example of one-dimensional images K1 to K19 obtained by the line sensor in the defect inspection device of the first prior art.

Fig. 12B is a view showing an example of the defect map image L generated by spreading the one-dimensional images K1 to K19 in order of acquisition time.

Fig. 13A is a view showing an example of two-dimensional images M1 to M6 obtained by the area sensor in the defect inspection apparatus of the second prior art.

Fig. 13B is a view showing an example of the defect map image N generated by spreading the two-dimensional images M1 to M6 in order of acquisition time.

1A and 1B are diagrams showing the steps of a defect inspection method according to an embodiment of the present invention. Step chart. The defect inspection method according to the present embodiment includes the transport step s1, the light irradiation step s2, the imaging step s3, the feature amount calculation step s4, the processed image data generation step s5, the defect map image generation step s6, and the display shown in FIG. 1A. Step s7. Further, the defect map image generating step s6 includes the defect map image coordinate value calculating step s6-1, the accumulating step s6-2, and the luminance value setting step s6-3 shown in FIG. 1B.

Fig. 2 is a schematic view showing the configuration of a defect inspection apparatus 100 according to an embodiment of the present invention. FIG. 3 is a block diagram showing the configuration of the defect inspection apparatus 100. The defect inspection device 100 of the present embodiment is a device for detecting a defect of the sheet-like molded body 2 such as a thermoplastic resin, and includes the image generating device 1 and the display unit 21 of the present invention. The image generation device 1 of the defect inspection device 100 includes a transfer device 3, an illumination device 4, an imaging device 5, an image processing device 6, and an image analysis device 7. The defect inspection device 100 implements the defect inspection method of the present invention. The transport device 3 performs the transport step s1, the illumination device 4 performs the light irradiation step s2, the imaging device 5 performs the imaging step s3, the image processing device 6 executes the feature amount calculation step s4, and the processed image data generation step s5, and the image analysis device 7 The defect map image generation step s6 is executed, and the display unit 21 performs the display step s7.

In the defect inspection apparatus 100, the sheet-like molded body 2 having a constant pitch and continuous in the longitudinal direction is fixed in the fixed direction (the same length direction as the width direction of the sheet-like molded body 2) The direction is conveyed at a predetermined transport speed, and the sheet surface illuminated by the illumination device 4 is imaged by the imaging device 5 at a predetermined time interval to generate a two-dimensional image. The image processing device 6 generates a processed image corresponding to each of the plurality of two-dimensional images, and the image analyzing device 7 combines the plurality of processed images output from the image processing device 6 to generate a defect map image, and the display portion 21 The defect map image is displayed, and the defect detection of the sheet-like formed body 2 is performed.

The sheet-like molded body 2 to be inspected is subjected to a treatment such as smoothing the surface or providing a concave-convex shape by passing the thermoplastic resin extruded from the extruder through the gap between the rolls, and is pulled by cooling on the conveying roller. The roller is drawn and formed. Applicable to the sheet form of this embodiment The thermoplastic resin of the molded body 2 is, for example, a methacrylic resin, a methyl methacrylate-styrene copolymer (MS resin), a polyolefin such as polyethylene (PE) or polypropylene (PP), or a polycarbonate (PC). ), polyvinyl chloride (PVC), polystyrene (PS), polyvinyl alcohol (PVA), cellulose triacetate resin (TAC), and the like. The sheet-like formed body 2 is molded from a single layer sheet, a laminated sheet or the like of the thermoplastic resin.

Further, examples of the defects generated in the sheet-like molded body 2 include dot-like defects (point defects) and creases such as bubbles, fish eyes, foreign matter, footprints, scratches, and scratches generated during molding. A so-called knick produced by printing, etc., a linear defect (line defect) such as a so-called original stripe which is caused by a difference in thickness.

The conveying device 3 has a function as a conveying unit, and conveys the sheet-shaped formed body 2 in a fixed direction (transporting direction Z) at a predetermined conveying speed. The conveying device 3 includes, for example, a feeding roller and a receiving roller that convey the sheet-shaped molded body 2 in the conveying direction Z, and measures the conveying distance by a rotary encoder or the like. In the present embodiment, the conveying speed is set to about 2 to 30 m/min in the conveying direction Z.

The illuminating device 4 has a function as a light-irradiating portion, and illuminates the width direction of the sheet-like molded body 2 orthogonal to the transport direction Z in a line shape. The illumination device 4 is disposed such that the image captured by the imaging device 5 includes a linear reflection image. Specifically, the illumination device 4 faces the sheet-like molded body 2 on the same side as the image pickup device 5, and faces the surface of the sheet-like molded body 2, and the illumination region on the surface of the sheet-like molded body 2, that is, the image pickup. The distance from the imaging area captured by the apparatus 5 is set to, for example, 200 mm.

As a light source of the illumination device 4, an LED (Light Emitting Diode), a metal halide lamp, a halogen transmission lamp, a fluorescent lamp, or the like is irradiated with light that does not affect the composition and properties of the sheet-like formed body 2. There is no special limit. Further, the illumination device 4 may be provided on the opposite side of the imaging device 5 via the sheet-like molded body 2. In this case, the image captured by the imaging device 5 includes the transmission image of the transmissive sheet-like formed body 2. In addition, in FIG. 2, the light source which extended in the width direction of the sheet-form molding 2 in the linear direction is illustrated. The illuminating device 4 is not limited to such a configuration. As the illumination device 4, various configurations corresponding to the types of defect detection algorithm processing performed by the processed image generation unit 61 which will be described later are considered. For example, a configuration in which the illumination device 4 having the slit member disposed between the light source and the sheet-like molded body 2 is provided may be employed.

The defect inspection apparatus 100 includes a plurality of imaging devices 5 having a function as an imaging unit, and each imaging device 5 is arranged at equal intervals in a direction orthogonal to the transport direction Z (width direction of the sheet-like molded body 2). Moreover, the imaging device 5 is disposed such that the direction from the imaging device 5 to the center of the imaging region of the sheet-like molded body 2 and the transport direction Z form an acute angle. The imaging device 5 captures a two-dimensional image of a reflection image or a transmission image (hereinafter collectively referred to as an "illumination image") obtained by the illumination device 4 including the sheet-like molded body 2 at a predetermined time interval (imaging interval). Like, to generate a plurality of two-dimensional images. In the imaging device 5, the time interval is set such that one of the imaging regions captured by the two consecutive imaging operations partially overlaps. As described above, the two two-dimensional images generated in the two consecutive shooting operations are images that partially overlap each other in the direction parallel to the longitudinal direction of the sheet-like molded body 2.

The imaging device 5 includes a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor) area sensor that captures a two-dimensional image. As shown in FIG. 2, the imaging device 5 is disposed so as to capture the entire region in the width direction orthogonal to the transport direction Z of the sheet-like molded body 2. By photographing the entire region in the width direction of the sheet-like molded body 2 and transporting the sheet-like molded body 2 continuous in the transport direction Z, the defects of the entire region of the sheet-like molded body 2 can be efficiently inspected.

The imaging interval of the imaging device 5 can be fixed, and can be changed by the user operating the imaging device 5 itself. Further, although the imaging interval of the imaging device 5 may be a time interval of continuous shooting of the digital still camera, that is, a fraction of a second, etc., in order to improve the efficiency of the inspection, it is preferably a short time interval, for example, ordinary moving image data. The imaging interval is 1/30 second, etc.

Moreover, the imaging interval of the imaging device 5 is preferably such that an image capturing area partially overlaps The length of the transport direction Z is 1/2 or more times the length of the transport direction Z of the two-dimensional image, that is, the distance at which the sheet-like molded body 2 is transported at a time determined by the imaging interval becomes the length of the transport direction Z of the two-dimensional image. Set it by 1/2 or less. In other words, the length of the transport direction Z of the two-dimensional image captured by the imaging device 5 is preferably such that the imaging device 5 takes the two-dimensional image and takes the time before the next two-dimensional image is taken. The transport distance of the body 2 is more than twice. That is, it is preferable to image the same portion of the sheet-like formed body 2 twice or more. In this manner, the length of the transport direction Z of the two-dimensional image is made larger than the transport distance of the sheet-like molded body 2 after the image pickup device 5 takes in the two-dimensional image and before the next two-dimensional image is taken, and the sheet shape is increased. The number of times of imaging of the same portion of the molded body 2 can thereby detect defects with high precision.

The image processing device 6 includes a processed image generating unit 61 having a function as a feature amount calculating unit and a processed image data generating unit. The image processing device 6 is provided corresponding to each of the plurality of imaging devices 5. The processed image generating unit 61 can be an image processing board or an image pickup device such as an FPGA (Field-Programmable Gate Array) or a GPGPU (General-purpose Computing on Graphics Processing Unit). This is achieved by the internal hardware of the device 5.

The processed image generating unit 61 processes each of the two-dimensional images output from the imaging device 5 by a predetermined algorithm (hereinafter referred to as "defect detection algorithm") to calculate the respective two-dimensional images. The feature quantity of each pixel based on the luminance value. Further, the processed image generating unit 61 identifies the pixel having the feature amount equal to or greater than a predetermined threshold as a defective pixel, and generates a defective pixel corresponding to each two-dimensional image. The gradation value corresponding to the feature amount is a processing image for which a zero-order key value is given to a residual pixel other than the defective pixel (the pixel whose feature amount does not reach the threshold value), and each of the generated processed images is output.

The defect detection algorithm used by the processed image generating unit 61 will be described with reference to FIGS. 4A to 4C, FIGS. 5A to 5D, FIGS. 6A and 6B, and FIGS. 7A to 7C.

4A to 4C are diagrams for explaining an example of a defect detection algorithm, that is, an edge distribution method. Figure. 4A shows an example of a two-dimensional image A corresponding to the two-dimensional image data generated by the imaging device 5, the image side is on the downstream side in the transport direction Z, and the lower side of the image is on the upstream side in the transport direction Z. In the two-dimensional image A, the direction parallel to the width direction of the sheet-like molded body 2 is set to the X direction, and the direction parallel to the longitudinal direction of the sheet-shaped molded body 2 (the direction parallel to the conveyance direction Z) is Y. direction. In FIG. 4A, the band-shaped bright region in the center of the two-dimensional image A in the Y direction and extending in the X direction is the illumination image A1, and the dark region existing inside the illumination image A1 is the first defective pixel group A21. The bright region existing in the vicinity of the illumination image A1 is the second defective pixel group A22.

In the case of using the defect detection algorithm of the edge distribution method, the processed image generating portion 61 first divides the two-dimensional image A into data of progressive pixel rows in the Y direction. Next, the processed image generating unit 61 detects the edge of the data of each pixel row from one end in the Y direction (the upper end of the two-dimensional image A in FIG. 4A) to the other end (the lower end of the two-dimensional image A in FIG. 4A). Edge determination processing.

Specifically, the processed image generating unit 61 sets the second pixel from the one end side in the Y direction as the target pixel, and determines whether the luminance value of the focused pixel is adjacent to the one end side with respect to the pixel of interest. The luminance value of the adjacent pixel is greater than a certain threshold. When it is determined that the luminance value of the pixel of interest is larger than the threshold value of the adjacent pixel by a certain threshold or more, the processed image generation unit 61 determines that the adjacent pixel is the upper limit edge A3. In other cases, the processed image generating unit 61 repeats the edge determination process while shifting the pixel of interest to the other end in the Y direction by one pixel, until it is determined that the luminance value of the pixel of interest is larger than the luminance value of the adjacent pixel. Above the threshold.

After the upper limit edge A3 is detected, the processed image generating unit 61 determines whether or not the luminance value of the pixel of interest is smaller than the luminance value of the adjacent pixel by a specific threshold or more by shifting the pixel of interest to the other end in the Y direction by one pixel. When it is determined that the luminance value of the pixel of interest is smaller than the threshold value of the adjacent pixel by a specific threshold or more, the processed image generation unit 61 determines that the adjacent pixel is the lower limit edge A4. In the case other than this, the image generating portion 61 is processed. While shifting the pixel of interest to the other end in the Y direction by one pixel, the edge determination process is repeated until it is determined that the luminance value of the pixel of interest is smaller than the threshold value of the adjacent pixel by a specific threshold or more.

In FIG. 4A, an example in which the upper limit edge A3 detected by the edge determination processing of the image generating unit 61 is detected is indicated by "○", and a lower limit edge A4 is indicated by "●". As can be seen from FIG. 4A, in the first defective pixel group A21 and the second defective pixel group A22 in which the defect exists in the two-dimensional image A, the coordinate value of the upper limit edge A3 and the lower limit edge A4 in the Y direction (Y coordinate) The difference between the values is extremely small compared to the difference between the Y coordinate values of the residual pixels other than the defective pixel. Further, in the second defective pixel group A22 of the two-dimensional image A, the Y coordinate value of the upper limit edge A3 is significantly different from the Y coordinate value of the residual pixels other than the defective pixel.

With such a feature, the processed image generating unit 61 creates the edge distribution P1 shown in Fig. 4B. In the edge distribution P1 shown in FIG. 4B, corresponding to the second defective pixel group A22 of the two-dimensional image A, a peak P11 corresponding to the Y coordinate value of the upper limit edge A3 appears. Furthermore, the processed image generating unit 61 may be configured to create an edge distribution based on the difference between the Y coordinate values of the upper limit edge A3 and the lower limit edge A4. In this case, the edge distribution created by the processed image generating unit 61 corresponds to the first defective pixel group A21 and the second defective pixel group A22 of the two-dimensional image A, and the upper limit edge A3 and the lower limit edge appear. The difference between the Y coordinate values of A4 is small.

Further, the processed image generating unit 61 performs differential processing on the edge distribution P1 to create a differential distribution P2 shown in FIG. 4C. In the differential distribution P2 shown in FIG. 4C, it corresponds to the peak P11 of the edge distribution P1, that is, corresponds to the second defective pixel group A22 of the two-dimensional image A, and appears to have a predetermined threshold or more (large differential value) The peak value P21 of the feature amount P22.

The processed image generating unit 61 extracts, as a defective pixel, a pixel of the two-dimensional image A corresponding to the peak value P21 of the feature amount P22 having a predetermined threshold or more based on the differential distribution P2. In the example of the differential distribution P2 shown in FIG. 4C, the processed image generating unit 61 extracts the second defective pixel group A22 as a defective pixel.

5A to 5D are diagrams for explaining another example of the defect detection algorithm, that is, the peak method. 5A shows an example of a two-dimensional image B corresponding to the two-dimensional image data generated by the imaging device 5, the image side is on the downstream side in the transport direction Z, and the lower side of the image is on the upstream side in the transport direction Z. In the two-dimensional image B, the direction parallel to the width direction of the sheet-like molded body 2 is set to the X direction, and the direction parallel to the longitudinal direction of the sheet-shaped molded body 2 (the direction parallel to the conveyance direction Z) is set to Y direction. In FIG. 5A, the band-shaped bright region of the two-dimensional image B located at the center in the Y direction and extending in the X direction is the illumination image B1, and the dark region existing inside the illumination image B1 is the first defective pixel group B21. The bright region existing in the vicinity of the illumination image B1 is the second defective pixel group B22.

In the case of using the defect detection algorithm of the peak method, the processed image generating portion 61 first divides the two-dimensional image B into data of progressive pixel rows in the Y direction. Next, the processed image generating unit 61 successively draws the data of the luminance values of the position on the straight line L parallel to the Y direction of the two-dimensional image B as a point for the data of each pixel row, and creates a curve connecting the pixels. It is the luminance distribution P3 shown in Fig. 5B.

In the case where there is no defective pixel in the two-dimensional image B, the luminance distribution P3 shows the distribution of the single peak where the trough portion does not occur, but in the case where the defective pixel exists, as shown in FIG. 5B, the double of the trough portion P31 is displayed. The distribution of peaks.

Next, the processed image generating unit 61 fixes the luminance distribution P3 of each pixel row so that the moving time between adjacent data points is fixed irrespective of the distance between the data points, and assumes that one direction from the X direction of the luminance distribution P3 The particle that moves at the other end. Here, as shown in FIG. 5C, the above-mentioned particle point moves from the data point c to the data point b adjacent thereto, moves from the data point b to the data point a adjacent thereto, and is adjacent to the data point a from the data point a. The data point d moves. Further, the data point d is a data point corresponding to the pixel of interest.

The processed image generating unit 61 obtains a velocity vector and an acceleration vector of the mass points of the data points a, b, and c passing through the mass point immediately before the data point d. In other words, the processed image generating unit 61 is based on the coordinates of the two data points a and the data points b that pass the mass point immediately before the data point d. The moving time is obtained, and the velocity vector of the mass point from the data point b to the data point a is obtained. Further, the processed image generating unit 61 obtains the dot from the data point c to the data point b based on the coordinates of the two data points b and the data points c that pass the mass point before the data point a and the moving time. Speed vector. Further, the processed image generating unit 61 obtains the data point c from the velocity vector of the mass point from the data point b to the data point a and the velocity vector of the mass point from the data point c to the data point b. The acceleration vector of the particle at the interval of the data point a. Further, the processed image generating unit 61 predicts the coordinates of the data point d based on the velocity vector of the mass point from the data point b to the data point a and the acceleration vector of the mass point from the data point c to the data point a ( Forecast data point f).

The processed image generating unit 61 obtains the difference between the luminance value of the predicted data point f of the data point d predicted as described above and the actual (actually measured) luminance value of the data point d, and produces the luminance value difference shown in FIG. 5D. Distribution P4. The luminance value difference distribution P4 shown in FIG. 5D corresponds to the valley portion P31 of the luminance distribution P3 shown in FIG. 5B, that is, corresponds to the first defective pixel group B21 of the two-dimensional image B, and appears to have a predetermined The peak value P41 of the feature quantity P42 above the threshold (the difference in luminance value is large).

The processed image generating unit 61 extracts a pixel of the two-dimensional image B corresponding to the peak value P41 of the feature amount P42 having a predetermined threshold value or more as a defective pixel based on the luminance value difference distribution P4. In the example of the luminance value difference distribution P4 shown in FIG. 5D, the processed image generating unit 61 extracts the first defective pixel group B21 as a defective pixel.

6A and 6B are diagrams for explaining another example of the defect detection algorithm, that is, the smoothing method. 6A shows an example of a two-dimensional image C corresponding to the two-dimensional image data generated by the imaging device 5, the image side is on the downstream side in the transport direction Z, and the lower side of the image is on the upstream side in the transport direction Z. In the two-dimensional image C, the direction parallel to the width direction of the sheet-like molded body 2 is set to the X direction, and the direction parallel to the longitudinal direction of the sheet-shaped molded body 2 (the direction parallel to the conveyance direction Z) is set to Y direction. In FIG. 6A, the band-shaped bright region in which the two-dimensional image C is located in the center in the Y direction and extends in the X direction is the illumination image C1 and exists in the illumination image C1. The dark region in the interior is the first defective pixel group C21, and the bright region existing in the vicinity of the illumination image C1 is the second defective pixel group C22.

In the case of using the defect detection algorithm of the smoothing method, the processed image generating portion 61 first divides the two-dimensional image C into data of progressive pixel rows in the Y direction. Next, the processed image generating unit 61 creates a core C31 having a few pixels in the X direction and the Y direction (for example, 5 pixels in the X direction and 1 pixel in the Y direction).

Further, the processed image generating unit 61 sets the luminance value of the central pixel in the core C31 at the position on the straight line L parallel to the Y direction of the two-dimensional image C with respect to the data of each pixel row, and all of the core C31. The data of the difference between the average values of the luminance values of the pixels is continuously drawn as dots, and the curve connecting them is created as the smoothing distribution P5 shown in FIG. 6B. In the smoothing distribution P5 shown in FIG. 6B, corresponding to the first defective pixel group C21 of the two-dimensional image C, a peak P51 having a feature amount P52 (which is larger than the luminance value difference) having a predetermined threshold value or more appears. .

The processed image generating unit 61 extracts, as the defective pixel, a pixel of the two-dimensional image C corresponding to the peak value P51 of the feature amount P52 having a predetermined threshold value or more based on the smoothing distribution P5. In the example of the smoothing distribution P5 shown in FIG. 6B, the processed image generating unit 61 extracts the first defective pixel group C21 as a defective pixel.

7A to 7C are diagrams for explaining a second edge distribution method which is another example of the defect detection algorithm. FIG. 7A shows an example of a two-dimensional image D corresponding to the two-dimensional image data generated by the imaging device 5, the image side is on the downstream side in the transport direction Z, and the lower side of the image is on the upstream side in the transport direction Z. In the two-dimensional image D, the direction parallel to the width direction of the sheet-like molded body 2 is set to the X direction, and the direction parallel to the longitudinal direction of the sheet-shaped molded body 2 (the direction parallel to the conveyance direction Z) is set to Y direction. In FIG. 7A, the band-shaped bright region in which the two-dimensional image D is located at the center in the Y direction and extends in the X direction is the illumination image D1, and the dark region existing inside the illumination image D1 is the first defective pixel group D21. The bright region existing in the vicinity of the illumination image D1 is the second defective pixel group D22.

In the case of using the defect detection algorithm of the second edge distribution method, the processed image generating portion 61 first divides the two-dimensional image D into data of progressive pixel rows in the Y direction. Next, the processed image generating unit 61 detects the edge of the data of each pixel row from one end in the Y direction (the upper end of the two-dimensional image D in Fig. 7A) to the other end (the lower end of the two-dimensional image D in Fig. 7A). Edge determination processing.

Specifically, the processed image generating unit 61 sets the second pixel from the one end side in the Y direction as the target pixel, and determines whether the luminance value of the target pixel is adjacent to the one end side of the target pixel. The luminance value of the adjacent pixel is greater than a certain threshold. When it is determined that the luminance value of the pixel of interest is greater than or equal to the threshold value of the adjacent pixel, the processed image generation unit 61 determines that the adjacent pixel is the edge D3. In other cases, the processed image generating unit 61 repeats the edge determination process while shifting the pixel of interest to the other end in the Y direction by one pixel, until it is determined that the luminance value of the pixel of interest is larger than the luminance value of the adjacent pixel. Above the threshold.

In FIG. 7A, an example in which the edge D3 detected by the edge determination processing of the image generating unit 61 is detected is indicated by "○". As can be seen from FIG. 7A, in the second defective pixel group D22 in which the boundary portion between the bright region and the dark region of the two-dimensional image D is defective, the coordinate value (Y coordinate value) of the edge D3 in the Y direction is extremely changed. .

There are two methods for extracting defective pixels of the two-dimensional image D by such a feature. In the first method shown in FIG. 7B, the processed image generating unit 61 creates an edge distribution P6 corresponding to the edge D3 of the two-dimensional image D. In addition, in FIG. 7B, the edge distribution P6 corresponding to the edge D3 in the vicinity of the second defective pixel group D22 of the two-dimensional image D is enlarged and shown. In the edge distribution P6 shown in FIG. 7B, the Y coordinate value is extremely changed in correspondence with the second defective pixel group D22 of the two-dimensional image D.

The processed image generating unit 61 selects the point P61 and the point P62 which are arbitrary two points on the edge distribution P6 to be created, and calculates the area of the region P63 surrounded by the straight line connecting the point P61 and the point P62 and the curve of the edge distribution P6. Feature amount. The processed image generating section 61 is based on the edge distribution P6, and a pixel of the two-dimensional image D corresponding to the distribution portion having the feature amount (area of the region P63) having a predetermined threshold or more is extracted as the defective pixel.

In the second method shown in FIG. 7C, the processed image generating unit 61 creates an edge distribution P7 corresponding to the edge D3 of the two-dimensional image D. In addition, in FIG. 7C, the edge distribution P7 corresponding to the edge D3 in the vicinity of the second defective pixel group D22 of the two-dimensional image D is enlarged and shown. In the edge distribution P7 shown in FIG. 7C, the Y coordinate value of the two-dimensional image D corresponds to the second defective pixel group D22, and the Y coordinate value extremely changes.

The processed image generating unit 61 selects two points P71 and P72 which are arbitrary points on the created edge distribution P7, and creates a tangent P711 of the edge distribution P7 of the point P71 and a tangent P721 of the edge distribution P7 of the point P72. Next, the processed image generating unit 61 calculates an angle α1 between the virtual straight line P73 parallel to the X-axis and the tangent line P711, and an angle α2 between the virtual straight line P73 and the tangent line P721, and obtains the calculated angle α1 and angle α2. The difference is the angle α3. Then, the processed image generating unit 61 calculates the arc P74 between the point P71 and the point P72 in the edge distribution P7 using the length of the arc P74 between the point P71 and the point P72 of the edge distribution P7 and the angle α3. The radius of curvature R is taken as a feature quantity. The processed image generating unit 61 extracts, as the defective pixel, a pixel of the two-dimensional image D corresponding to the distributed portion having the feature amount (curvature radius R) within the predetermined threshold range based on the edge distribution P7.

As the defects generated in the sheet-like formed body 2, as described above, point defects such as bubbles, fish eyes, foreign matter, footprints, scratches, and scratches, and so-called cracks caused by crease marks and the like can be cited. A line defect such as a so-called original stripe which is produced by a difference in thickness.

The types of defects that can be extracted differ depending on the type of defect detection algorithm used in the processed image by the processed image generating unit 61. One example of the defect detection algorithm is the edge distribution method described above, which can extract a high degree of extraction capability for defects such as foreign matter or fetal marks and scars. The above peak method can extract a high degree of extraction capability for defects such as foreign matter, scratches, and scratches. The above smoothing method can extract a high extraction capacity for defects such as bubbles, fish eyes, and scratches. The above second edge distribution method can be used for defects such as strips or splits of the original sheet. Higher extraction capacity extraction.

The processed image generating unit 61 calculates the feature amount by using the processing of a plurality of defect detecting algorithms by the difference in the defect extracting ability caused by the type of the defect detecting algorithm. Further, by extracting defective pixels of the two-dimensional image using the calculated feature amount, it is possible to distinguish the defect type of the defective region of the two-dimensional image generated by the imaging device 5.

8A and 8B are views showing an example of processed images E1 to E6 generated by the image processing device 6. In the present embodiment, the processed image generating unit 61 of the image processing device 6 processes each of the two-dimensional images output from the imaging device 5 by the above-described defect detecting algorithm and extracts defective pixels, and then two-dimensional images. The images correspondingly produce processed images E1 to E6 as shown in FIGS. 8A and 8B. Further, in the processed images E1 to E6 shown in Figs. 8A and 8B, the black portion indicates a defective portion, that is, a residual pixel, and the white portion indicates a defective portion, that is, a defective pixel.

Further, in the processed images E1 to E6 shown in FIGS. 8A and 8B, the direction parallel to the width direction of the sheet-like molded body 2 is referred to as the X direction, and the longitudinal direction of the sheet-shaped molded body 2 (and the transport direction) The direction parallel to the Z direction is set to the Y direction. The processed images E1 to E6 shown in Figs. 8A and 8B are made from one end in the X direction (the left end of each processed image in Figs. 8A and 8B) to the other end (the right end of each processed image in Figs. 8A and 8B). 0, 1, 2, ..., m-2, m-1 are sequentially arranged in m pixels in the X direction, and one end in the Y direction (the upper end of each processed image in FIGS. 8A and 8B) to the other end (Fig. The lower end of each of the processed images of 8A and 8B is an image in which n pixels arranged in the Y direction are positioned in the order of 0, 1, 2, ..., n-2, and n-1.

In the example shown in FIGS. 8A and 8B, the processed image generating unit 61 corresponds to each two-dimensional image generated by the imaging device 5 at a predetermined time interval, and processes the image E1 in accordance with the imaging sequence. The processed image is sequentially generated in the order of the processed image E2, the processed image E3, the processed image E4, the processed image E5, and the processed image E6. The size and shape of the processed images E1 to E6 generated by the processed image generating unit 61 are the same as the size and shape of each of the two-dimensional images, and the processed image E1 constituting each of the processed images E1 to E6 is formed. ~E6 The processed image position coordinates at the position correspond to the coordinate values of the positions of the two-dimensional images of the respective pixels constituting the corresponding two-dimensional image. Further, the processed images E1 to E6 generated by the processed image generating unit 61 are generated between two processed images in which the order is continuous, specifically, between the processed image E1 and the processed image E2. Between the processed image E2 and the processed image E3, between the processed image E3 and the processed image E4, between the processed image E4 and the processed image E5, and between the processed image E5 and the processed image E6, An overlapping portion having at least a portion of the overlap.

The processed images E1 to E6 generated by the processed image generating unit 61 are input to the image analyzing device 7.

The image analysis device 7 included in the defect inspection device 100 of the present embodiment synthesizes a plurality of processed images E1 to E6 generated by the processed image generating unit 61, thereby generating a distribution indicating defects of the sheet-like formed body 2. The defect map image F shown in FIG. FIG. 9 is a view showing an example of the defect map image F generated by the image analysis device 7. Further, in the defect map image F shown in FIG. 9, the black portion indicates a defective portion, that is, a residual pixel, and the white portion indicates a defective portion, that is, a defective pixel.

Further, in the defect map image F shown in FIG. 9, the direction parallel to the width direction of the sheet-like molded body 2 is defined as the X direction, and the longitudinal direction of the sheet-like molded body 2 (the direction parallel to the transport direction Z) The parallel direction is set to the Y direction. The defect map image F shown in FIG. 9 is 0, 1, 2 from one end in the X direction (the left end of the defect map image F in FIG. 9) to the other end (the right end of the defect map image F in FIG. 9). , ..., t-2, t-1 are sequentially arranged in t pixels arranged in the X direction, and from one end in the Y direction (the upper end of the defect map image F in Fig. 9) to the other end (the defect map image of Fig. 9) The lower end of F is an image formed by u pixels arranged in the Y direction in the order of 0, 1, 2, ..., u-2, and u-1.

The image analysis device 7 includes a processed image input unit 71, a defect map image generation unit 72, and a control unit 73.

The processed image input unit 71 is input from the processed image generating unit 61 of the image processing device 6. Process the images E1~E6.

The defect map image generation unit 72 generates a portion of the defect map image F, and includes a coordinate value calculation unit 721, a total value calculation unit 721, an accumulation unit 722, and a luminance value setting unit 723.

The coordinate value calculation unit 721 calculates the coordinate map constituting the defect map based on the coordinate values of the pixels (hereinafter referred to as "process image position coordinates") of the respective processed images E1 to E6 sequentially generated by the processed image generating unit 61. The coordinate value of each pixel of the image F (hereinafter referred to as "defect mapping image position coordinate").

The processing image position coordinates of the pixels constituting the processed image sequentially generated in the above-described imaging sequence and generating the Nth processed image are set to (X _N , Y _N ), and the defect map is formed. When the position map of the defect map image of each pixel of F is (X _t , Y _u ), the coordinate value calculation unit 721 calculates and processes the image position coordinates (X _N , Y according to the following formula (3). The pixel corresponding to the pixel of _N ) maps the image position coordinates (X _t , Y _u ).

X _t =X _N Y _u =N×LS÷(FR×RS)+Y _N (3)

[In the formula, "N" indicates the order in which the processed image is generated, "LS" indicates the transport speed (mm/sec) of the sheet-like molded body 2 by the transport device 3, and "FR" indicates the frame of the photographing operation of the image pickup device 5. Rate (number of images per unit time = reciprocal of the imaging interval, unit: / second), and "RS" indicates the resolution (mm/pixel) of the imaging device 5. ]

The accumulating unit 722 performs either one of the following (1) or the following (2), or both of the following (1) and the following (2).

(1) For each pixel of the defect map image F described above, the number of defective pixels in the corresponding pixel in the processed image is counted.

(2) For each pixel of the defect map image F described above, the total of the tone values assigned to the corresponding pixels in the processed image is calculated.

As described above, the processed images E1 to E6 generated by processing the image generating portion 61 are Between the two processed images in sequential order, there is at least a portion of overlapping overlapping portions. Therefore, the pixels having the same defect map image position coordinates can be calculated from the plurality of processed images by the processing of the coordinate value calculation unit 721. In the present invention, it is preferable to calculate the same defect map image position coordinates from the two or more processed images for all the pixels of the defect map image F. In other words, one or two or more pixels corresponding to the pixels of the defect map image F are processed in the pixels of the image. In the processing of the above (1), the number of defective pixels in the pixel in which one or two or more processed images are present is counted. When a defective situation is captured in a two-dimensional image, as described above, the processed image has defective pixels and residual pixels. In the defective pixel, a tone value corresponding to the above feature amount is given, and a zeroth tone value is given to the residual pixel. In the processing of the above (2), the total of the gradation values assigned to each of the pixels having one or two or more processed images as described above is calculated.

Then, the luminance value setting unit 723 calculates the value calculated based on the total number of defective pixels obtained by the above (1) by the accumulating unit 722 and/or the gradation value obtained by the above (2), by using the coordinates The value calculation unit 721 calculates the luminance value of each pixel of the defect map image F indicated by the defect map image position coordinate. For example, the luminance value setting unit 723 multiplies the average value of the luminance values of the respective pixels of the processed images E1 to E6 corresponding to the respective pixels of the defect map image F by the number of defective pixels obtained by the above (1). The value is set to the brightness value. Further, the luminance value setting unit 723 can set the total of the gradation values obtained by the above (2) as the luminance values of the pixels of the defect map image F, and can also set the number of defective pixels obtained by the above (1). The luminance value of each pixel of the image F is mapped for the defect.

Since the luminance value setting unit 723 sets the luminance values of the pixels constituting the defect map image F as described above, the difference between the luminance values of the defective pixel and the residual pixel becomes large, and as a result, the defective pixel in the defect map image F is obtained. Become clearer. Further, in the defect map image F, defective pixels corresponding to the defect map image position coordinates which are larger than the total number of defective pixels obtained by the above (1) or the sum of the tone values obtained by the above (2) are used. The greater the brightness value, the better the degree of sharpness even between defective pixels.

The defect map image F generated by the defect map image generating unit 72 is input to the control unit 73. The control unit 73 outputs the input defect map image F to the display unit 21.

The display unit 21 is, for example, a liquid crystal display, an EL (Electroluminescence) display, a plasma display, or the like. The display unit 21 displays the defect map image F generated by the defect map image generating unit 72 on the display screen.

[Industrial availability]

In the defect inspection apparatus 100 of the present embodiment configured as described above, a defect for inspecting the sheet-like formed body 2 is generated based on the two-dimensional image of the sheet-like formed body 2 generated by the image pickup device 5. The image is the defect map image F, so that the defect detection capability can be maintained as compared with the case of generating an image for checking defects based on a plurality of one-dimensional images obtained by, for example, a line sensor. .

Further, in the defect inspection apparatus 100 of the present embodiment, the defect map image position coordinates indicating the position of the defect map image F of each pixel are based on the coordinate values of the respective pixels of the processed images E1 to E6. (3) calculating and setting a defect based on a plurality of pixels in the processed images E1 to E6 and calculating the total number of defective pixels in the pixel of the same defect map image position coordinate or the gradation value of the defective pixel Since the luminance value of each pixel of the image F is mapped, the defect of the sheet-like molded body 2 is inspected by using the defect map image F, and the position of the defect of the sheet-shaped molded body 2 can be accurately inspected with high detection capability.

Further, in the defect inspection apparatus 100 of the present embodiment, since the display unit 21 displays the defect map image F generated by the defect map image generation unit 72, the user observes the defect map displayed by the display unit 21. In the image F, the position of the defect of the sheet-like formed body 2 can be confirmed.

10A and 10B are diagrams showing another example of the processed image generated by the image processing device 6, that is, the processed image G1 to G13, and the defect map image generated by the image analyzing device 7, which is another example of the defect map image. The map of H. 11A and FIG. 11B illustrate that the processed images G1 to G13 including the one-dimensional image generated by the image processing apparatus 6 are sequentially spread to generate a defect map. A diagram of the operation of the image analysis device 7 in the case of the image J. Further, in the processed images G1 to G13 shown in FIGS. 10A and 11A, the defect map image H shown in FIG. 10B, and the defect map image J shown in FIG. 11B, the black portion indicates the defect-free portion. The residual pixel, the white portion indicates the defective portion, that is, the defective pixel.

In the above-described embodiment, the processed image generating unit 61 is configured to generate processed images E1 to E6 having the same size and shape as the two-dimensional image generated by the imaging device 5 in accordance with each of the two-dimensional images. However, it is not limited to this configuration. In other embodiments, the processed image generating unit 61 extracts a boundary region portion between the bright portion and the dark portion of the illumination image of the two-dimensional image generated by the imaging device 5, thereby generating a one-dimensional image as shown in FIG. 10A. The images G1 to G13 are processed. Further, the defective pixels may be extracted by the defect detection algorithm by the two-dimensional image generated by the imaging device 5, and the processed images G1 to G13 including the one-dimensional image may be generated.

The pixels constituting the processed images G1 to G13 generated by the processed image generating unit 61 are additionally stored with the processed image position coordinates by storing the bit values of the luminance value information storing the luminance value information indicating the luminance value. The coordinate information of the information is stored in the bit row obtained by the bit row. In the coordinate information storage bit row constituting each pixel of the processed image G1 to G13, information on a coordinate value corresponding to coordinates of each pixel constituting the two-dimensional image generated by the imaging device 5 is stored as a processing map. Information like location coordinates.

Here, when the defect map image generating unit 72 sequentially fills the plurality of processed images G1 to G13 generated by the processed image generating unit 61 in the order of generation to generate a defect map image, a defect map is generated. The defect map image J shown in FIG. 11B is such that, in one defect map image J, there are a plurality of defective pixels displaying the same defect. When the defect of the sheet-like formed body 2 is inspected using such a defect map image J, it is difficult to accurately grasp the position of the defect of the sheet-like formed body 2. Also, the same defect is repeatedly detected.

On the other hand, in the present embodiment, the defect map image generating unit 72 synthesizes a plurality of processed images G1 to G13 generated by the processed image generating unit 61, thereby generating the image. The defect map image H shown in 10B.

The coordinate value calculation unit 721 of the defect map image generation unit 72 calculates the information of the processed image position coordinates stored in the coordinate information storage bit line of each pixel of each of the processed images G1 to G13 based on the above equation (3). The defect map image position coordinates indicating the position of the defect map image H of each pixel constituting the defect map image H.

The accumulating unit 722 obtains the pixels of the plurality of processed images G1 to G13, and the coordinate value calculating unit 721 calculates the number of defective pixels in the pixels of the same defect map image position coordinate and/or the gradation value of the defective pixel. total. Then, the luminance value setting unit 723 calculates and sets a defect indicating the position map of the defect map image calculated by the coordinate value calculation unit 721 based on the total number of defective pixels and/or the tone value obtained by the accumulation unit 722. The luminance value of each pixel of the image H is mapped.

In the defect inspection apparatus 100 of the present embodiment, the defect map image position coordinates indicating the position of the defect map image H are processed based on the coordinates of each pixel of each of the processed images G1 to G13 stored in the coordinate information storage bit row. The information of the image position coordinates is calculated according to the above formula (3), and is based on the total number of the defective pixels or the gradation values in the pixels of the plurality of processed images G1 to G13 that calculate the position coordinates of the same defect map image. By setting the luminance value of each pixel of the defect map image H, the defect of the sheet-like formed body 2 is inspected by using the defect map image H, and the defect of the sheet-shaped formed body 2 can be accurately inspected with a high detection capability. position. In the defect mapping, since the same defect occurs in one portion, repeated detection of the same defect can be prevented.

1‧‧‧Image generating device

3‧‧‧Transporting device

5‧‧‧ camera

6‧‧‧Image processing device

7‧‧‧Image analysis device

21‧‧‧Display Department

61‧‧‧Processing Image Generation Department

71‧‧‧Processing image input section

72‧‧‧Defect mapping image generation unit

73‧‧‧Control Department

100‧‧‧ Defect inspection device

721‧‧‧ coordinate value calculation unit

722‧‧‧Accumulate

723‧‧‧Brightness value setting unit

Claims (4)

An image generating device that generates an image for inspecting a defect of a sheet-shaped molded body, and includes a conveying unit that conveys the sheet-shaped formed body in a longitudinal direction at a predetermined conveying speed; the light-irradiating portion The sheet-shaped molded body to be conveyed is irradiated with light, and the image pickup unit is disposed to face the surface of the sheet-like formed body to be conveyed, and the surface of the sheet-shaped formed body is imaged at predetermined time intervals. a plurality of two-dimensional images are generated in part, and the time interval is set such that one of the imaging regions captured by the two consecutive imaging operations partially overlaps; the feature amount calculation unit is determined by a predetermined algorithm The processing calculates the feature amount of each pixel constituting each of the two-dimensional images based on the luminance value of each pixel, and the processed image data generating unit divides each pixel constituting each of the two-dimensional images into the feature amount as a predetermined Defective pixels above the threshold value determined, and residual pixels having the feature amount not reaching the threshold value, and generating a processed image corresponding to each two-dimensional image, the processed image being a defective pixel is given a tone value corresponding to the feature amount, and a zero-order tone value is given to the residual pixel; and a defect map image generation unit that synthesizes a plurality of processes generated by the processed image data generation unit An image, whereby a defect map image indicating a distribution of defects of the sheet-shaped formed body is generated, and includes: a defect map image coordinate value calculation unit that is based on a coordinate value of each pixel constituting each processed image, The transfer speed and the time interval are used to calculate a coordinate value of each pixel constituting the defect map image, and an accumulation unit that performs one of the following (1) or (2) or the following ( 1) and both of the following (2): (1) counting, for each pixel of the defect mapping image, the number of defective pixels in the corresponding pixel in the processed image; (2) calculating, for each pixel of the defect mapping image, the assignment to the processed image a total of the gradation values of the corresponding pixels; and a luminance value setting unit that calculates the value based on the total number of defective pixels obtained by the above (1) and/or the total of the gradation values obtained by the above (2) The luminance map value of each pixel of the defect map image is set, thereby generating a defect map image. The image generating apparatus according to claim 1, wherein the time interval is such that a length of the longitudinal direction of the image capturing area partially overlapped is 1/2 times or more of a length of the two-dimensional image in the longitudinal direction. Set by mode. A defect inspection device comprising: the image generation device of claim 1 or 2; and a display portion that displays a defect map image generated by the defect map image generation portion of the image generation device. A defect inspection method for inspecting a defect of a sheet-shaped molded body, comprising: a conveying step of conveying a sheet-shaped formed body to a longitudinal direction thereof by a conveying speed at a predetermined conveying speed; and a light irradiation step The sheet-shaped molded body to be conveyed is irradiated with light; and in the image forming step, the surface of the sheet-shaped formed body is imaged at a predetermined time interval by an image forming unit disposed to face the surface of the sheet-like formed body to be conveyed. a plurality of two-dimensional images are generated in part, and the time interval is set such that one of the imaging regions captured by the two consecutive shooting operations partially overlaps; the feature amount calculating step is performed by a predetermined algorithm. Calculating a feature quantity of each pixel constituting each of the two-dimensional images based on a luminance value of each pixel; Processing the image data generating step of dividing each pixel constituting each of the two-dimensional images into a defective pixel having a feature amount equal to or greater than a predetermined threshold value, and a residual pixel having the feature amount not reaching the threshold value, and each two-dimensional The image correspondingly generates a processed image, the processed image is given a tone value corresponding to the feature quantity to the defective pixel, and a zero-order key value is added to the residual pixel; the defect mapping image generating step is synthesized by Processing the plurality of processed images generated by the image data generating step, thereby generating a defect map image indicating a distribution of defects of the sheet-shaped formed body, and comprising: a defect mapping image coordinate value calculating step, based on the respective processing Calculating a coordinate value of each pixel constituting the defect map image by a coordinate value of each pixel of the image, the transport speed, and the time interval; and performing the following steps (1) or (2) below Either or both of (1) and (2) below: (1) counting, for each pixel of the defect map image, a defective pixel in a corresponding pixel in the processed image (2) calculating, for each pixel of the defect mapping image, a total of the tone values assigned to the corresponding pixels in the processed image; and a brightness value setting step based on the defective pixel obtained by using the above (1) The number calculated and/or the value calculated by using the total of the gradation values obtained in the above (2) is set as the luminance value of each pixel of the defect map image, thereby generating a defect map image; and a display step. A defect map image generated by the above-described defect map image generating step is displayed.