KR20150044907A - Defect inspection apparatus, and defect inspection method - Google Patents

Abstract

In the defect inspection apparatus 1, the processed image generating section 61 processes the two-dimensional image data generated by the image pickup device 5 with a predetermined algorithm to obtain a feature quantity of each pixel constituting the two- . The processed image generating section 61 extracts, as two defective pixels, a pixel having a predetermined threshold value or more in the two-dimensional image data. Then, the processed image generating section 61 generates processed image data to which a tone value corresponding to the feature amount is assigned to the defective pixel and a zero tone value is assigned to the remaining pixels other than the defective pixel. The analysis image generation unit 62 generates analysis image data composed of one or a plurality of one-dimensional image data based on the processed image data.

Description

[0001] DEFECT INSPECTION APPARATUS AND DEFECT INSPECTION METHOD [0002]

The present invention relates to a defect inspection apparatus and a defect inspection method for inspecting defects in a sheet-like molded article such as a polarizing film or a retardation film.

Conventionally, a defect inspection apparatus uses a one-dimensional camera called a line sensor to inspect defects in a sheet-shaped formed article such as a polarizing film and a retardation film. The defect inspection apparatus is a system in which a sheet-shaped formed article is irradiated with a line sensor from one longitudinal end to the other end along the longitudinal direction of the sheet-shaped formed article while illuminating the formed article with a linear light source such as a fluorescent tube, Dimensional image data (still image data). Then, a plurality of one-dimensional image data are densely arranged in order of acquisition time to generate two-dimensional image data, and defects of the sheet-shaped formed body are inspected based on the two-dimensional image data.

The one-dimensional image data acquired by the line sensor typically includes a linear light source image. The linear light source image is an image of light emitted from the linear light source and regularly reflected by the sheet-shaped formed body to reach the line sensor when the linear light source and the line sensor are arranged on one side of the sheet-shaped formed body. The linear light source image is an image of light emitted from the linear light source and transmitted through the sheet-shaped molded body to reach the line sensor when the sheet-like molded body is disposed between the linear light source and the line sensor. In the defect inspection apparatus, when the width of the sheet-shaped formed body is wide, a plurality of line sensors are arranged in the width direction so as to be able to inspect the entire width direction of the sheet-shaped formed body.

The defect inspection apparatus of this embodiment checks the defects of the sheet-shaped formed body based on the two-dimensional image data representing the entire sheet-shaped formed body produced by closely arranging a plurality of one-dimensional image data, The positional relationship between the inspection subject pixel and the linear light source image in each one-dimensional image data becomes one predetermined positional relationship. The defect may appear on the one-dimensional image data only when the positional relationship between the pixel to be inspected (the target pixel) and the linear light source image is in a specific positional relationship. For example, bubbles, which are a kind of defects, often appear on one-dimensional image data only when they are located at the periphery or in the vicinity of the linear light source image. In this way, the defect may not be detected depending on its position. Therefore, the false defect inspection apparatus for inspecting the defects of the sheet-shaped formed body using the two-dimensional image data composed of the plurality of one-dimensional image data acquired by the line sensor has only a limited defect detection capability.

Patent Document 1 and Patent Document 2 disclose a defect inspecting apparatus for solving such a problem. In Patent Documents 1 and 2, a sheet-shaped formed article is illuminated with a linear light source such as a fluorescent tube, and while the sheet-shaped formed article is continuously conveyed in a predetermined conveying direction, Dimensional image data (moving image data) using a two-dimensional camera called a so-called two-dimensional camera, and inspects defects in the sheet-shaped formed body based on the two-dimensional image data.

According to the defect inspection apparatus disclosed in Patent Documents 1 and 2, it is possible to determine whether or not there is a defect based on a plurality of two-dimensional image data in which the positional relationship between the inspection subject pixel and the linear light source image is different. The defects can be reliably detected by the defective defect inspection apparatus. Therefore, the defect inspection apparatus using the area sensor disclosed in Patent Documents 1 and 2 has improved defect detection capability as compared with a defect inspection apparatus using a line sensor.

Japanese Patent Application Laid-Open No. 2007-218629 Japanese Laid-Open Patent Publication No. 2010-122192

A defect inspection apparatus using an area sensor disclosed in Patent Documents 1 and 2 analyzes defective positions and the like in an image analysis unit realized by a personal computer (PC) on two-dimensional image data output from an area sensor . At this time, since the two-dimensional image data has a large amount of information, the analysis processing time of the two-dimensional image data by the image analyzing section tends to be long.

As described above, when the analysis processing time by the image analysis section becomes longer, it is necessary to lower the conveying speed of the sheet-shaped formed article controlled according to the analysis processing time, and the inspection efficiency is lowered.

An object of the present invention is to provide a defect inspection apparatus and a defect inspection method capable of enhancing the inspection efficiency and speeding up image processing by the image analysis unit as a result of maintaining high defect detection capability.

According to the present invention, there is provided a sheet-

An irradiating unit for irradiating the sheet-shaped formed article to be conveyed with light,

An image pickup section for picking up the sheet-shaped formed article to be conveyed and generating two-dimensional image data based on light reflected or transmitted by the sheet-shaped formed article,

A feature amount calculating unit that calculates a feature amount based on a luminance value of each pixel constituting the two-dimensional image data by a predetermined algorithm process;

Wherein each pixel constituting the two-dimensional image data is distinguished by a defective pixel whose characteristic amount based on the luminance value is a predetermined threshold value or more and a remaining pixel whose characteristic amount based on the luminance value is less than the threshold value A processed image data generating unit for generating processed image data to which a tone value is assigned according to a feature amount based on the brightness value and a zero tone value is assigned to the remaining pixels,

An analysis image data generation unit that generates at least one analysis image data group consisting of one or a plurality of one-dimensional image data based on the processed image data;

And an image analysis unit for performing image analysis on the basis of the analysis image data group generated by the analysis image data generation unit to detect defects of the sheet-shaped formed body.

In the defect inspection apparatus of the present invention, it is preferable that the analysis image data group includes at least one of position information, luminance information, size information and type information of defects in the sheet-shaped formed article.

In the defect inspection apparatus of the present invention, the feature-quantity calculating section may calculate a feature quantity based on the luminance value by a plurality of algorithm processes,

Wherein the analysis image data generation section generates the analysis image data group in which a tone value corresponding to a predetermined type number for specifying the type of the algorithm process for calculating the feature amount is assigned as the tone value of the pixel, It is preferable to generate them as the analysis image data group.

The present invention also provides a method of manufacturing a sheet-

An irradiating step of irradiating the sheet-shaped formed article to be conveyed with light,

An image pickup step of picking up the sheet-shaped formed article to be conveyed by the image pickup section and generating two-dimensional image data based on reflected light or transmitted light of light irradiated to the sheet-

A feature amount calculating step of calculating a feature amount based on a luminance value of each pixel constituting the two-dimensional image data by a predetermined algorithm process;

Wherein each pixel constituting the two-dimensional image data is distinguished by a defective pixel whose characteristic amount based on the luminance value is a predetermined threshold value or more and a remaining pixel whose characteristic amount based on the luminance value is less than the threshold value A process image data generating step of generating process image data to which a tone value corresponding to a feature based on the brightness value is assigned to the defective pixel and a zero tone value is assigned to the remaining pixel;

An analysis image data generating step of generating at least one analysis image data group consisting of one or a plurality of one-dimensional image data based on the processed image data;

And an image analyzing step of performing image analysis based on the image data group for analysis generated in the image data generation step for analysis to detect defects in the sheet-shaped formed article.

According to the present invention, the defect inspection apparatus is provided with a carrying section, an irradiating section, an imaging section, a feature quantity calculating section, a processed image data generating section, an analysis image data generating section and an image analyzing section. In the defect inspection apparatus, the imaging section generates two-dimensional image data based on reflected light or transmitted light of light irradiated to the sheet-shaped formed body by the irradiation section. The feature-quantity calculating unit calculates the feature quantity based on the luminance value of each pixel constituting the two-dimensional image data by processing the two-dimensional image data with a predetermined algorithm. The processed image data generation unit may be configured to generate the processed image data by setting each pixel constituting the two-dimensional image data to a defective pixel whose characteristic amount based on the luminance value is a pixel whose threshold value is a predetermined value or more and a characteristic amount based on the luminance value, And distinguishes the remaining pixels as pixels. The processed image data generation unit generates the processed image data to which the tone value corresponding to the characteristic value based on the brightness value is assigned to the defective pixel and the tone value of zero is assigned to the remaining pixel. The analysis-purpose image data generation unit generates at least one group of analysis image data consisting of one or a plurality of one-dimensional image data based on the processed image data, and outputs the generated analysis-purpose image data group. The analysis image data group output from the analysis image data generation unit is input to the image analysis unit. The image analysis section performs image analysis based on the above-mentioned group of image data for analysis to detect defects in the sheet-shaped formed body.

In the defect inspection apparatus according to the present invention configured as described above, the defects of the sheet-shaped formed body are detected based on the two-dimensional image data of the sheet-shaped formed body picked up by the image pickup unit. It is possible to maintain a high defect detection capability as compared with the case where defect detection is performed based on the data.

Further, in the defect inspection apparatus of the present invention, the two-dimensional image data output from the image pickup section and having a large amount of information is converted into the processed image data by the processed image data generating section, and one or more Dimensional image data of one-dimensional image data. Since the image analysis section performs image analysis based on the image data group for analysis made up of one or a plurality of one-dimensional image data converted from the two-dimensional image data in this manner to detect defects in the sheet-shaped formed article, It is possible to increase the speed of the image processing by the image processing apparatus and improve the inspection efficiency.

According to the present invention, the analysis image data group generated by the analysis image data generation unit includes at least one of position information, luminance information, size information and type information of defects in the sheet-shaped formed article. Thereby, in the defect inspection apparatus, the image analysis section can detect defects in the sheet-shaped formed article based on information on defects such as position information, luminance information, size information, and type information.

According to the present invention, the feature-quantity calculating unit calculates a feature quantity by a plurality of algorithm processes. Then, the analysis-purpose image data generation unit generates an analysis-purpose image data group in which a tone value corresponding to a predetermined type number is specified as the tone value of the pixel for specifying the type of the algorithm process for calculating the feature amount. In this manner, the analysis image data group generated by the analysis image data generation unit becomes the analysis image data group including the type information on defects.

According to the present invention, the defect inspection method includes a transporting step, an irradiating step, an imaging step, a feature amount calculating step, a processed image data generating step, an analysis image data generating step and an image analyzing step. In the defect inspection method, in the imaging step, two-dimensional image data based on reflected light or transmitted light of light irradiated to the sheet-shaped formed body in the irradiation step is generated. In the feature quantity calculating step, the two-dimensional image data is processed by a predetermined algorithm to calculate a feature quantity based on the luminance value of each pixel constituting the two-dimensional image data. In the process image data generating step, a pixel having a feature value based on the luminance value is extracted as a defective pixel in the two-dimensional image data, the defective pixel having a feature value equal to or larger than a predetermined threshold value, And a processed image data to which a zero grayscale value is assigned to the remaining pixels other than the defective pixel is generated. In the analysis image data generation step, at least one analysis image data group composed of one or a plurality of one-dimensional image data is generated based on the processing image data. In the image analysis step, image analysis is performed based on the above-mentioned group of image data for analysis to detect defects in the sheet-shaped formed body.

In the defect inspection method of the present invention configured as described above, defect detection of the sheet-shaped formed article is performed based on the two-dimensional image data of the sheet-shaped formed article picked up in the image pickup step, It is possible to maintain a high defect detection capability as compared with the case where defect detection is performed based on image data.

Further, in the defect inspection method of the present invention, two-dimensional image data having a large amount of information generated in the imaging process is converted into processed image data in the process image data generating process, and one or more Dimensional image data of one-dimensional image data. In the image analysis step, image analysis is performed based on the image data group for analysis made up of one or a plurality of one-dimensional image data converted from two-dimensional image data to detect defects in the sheet-shaped formed body. The image processing speed of the image processing apparatus can be increased and the inspection efficiency can be improved.

The objects, features and advantages of the present invention will become more apparent from the following detailed description and the drawings.
1 is a schematic diagram showing a configuration of a defect inspection apparatus 1 according to an embodiment of the present invention.
2 is a block diagram showing a configuration of the defect inspection apparatus 1. As shown in FIG.
3A is a diagram for explaining an edge profile method, which is an example of a defect detection algorithm, and is a diagram showing an example of a two-dimensional image A corresponding to two-dimensional image data generated by the image pickup device 5. FIG.
Fig. 3B is a diagram showing an example of an edge profile P1 created by the processed image generating section 61. Fig.
FIG. 3C is a diagram showing an example of the differential profile P2 created by the processed image generating section 61. FIG.
4A is a diagram for explaining a peak method, which is another example of a defect detection algorithm, and is a diagram showing an example of a two-dimensional image B corresponding to two-dimensional image data generated by the image pickup apparatus 5. In Fig.
Fig. 4B is a diagram showing an example of the luminance profile P3 generated by the processed image generating section 61. Fig.
4C is a diagram for explaining an assumed order of a material point moving from the one end to the other end of the brightness profile P3, which is executed in the processed image generating unit 61. Fig.
FIG. 4D is a diagram showing an example of the luminance difference profile P4 generated by the processed image generating section 61. FIG.
5A is a diagram for explaining a smoothing method which is another example of a defect detection algorithm, and is a diagram showing an example of a two-dimensional image C corresponding to two-dimensional image data generated by the image pickup device 5. In Fig.
Fig. 5B is a diagram showing an example of the smoothing profile P5 generated by the processed image generating section 61. Fig.
6A is a diagram showing an example of image data generated by the image processing apparatus 6 and showing an example of a processed image D generated by the processed image generating unit 61. FIG.
6B is a diagram showing an example of the analysis image generated by the analysis image generation unit 62. Fig.
FIG. 7A is a diagram showing a change in the luminance value due to the difference in types of defects in a two-dimensional image picked up by the image pickup device 5. FIG.
Fig. 7B is a view showing a change in the luminance value due to the difference in types of defects in the two-dimensional image picked up by the image pickup device 5. Fig.
Fig. 7C is a diagram showing a change in the luminance value due to the difference in types of defects in the two-dimensional image picked up by the image pickup device 5. Fig.
Fig. 7D is a diagram showing a change in the luminance value due to the difference in types of defects in the two-dimensional image picked up by the image pickup device 5. Fig.
7E is a diagram showing a change in the luminance value due to the difference in types of defects in the two-dimensional image picked up by the image pickup device 5. Fig.
8 is a diagram for explaining an output method of a plurality of information amounts when a plurality of image pickup devices 5 are driven in parallel.
9 is a diagram showing an example of a defect map H displayed on the display section 74 of the image analyzing apparatus 7. As shown in Fig.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.

1 is a schematic diagram showing a configuration of a defect inspection apparatus 1 according to an embodiment of the present invention. 2 is a block diagram showing a configuration of the defect inspection apparatus 1. As shown in FIG. The defect inspection apparatus 1 of the present embodiment is an apparatus for detecting defects in a sheet-like formed body 2 such as a thermoplastic resin. The defect inspection method of the present invention is executed by the defect inspection apparatus (1).

The to-be-inspected chain sheet formed article 2 is subjected to a treatment such as passing the thermoplastic resin extruded from the extruder through a gap between the rolls to smooth the surface or giving a concavo-convex shape, and cooling the conveying roll by the take- So that it is molded. Examples of the thermoplastic resin applicable to the sheet-shaped formed body 2 of the present embodiment include a thermoplastic resin such as methacrylic resin, methyl methacrylate-styrene copolymer (MS resin), polyethylene (PE), polypropylene Polyolefin, polycarbonate (PC), polyvinyl chloride (PVC), polystyrene (PS), polyvinyl alcohol (PVA), and triacetyl cellulose resin (TAC). The sheet-form molded body 2 is formed into a single-layer sheet, a laminated sheet, or the like of these thermoplastic resins.

Examples of the defects that occur in the sheet-like formed body 2 include defects (point defects) such as bubbles, fish eyes, foreign matter, tire marks, scratches, scratches, (Line defects) such as so-called nicks and so-called fabric stripes caused by the difference in thickness.

The defect inspection apparatus 1 includes a transport apparatus 3, a lighting apparatus 4, an image pickup apparatus 5, an image processing apparatus 6, and an image analyzing apparatus 7. The defect inspecting apparatus 1 is a defect inspection apparatus which is constituted such that a sheet-like formed body 2 continuous in the longitudinal direction with a constant width is fixed in a predetermined direction (same as the longitudinal direction orthogonal to the width direction of the sheet- Dimensional image data is generated by capturing an image of the sheet surface illuminated by the illuminating device 4 by the image pickup device 5 in the course of the transfer and the image processing apparatus 6 reads the two- And the image analysis device 7 performs defect detection on the basis of the analysis image data output from the image processing device 6. [

The transport apparatus 3 has a function as a transport section and transports the sheet-like formed body 2 in a predetermined direction (transport direction Z). The conveying apparatus 3 has, for example, a feed roller and a take-out roller for conveying the sheet-like formed body 2 in the conveying direction Z, and measures the conveying distance by a rotary encoder or the like. In this embodiment, the conveying speed is set to about 2 to 30 m / min.

The illuminating device 4 has a function as an irradiating portion and illuminates the width direction of the sheet-like formed body 2 perpendicular to the carrying direction Z in a line. The illumination device 4 is arranged so that a line-shaped reflection image is included in the image picked up by the image pickup device 5. Specifically, the illuminating device 4 is configured to face the surface of the sheet-like formed body 2 at the upper side of the sheet-like formed body 2 and to face the illuminated area on the surface of the sheet-shaped formed body 2, For example, 200 mm to the imaging area where the device 5 picks up the image.

The light source of the illuminating device 4 is not particularly limited as long as it emits light which does not affect the composition and properties of the sheet-shaped formed article 2, such as an LED, a metal halide lamp, a halogen transmission light or a fluorescent lamp. The illumination device 4 may be disposed on the side opposite to the imaging device 5 with the sheet-like formed body 2 therebetween. In this case, the image captured by the imaging device 5 includes the transmitted image that transmits the sheet-shaped formed body 2.

The defect inspection apparatus 1 is provided with a plurality of image pickup devices 5 each having a function as an image pickup section and each of the image pickup apparatuses 5 is arranged in a direction orthogonal to the carrying direction Z Width direction). The imaging device 5 is arranged so that the direction from the imaging device 5 toward the center of the imaging region of the sheet-like formed body 2 and the carrying direction Z make an acute angle. The image pickup device 5 images a two-dimensional image including a reflected image or a transmitted image (hereinafter referred to as " illumination image ") of the sheet-shaped formed body 2 by the illumination device 4 a plurality of times, Thereby generating two-dimensional image data.

The image pickup device 5 is composed of an area sensor of a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor) for picking up a two-dimensional image. As shown in Fig. 1, the image pickup device 5 is arranged so as to pick up an entire area in the width direction orthogonal to the conveying direction Z of the sheet-like formed article 2. As described above, by capturing the entire area in the width direction of the sheet-like formed body 2 and conveying the sheet-like formed body 2 continuous in the carrying direction Z, the defect in the entire region of the sheet- Can be inspected.

The image capturing interval (frame rate) of the image capturing apparatus 5 may be fixed or may be changed by the user operating the image capturing apparatus 5 itself. The imaging interval of the imaging device 5 may be a fraction of a second, which is the time interval between successive imaging operations of a digital still camera. In order to improve the efficiency of the examination, a short time interval, for example, 1/30 second in rate, and the like.

The length of the two-dimensional image taken by the image pickup device 5 in the carrying direction Z is set to be shorter than the length of the sheet-shaped formed body 2 is at least twice the conveying distance at which the conveying member is conveyed. That is, it is preferable to image the same point of the sheet-like formed body 2 twice or more. As described above, the length of the two-dimensional image in the carrying direction Z is set so that the length of the sheet-shaped formed article 2 in the time from when the image pickup device 5 receives the two- It is possible to inspect the defect with high precision by increasing the number of times of image pickup of the same portion of the sheet-like formed body 2 and increasing the conveyance distance.

The image processing apparatus 6 includes a processed image generating section 61 having a function as a feature calculating section and a processed image data generating section and an analysis image generating section 62 having a function as an analysis image data generating section And is realized by an image processing board. The image processing apparatus 6 is formed corresponding to each of the plurality of image pickup apparatuses 5. [

The processed image generating section 61 processes the two-dimensional image data output from the image pickup device 5 with a predetermined algorithm (defect detection algorithm) to generate a processed image based on the luminance value of each pixel constituting the two- Is calculated. Further, the processed image generating unit 61 extracts, as the defective pixel, the pixel having the feature value equal to or larger than the predetermined threshold value in the two-dimensional image data. The processed image generating section 61 generates processed image data to which a tone value according to the feature amount is assigned to the defective pixel and a zero tone value is given to the remaining pixels other than the defective pixel, And outputs processed image data. The remaining pixels other than the defective pixels are pixels whose characteristic quantities are less than the threshold value.

The defect detection algorithm used in the processed image generating unit 61 will be described with reference to Figs. 3A to 3C, 4A to 4D, 5A and 5B.

3A to 3C are diagrams for explaining an edge profile method, which is an example of a defect detection algorithm. 3A shows an example of a two-dimensional image A corresponding to the two-dimensional image data generated by the image pickup device 5. The image has an image on the downstream side in the transport direction Z and an image on the lower side in the transport direction Z) upstream. In the two-dimensional image A, the direction parallel to the width direction of the sheet-like formed body 2 is the X direction, and parallel to the longitudinal direction of the sheet-like formed body 2 (direction parallel to the carrying direction Z) One direction is the Y direction. 3A, it is assumed that a bright region in a band positioned at the center with respect to the Y direction of the two-dimensional image A and extending in the X direction is the illumination image A1, and a dark region existing inside the illumination image A1 Is the first defective pixel group A21, and the bright region existing in the vicinity of the illumination image A1 is the second defective pixel group A22.

When the defect detection algorithm by the edge profile method is used, the processed image generation section 61 first divides the two-dimensional image A into data of the pixel column of one row along the Y direction. Next, the processed image generating section 61 generates the processed image data for the data of each pixel column from the other end (the two-dimensional image A in Fig. 3A) at one end in the Y direction (the upper end of the two- (I.e., the lower end of the line).

Specifically, the processed image generating section 61 sets the second pixel from the one end side in the Y direction to the target pixel with respect to the data of each pixel column, It is determined whether or not the luminance value of the target pixel is equal to or larger than a predetermined threshold value. When it is determined that the luminance value of the target pixel is larger than the luminance value of the adjacent pixel by a predetermined threshold or more, the processed image generating unit 61 determines that the adjacent pixel is the upper limit edge A3. In other cases, the processed image generating unit 61 moves the target pixel by one pixel toward the other end in the Y direction, and determines that the luminance value of the target pixel is larger than the luminance value of the adjacent pixel by a predetermined threshold value or more The edge determination process is repeated.

After detecting the upper limit edge A3, the processed image generating section 61 moves the target pixel by one pixel toward the other end in the Y direction, and detects the luminance value of the target pixel at a predetermined threshold value or more And judges whether it is small. If it is determined that the luminance value of the target pixel is smaller than the luminance value of the adjacent pixel by a predetermined threshold value or less, the processed image generating section 61 determines that the adjacent pixel is the lower limit edge A4. In other cases, the processed image generating unit 61 moves the target pixel by one pixel toward the other end in the Y direction, and determines that the luminance value of the target pixel is smaller than the luminance value of the adjacent pixel by a predetermined threshold value or smaller The edge determination process is repeated.

In Fig. 3A, an example of the upper limit edge A3 detected by the edge determination processing by the processed image generating unit 61 is indicated by " o ", and an example of the lower limit edge A4 is indicated by ". 3A, in the first defective pixel group A21 and the second defective pixel group A22 in which defects exist in the two-dimensional image A, the difference between the upper limit edge A3 and the lower limit edge A4 The difference in the coordinate value (Y coordinate value) in the Y direction is extremely smaller than the difference in the Y coordinate value in the remaining pixels other than the defective pixel.

Using this feature, the processed image generating unit 61 creates the edge profile P1 shown in Fig. 3B. In the edge profile P1 shown in Fig. 3B, the difference between the Y coordinate values of the upper limit edge A3 and the lower limit edge A4 in correspondence to the first defective pixel group A21 in the two-dimensional image A is A small peak P11 appears.

Further, the processed image generating section 61 performs the differential processing on the edge profile P1 to generate the differential profile P2 shown in Fig. 3C. In the differential profile P2 shown in Fig. 3C, the differential value P2 corresponding to the peak P11 in the edge profile P1, that is, the first defective pixel group A21 in the two-dimensional image A, A peak P21 having a characteristic amount P22 larger than a predetermined threshold value appears.

The processed image generating section 61 generates a processed image based on the differential profile P2 so that the pixel in the two-dimensional image A corresponding to the peak P21 having the feature quantity P22 of the predetermined threshold value or more Pixels. In the example of the differential profile P2 shown in Fig. 3C, the processed image generating unit 61 extracts the first defective pixel group A21 as defective pixels.

4A to 4D are diagrams for explaining the peak method, which is another example of the defect detection algorithm. 4A shows an example of a two-dimensional image B corresponding to the two-dimensional image data generated by the image pickup apparatus 5. The image has an image on the downstream side in the transport direction Z and an image on the lower side in the transport direction Z) upstream. In the two-dimensional image B, the direction parallel to the width direction of the sheet-like formed body 2 is the X direction, and parallel to the longitudinal direction of the sheet-like formed body 2 (direction parallel to the carrying direction Z) One direction is the Y direction. In Fig. 4A, a bright region in a band located in the center with respect to the Y direction of the two-dimensional image B and extending in the X direction is the illumination image B1, and a dark region existing inside the illumination image B1 Is the first defective pixel group B21 and 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 by the peak method, the processed image generating section 61 first divides the two-dimensional image B into data of the pixel columns of one row along the Y direction. Next, the processed image generating section 61 continuously plots the change of the luminance value at the position along the straight line L parallel to the Y direction of the two-dimensional image B with respect to the data of each pixel column And the curve connecting the continuous plots is created as the brightness profile P3 shown in Fig. 4B.

When there is no defective pixel in the two-dimensional image B, the brightness profile P3 indicates a single peak profile in which the valley portion does not appear, but when there is a defective pixel, As a result, the valley portion P31 shows a profile of a bimodal appearance.

Next, the processed image generating section 61 sets the other end in the X direction of the luminance profile P3 so that the moving time between plots adjacent in the X direction becomes constant with respect to the luminance profile P3 of each pixel string Assumes a moving particle point toward the target. Here, it is assumed that the material point moves from the plot c to the adjacent plot b, from the plot b to the adjacent plot a, from the plot a to the adjacent plot d as shown in Fig. 4C. It is also assumed that the plot d is a plot corresponding to the pixel of interest.

The processed image generating unit 61 obtains velocity vectors and acceleration vectors of the mass points in the plots a, b, and c passing through the material point immediately before the plot d. That is, the processed image generating section 61 generates the processed image 61 based on the coordinates of the two plot a and plot b passed through the material point immediately before the plot d and the coordinates of the material point in the section from the plot b to the plot a The velocity vector is obtained. The processed image generating section 61 generates the processed image 61 based on the coordinates of the two plot b and plot c passed by the material point immediately before the plot d and the coordinates of the material point in the section from the plot c to the plot b The velocity vector is obtained. The processed image generating section 61 generates the processed image on the basis of the velocity vector of the material point in the section from the plot b to the plot a and the velocity vector of the material point in the section from the plot c to the plot b, The acceleration vector of the material point in the section up to plot a is obtained. The processed image generating unit 61 calculates the coordinate of the plot d from the velocity vector of the material point in the interval from the plot b to the plot a and the acceleration vector of the material point in the interval from the plot c to the plot a (Predicted plot f).

The processed image generating section 61 obtains the difference between the luminance value of the predicted plot f of the plot d predicted as described above and the actual value (actual value) of the plot d and obtains the luminance value difference profile P4 shown in Fig. . In the brightness value difference profile P4 shown in Fig. 4D, the first defective pixel group B21 in the two-dimensional image B corresponds to the valley portion P31 in the brightness profile P3 shown in Fig. 4B, , A peak P41 having a characteristic value P42 of a predetermined threshold value or more with a large difference in luminance value appears.

The processed image generating unit 61 generates a processed image P41 based on the luminance value difference profile P4 by using the pixel in the two-dimensional image B corresponding to the peak P41 having the feature amount P42 of the predetermined threshold value or more And extracted as defective pixels. In the example of the brightness difference profile P4 shown in Fig. 4 (d), the processed image generation unit 61 extracts the first defective pixel group B21 as defective pixels.

5A and 5B are diagrams for explaining a smoothing method which is another example of the defect detection algorithm. 5A shows an example of a two-dimensional image C corresponding to the two-dimensional image data generated by the image pickup device 5. The image has an image on the downstream side in the transport direction Z and an image on the lower side in the transport direction Z) upstream. In the two-dimensional image C, the direction parallel to the width direction of the sheet-like formed body 2 is the X direction, and parallel to the longitudinal direction of the sheet-like formed body 2 (direction parallel to the carrying direction Z) One direction is the Y direction. In Fig. 5A, it is assumed that a bright region in a band positioned at the center with respect to the Y direction of the two-dimensional image C and extending in the X direction is the illumination image C1, and a dark region existing inside the illumination image C1 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 by the smoothing method, the processed image generating section 61 first divides the two-dimensional image C into data of a pixel column of one row along the Y direction. Next, the processed image generating section 61 creates a kernel C31 of several pixels (for example, five pixels in the X direction and one pixel in the Y direction) in the X direction and the Y direction.

The processed image generating unit 61 generates the processed image data for each pixel column based on the luminance of the central pixel in the kernel C31 at a position along the straight line L parallel to the Y direction of the two- Value and the average value of the luminance values of all the pixels in the kernel C31 are continuously plotted and the curve connecting the continuous plots is created as the smoothing profile P5 shown in Fig. 5B . In the smoothing profile P5 shown in FIG. 5B, a peak (P52) having a feature value P52 of a predetermined threshold value or more with a large difference in luminance value corresponding to the first defective pixel group C21 in the two- P51) is emerging.

The processed image generating unit 61 generates a processed image P51 based on the smoothing profile P5 by replacing the pixel in the two-dimensional image C, which corresponds to the peak P51 having the feature amount P52 of the predetermined threshold value or more, Pixels. In the example of the smoothing profile P5 shown in Fig. 5B, the processed image generating unit 61 extracts the first defective pixel group C21 as defective pixels.

Figs. 6A and 6B are diagrams showing examples of image data generated by the image processing apparatus 6. Fig. In the present embodiment, the processed image generating section 61 of the image processing apparatus 6 processes the two-dimensional image data output from the image capturing apparatus 5 with the above-described defect detection algorithm, and outputs a pixel having a predetermined threshold value or more After being extracted as defective pixels, a processed image D as shown in Fig. 6A is generated. The processed image D generated by the processed image generating section 61 is supplied with the gradation value according to the characteristic amount for the defective pixel groups D11 and D12 and for the residual pixel group D21 other than the defective pixel, Is given. The processed image generating unit 61 outputs processed image data corresponding to the generated processed image D. [

The processed image D shown in Fig. 6A is a process image D shown in Fig. 6A in which the direction from the one end in the X direction (the left end of the processed image D in Fig. 6A) to the other end (the right end in the processed image D in Fig. 2, … (The top of the processed image D in Fig. 6A) and the other end in the Y direction (the processed image in Fig. 6A D) in the direction of the arrow, , H-2, and H-1 arranged in the Y direction.

In Fig. 6A, the processed image D is a pixel in which the rank (X coordinate value) from one end in the X direction is " 8 ", and the pixel whose rank (Y coordinate value) And a first defective pixel group D11. In the processed image D, the pixel having the rank (X coordinate value) from the one end in the X direction is "W-5" and the rank (Y coordinate value) from the one end in the Y direction is "3" And a second defective pixel group D12.

The processed image data corresponding to the processed image (D) output from the processed image generating section (61) is input to the analysis image generating section (62). The analysis image generation unit 62 generates an analysis image, which is an image data group composed of one or a plurality of one-dimensional image data as shown in Fig. 6B, based on the process image data. The analysis image generation unit 62 outputs analysis image data corresponding to the generated analysis image. The analysis image data output from the analysis image generation unit 62 is input to the image analysis apparatus 7 described later.

In the present embodiment, the analysis image generation section 62 generates a one-dimensional image (image data) including at least one piece of information selected from the position information, the luminance information, the size information and the type information of the defect in the sheet- And generates an analysis image composed of data.

Specifically, the analysis image generation unit 62 generates an analysis image E1 composed of one-dimensional image data including defect position information as shown in FIG. 6B, and generates the analysis image E1, And outputs the image data for analysis corresponding to the image data. The analytical image E1 is divided into 0, 1, and 2 from the one end in the X direction (the left end of the analysis image E1 in Fig. 6B) to the other end (the right end of the analysis image E1 in Fig. , ... , W-pixels arranged in the order of W-2, W-1 arranged in the X-direction, and one pixel in the Y-direction.

This analytical image E1 corresponds to the first defective pixel group D11 in the processed image D and the rank (X coordinate value) from one end in the X direction is "6", "7", " 8 "," 9 ", and" 10 "have tone values of the Y coordinate value" 6 "which is a pixel indicating the maximum luminance value of the first defective pixel group D11. The analytical image E1 corresponds to the second defective pixel group D12 in the processed image D and the rank (X coordinate value) from one end in the X direction is "W-6", "W -5 " and " W-4 " have tone values of the Y coordinate value " 3 ", which is a pixel representing the maximum luminance value of the second defective pixel group D12. The image for analysis E1 is obtained for the pixels corresponding to the remaining pixel group D21 other than the first defective pixel group D11 and the second defective pixel group D12 in the processed image D Quot; 0 ".

In such an analysis image E1, the defect position information of the first defective pixel group D11 and the second defective pixel group D12 in the processed image D is given as the gradation value of the pixel, The defect position information of the defective pixel in the two-dimensional image generated by the imaging device 5 is given as the tone value of the pixel.

The analysis image generating section 62 generates an analysis image E2 composed of one-dimensional image data including defect brightness information as shown in Fig. 6B, and generates an analysis image E2 corresponding to the generated analysis image E2 And outputs one analysis-purpose image data. The analytical image E2 is divided into 0, 1, and 2 (from left end of the analysis image E2 in Fig. 6B) toward the other end (right end of the analysis image E2 in Fig. , ... , W-pixels arranged in the order of W-2, W-1 arranged in the X-direction, and one pixel in the Y-direction.

This analytical image E2 corresponds to the first defective pixel group D11 in the processed image D and the order (X coordinate value) from one end in the X direction is "6", "7", " 8 "," 9 ", and" 10 "have gradation values in the pixels of the same pixel train and the pixels showing the maximum luminance value of the first defective pixel group D11. In the example of Fig. 6B, the analytical image E2 has the tone value of the pixel whose X coordinate value is "6" is "80" and the tone value of the pixel whose X coordinate value is "7" The grayscale value of the pixel whose X coordinate value is "8" is "255" and the grayscale value of the pixel whose X coordinate value is "9" is "128" and the X coordinate value is "10" 80 ". The analytical image E2 corresponds to the second defective pixel group D12 in the processed image D and the rank (X coordinate value) from one end in the X direction is "W-6", "W -5 " and " W-4 " have gradation values in the pixels of the same pixel train and the pixels showing the maximum luminance value of the second defective pixel group D12. In the example of Fig. 6B, the analysis image E2 has the gradation value of the pixel whose X coordinate value is "W-6" is "80" and the gradation value of the pixel whose X coordinate value is "W-5" 128 ", and the grayscale value of the pixel whose X coordinate value is " W-4 " is " 80 ". It is to be noted that the analysis image E2 is the image of the pixel corresponding to the remaining pixel group D21 other than the first defective pixel group D11 and the second defective pixel group D12 in the processed image D Quot; 0 ".

In such an analysis image E2, the defect luminance information of the first defective pixel group D11 and the second defective pixel group D12 in the processed image D is given as the gradation value of the pixel, The defect luminance information of the defective pixel in the two-dimensional image generated by the image pickup device 5 is given as the tone value of the pixel.

The analysis image generation unit 62 generates an analysis image E3 composed of one-dimensional image data including defect size information as shown in Fig. 6B, and generates the analysis image E3 corresponding to the generated analysis image E3 And outputs one analysis-purpose image data. The analytical image E3 is divided into 0, 1, and 2 from the one end in the X direction (left end of the analysis image E3 in Fig. 6B) toward the other end (right end of the analysis image E3 in Fig. , ... , W-pixels arranged in the order of W-2, W-1 arranged in the X-direction, and one pixel in the Y-direction.

This analytical image E3 corresponds to the first defective pixel group D11 in the processed image D and the rank (X coordinate value) from one end in the X direction is "6", "7", " 8, " 9 ", and " 10 " have tone values corresponding to the number of pixels arranged in the Y direction with respect to the first defective pixel group D11 of the processed image D. 6B, in the analysis image E3, the tone value of the pixel whose X coordinate value is "6" is "1", the tone value of the pixel whose X coordinate value is "7" is "2" When the tone value of the pixel whose X coordinate value is "8" is "3" and the tone value of the pixel whose X coordinate value is "9" is "2" and the X coordinate value is "10" 1 ". In addition, the analysis image E3 corresponds to the second defective pixel group D12 in the processed image D and the rank (X coordinate value) from one end in the X direction is "W-6", "W -5 " and " W-4 " have tone values corresponding to the number of pixels arranged in the Y direction with respect to the second defective pixel group D12 of the processed image D. In the example of Fig. 6B, the analytical image E3 has the gradation value of the pixel whose X coordinate value is "W-6" is "1" and the gradation value of the pixel whose X coordinate value is "W-5" 3 ", and the grayscale value of the pixel whose X coordinate value is " W-4 " is " 1 ". And the analysis image E3 is obtained for the pixels corresponding to the remaining pixel group D21 other than the first defective pixel group D11 and the second defective pixel group D12 in the processed image D Quot; 0 ".

In such an analysis image E3, the defect size information of the first defective pixel group D11 and the second defective pixel group D12 in the processed image D is given as the gradation value of the pixel, The defect size information of the defective pixel in the two-dimensional image generated by the image pickup device 5 is given as the tone value of the pixel.

The analysis image generating unit 62 generates an analysis image E4 composed of one-dimensional image data including defect type information as shown in Fig. 6B, and corresponds to the generated analysis image E4 And outputs one analysis-purpose image data. The analysis image E4 is divided into 0, 1, and 2 from the one end in the X direction (the left end of the analysis image E4 in Fig. 6B) to the other end (the right end of the analysis image E4 in Fig. , ... , W-pixels arranged in the order of W-2, W-1 arranged in the X-direction, and one pixel in the Y-direction.

This analytical image E4 corresponds to the first defective pixel group D11 in the processed image D and the rank (X coordinate value) from one end in the X direction is "6", "7", " 8 "," 9 ", and" 10 "are assigned to the type number of the defect detection algorithm for which the first defective pixel group D11 could be extracted at the time of generating the processed image D by the processed image generation unit 61 As shown in FIG. The type number of the defect detection algorithm is a predetermined number for specifying the type of the defect detection algorithm, which is given for convenience in each defect detection algorithm. In the example of Fig. 6B, the analysis image E4 has the gradation value of the pixel whose X coordinate values are "6", "7", "8", "9" Quot; 1 ", which indicates the type number of one defect detection algorithm for which extraction of D11 has been possible. The analytical image E4 corresponds to the second defective pixel group D12 in the processed image D and the rank (X coordinate value) from one end in the X direction is "W-6", "W -5 " and " W-4 " are added to the type number of the defect detection algorithm in which the second defect pixel group D12 can be extracted at the time of generation of the processed image D by the processed image generating unit 61 And has a corresponding tone value. In the example of Fig. 6B, the analysis image E4 has the gradation value of the pixels whose X coordinate values are "W-6", "W-5" and "W- Quot; 2 " indicating the type number of another defect detection algorithm that has been able to extract. It is to be noted that the analysis image E4 is the image of the pixel corresponding to the remaining pixel group D21 other than the first defective pixel group D11 and the second defective pixel group D12 in the processed image D Quot; 0 ".

In such an analysis image E4, the defect type information of the first defective pixel group D11 and the second defective pixel group D12 in the processed image D is given as the gradation value of the pixel, The defect type information of the defective pixel in the two-dimensional image generated by the imaging device 5 is given as the tone value of the pixel.

As described above, defects that occur in the sheet-like formed body 2 are caused by differences in the thickness of the so-called cracks, which are caused by point defects such as bubbles, fish eyes, foreign substances, tire marks, scratches, scratches, Called line defect such as so-called fabric stripe which occurs.

The kinds of defects that can be extracted differ depending on the type of defect detection algorithm used at the time of generation of the processed image D by the processed image generating section 61. [ The edge profile method which is an example of the defect detection algorithm can extract defects such as foreign matter, tire marks, scratches and the like with high extractability. The peak method can extract the defects such as foreign matter, scratches, and scratches with high extractability. The smoothing method can extract defects such as bubbles, fish eyes, and scratches with high extractability. By constructing the analysis image E4 as the one-dimensional image data including the pixels having the gradation value indicating the type number of the defect detection algorithm, by using the difference in defect extraction ability by the kind of the defect detection algorithm, It becomes possible to distinguish defective types of defective areas in the two-dimensional image generated by the imaging device 5. [

In the above example, the one-dimensional image data including the pixels having the gradation value indicating the type number of the defect detection algorithm is used to generate the analysis image E4 including the defect type information. However, It is not.

7A to 7E are diagrams showing a change in the luminance value in accordance with the difference in types of defects in the two-dimensional image picked up by the image pickup device 5. FIG. Figs. 7A to 7E show a two-dimensional image F when the image-forming device 2 picks up the sheet-like formed body 2 conveyed by the conveying device 3, and Figs. 7A, 7B, 7c, 7d, and 7e.

For example, the spot defect F21 can be detected based on the reversal of light and darkness observed when passing through the illumination image F1. On the other hand, the foreign matter defect F22 is always detected as the dark region. Using this phenomenon, the analysis image generation section 62 generates a process image generation section (image processing section) 62 for a plurality of two-dimensional images F picked up by the image pickup apparatus 5 using one kind of defect detection algorithm 61). ≪ / RTI > Then, the analysis image generation section 62 generates a defect image in which all the defective pixels having the same coordinate value (X coordinate value) in the X direction in each processed image are extracted as defective pixels, And defect pixels in which the dark region is inverted are extracted, thereby generating an analysis image E4 including the defect type information.

8 is a diagram for explaining an output method of a plurality of information amounts when a plurality of image pickup devices 5 are driven in parallel. In the defect inspection apparatus 1, when the plurality of image pickup devices 5 are driven in parallel, the image pickup device 5 is arranged such that the field of view of the adjacent image pickup devices 5 slightly overlaps each other. In such a case, each of the analysis images (G1, G2, G3) generated by the analysis image generation unit 62 corresponding to each two-dimensional image picked up by each image pickup apparatus 5 is used for defect detection G23 and G33 which are not used for defect detection are formed in correspondence with the overlapping portions of the visual field of the image pickup device 5. The center regions G12, Other information on the defect (the defect position information, the defect luminance information, the defect size information, and the defect (s) described above are assigned to each pixel of the end regions G13, G23, and G33 in the analytical images G1, G2, and G3), it is possible to give information on many defects without increasing the number of pixels of the analysis images G1, G2, and G3.

2, the image analyzing apparatus 7 provided in the defect inspecting apparatus 1 of the present embodiment is an image analyzing apparatus for analyzing image data outputted from the analyzing image generating unit 62 of the image processing apparatus 6 The image analysis is carried out on the basis of the detected defects of the sheet-like formed body 2. The image analyzing apparatus 7 includes an analyzing image input unit 71, an image analyzing unit 72, a control unit 73, and a display unit 74. The analysis image input unit 71 inputs the analysis image data output from the analysis image generation unit 62 of the image processing apparatus 6. [

The image analysis unit 72 detects a defect based on the analysis image data input from the analysis image input unit 71 and detects the defect position information, the defect luminance information, the defect size information Defect type information, and the like, generates defect information indicating information on the defect, and outputs the defect information to the control section 73. [ When the image data for analysis made up of the one-dimensional image data including the defect position information is outputted from the image-for-analysis generating unit 62, the image analyzing unit 72 sets the coordinates of the defective pixel in the image for analysis to Shaped molded body 2 to generate defect information indicating the position of the defect in the sheet-shaped formed body 2, and outputs the generated defect information to the control unit 73. [

When the analysis image data composed of the one-dimensional image data including the defect luminance information is output from the analysis image generation unit 62, the image analysis unit 72 calculates the brightness of the defect in the analysis image The distribution is converted into the luminance distribution of defects on the sheet-like formed body 2 to generate defect information indicating the luminance distribution of the defects in the sheet-like formed body 2, and the generated defect information is outputted to the control section 73 do.

When the image data for analysis made up of the one-dimensional image data including the defect size information is output from the image-for-analysis generating unit 62, the image analyzing unit 72 calculates the size of the defect size The distribution is converted into a distribution of defect sizes on the sheet-like formed body 2 to generate defect information indicating the distribution of the defect sizes in the sheet-like formed body 2, and the generated defect information is outputted to the control section 73 do.

When the image data for analysis made up of the one-dimensional image data including the defect type information is outputted from the image-for-analysis generating unit 62, the image analyzing unit 72 performs the image- The distribution of defects is converted into a distribution of defects for each type on the sheet-like formed body 2 to generate defect information indicating the distribution of defects for each type in the sheet-like formed body 2, And outputs it to the control unit 73. [

Also, the image analyzing unit 72 is configured to analyze the image data for analysis, which is composed of a plurality of one-dimensional image data, each of which includes the information selected from the defect position information, the defect luminance information, the defect size information, When outputted from the generation section 62, each piece of information in the analysis image is converted into corresponding information on the sheet-shaped formed body 2 to generate defect information in the sheet-shaped formed body 2 , And outputs the generated defect information to the control unit 73. [

Based on the defect information output from the image analysis unit 72, the control unit 73 generates a defect map indicating defect information in the sheet-shaped formed body 2, and generates a defect map for the analysis image input unit 71, And controls the image analyzing unit 72 and the display unit 74 in a comprehensive manner.

The control unit 73 outputs the analysis image data composed of the one-dimensional image data including the defect position information from the analysis image generation unit 62, and in the sheet-like formed body 2 based on the analysis image data When the defect information indicating the position of the defect in the sheet-shaped formed article 2 is outputted from the image analysis section 72, a defect map indicating the defect position of the sheet-

The control section 73 outputs the analysis image data composed of the one-dimensional image data including the defect luminance information from the analysis image generation section 62 and outputs the sheet-shaped formed article 2 ), The defect map indicating the distribution of the defect brightness of the sheet-shaped formed body 2 is created.

The control unit 73 outputs the analysis image data composed of the one-dimensional image data including the defect size information from the analysis image generation unit 62, , The defect map indicating the distribution of the defect sizes of the sheet-shaped formed body 2 is created.

The control section 73 outputs the analysis image data composed of the one-dimensional image data including the defect type information from the analysis image generation section 62 and outputs the sheet-shaped formed article 2 ), Defect maps indicating the distribution of defects for each type of sheet-like formed body 2 are created when the defect information indicating the distribution of defects for each of the types of sheet-shaped formed bodies 2 is output from the image analysis unit 72. [

Furthermore, the control unit 73 may also be configured to determine whether or not the analysis-use image data including the plurality of one-dimensional image data, each of which includes the defect position information, the defect luminance information, the defect size information, When the plurality of pieces of defect information in the sheet-like formed body 2 are outputted from the image analysis section 72 based on the analysis image data, Thereby generating a defect map in which a plurality of pieces of defect information are respectively shown.

The defect map created by the control unit 73 is displayed on the display unit 74 in this way. 9 is a diagram showing an example of a defect map H displayed on the display section 74 of the image analyzing apparatus 7. As shown in Fig.

In the example shown in Fig. 9, the analysis image generating unit 62 generates the one-dimensional image data including the defect position information and the one-dimensional image data including the defect luminance information, .

Here, the analysis image constituted by the one-dimensional image data including the defect position information constituting the analysis image data is the analysis image (E1) shown in Fig. 6B, and the one-dimensional image data including the defect brightness information The analysis image is the analysis image E2 shown in Fig. 6B.

When the analysis image generating unit 62 outputs the one-dimensional image data including the defect position information and the one-dimensional image data including the defect luminance information, which is composed of two one-dimensional image data , The image analyzing unit 72 converts the coordinates of the defect position in the one-dimensional image data including the defect position information into the position on the sheet-shaped formed body 2. The image analyzing unit 72 also converts the luminance distribution of the defects in the one-dimensional image data including the defect luminance information into the luminance distribution of the defects on the sheet-shaped formed body 2, And outputs the generated defect information to the control unit 73. The control unit 73 determines whether or not the defect information indicates the defect position and the luminance value.

The control unit 73 determines whether or not the distribution of the defects H1 shown in Fig. 9 is equal to or larger than the distribution of the defects H1 shown in Fig. 9 based on the defect information indicating the defect position and the luminance value in the sheet- And generates the generated defect map H, and displays the generated defect map H on the display unit 74. By viewing the defect map H displayed on the display unit 74 in this way, the user operating the defect inspection apparatus 1 can check the occurrence status of defects in the sheet-like formed body 2. [

In the defect inspection apparatus 1 of the present embodiment configured as described above, the defect detection of the sheet-like formed body 2 is performed based on the two-dimensional image data of the sheet-shaped formed body 2 picked up by the image pickup apparatus 5 It is possible to maintain a high defect detection capability as compared with, for example, a case where defect detection is performed based on one-dimensional image data by a line sensor.

Further, in the defect inspection apparatus 1 of the present embodiment, the two-dimensional image data output from the image pickup device 5 and having a large amount of information is converted into processed image data by the processed image generating section 61, Is converted into an image data group for analysis made up of one or a plurality of one-dimensional image data by the image generation unit (62). The image analysis device 7 performs image analysis on the basis of the image data group for analysis made up of one or a plurality of one-dimensional image data converted from the two-dimensional image data in this manner, It is possible to increase the speed of image processing by the image analyzing apparatus 7 and improve the inspection efficiency.

The present invention can be embodied in various other forms without departing from the spirit or essential characteristics thereof. Therefore, the above-described embodiments are merely illustrative in all respects, and the scope of the present invention is not limited to the description in the specification. In addition, all modifications and variations falling within the scope of the claims are within the scope of the present invention.

1: defect inspection device
2: sheet-shaped formed article
3:
4: Lighting device
5:
6: Image processing device
7: Image analyzer
61: Processed image generation unit
62: an image for analysis
71: an image input unit for analysis
72: image analysis section
73:
74:

Claims (4)

A conveying section for conveying the sheet-shaped formed article,
An irradiating unit for irradiating the sheet-shaped formed article to be conveyed with light,
An image pickup section for picking up the sheet-shaped formed article to be conveyed and generating two-dimensional image data based on light reflected or transmitted by the sheet-shaped formed article,
A feature amount calculating unit that calculates a feature amount based on a luminance value of each pixel constituting the two-dimensional image data by a predetermined algorithm process;
Wherein each pixel constituting the two-dimensional image data is distinguished by a defective pixel whose characteristic amount based on the luminance value is a predetermined threshold value or more and a remaining pixel whose characteristic amount based on the luminance value is less than the threshold value A processed image data generating unit for generating processed image data to which a tone value is assigned according to a feature amount based on the brightness value and a zero tone value is assigned to the remaining pixels,
An analysis image data generation unit that generates at least one analysis image data group consisting of one or a plurality of one-dimensional image data based on the processed image data;
And an image analysis unit for performing image analysis based on the image data group for analysis generated by the image data generation unit for analysis to detect defects in the sheet-shaped formed body. The method according to claim 1,
Wherein the analysis image data group includes at least one of position information, brightness information, size information, and type information of defects in the sheet-shaped formed article. 3. The method of claim 2,
Wherein the feature quantity calculating section calculates a feature quantity based on the luminance value by a plurality of algorithm processes,
Wherein the analysis image data generation section generates the analysis image data group in which a tone value corresponding to a predetermined type number for specifying the type of the algorithm process for calculating the feature amount is assigned as the tone value of the pixel, As the image data group for analysis. A conveying step of conveying the sheet-
An irradiating step of irradiating the sheet-shaped formed article to be conveyed with light,
An image pickup step of picking up the sheet-shaped formed article to be conveyed by the image pickup section and generating two-dimensional image data based on reflected light or transmitted light of light irradiated to the sheet-
A feature amount calculating step of calculating a feature amount based on a luminance value of each pixel constituting the two-dimensional image data by a predetermined algorithm process;
Wherein each pixel constituting the two-dimensional image data is distinguished by a defective pixel whose characteristic amount based on the luminance value is a predetermined threshold value or more and a remaining pixel whose characteristic amount based on the luminance value is less than the threshold value A process image data generating step of generating process image data to which a tone value corresponding to a feature based on the brightness value is assigned to the defective pixel and a zero tone value is assigned to the remaining pixel;
An analysis image data generating step of generating at least one analysis image data group consisting of one or a plurality of one-dimensional image data based on the processed image data;
And an image analysis step of performing image analysis based on the image data group for analysis generated in the image data generation step for analysis to detect a defect in the sheet-shaped formed article.

Images