JP7017207B2 - Image inspection device and its image inspection method - Google Patents

Description

An embodiment of the present invention relates to an image inspection device to be inspected and an image inspection method thereof.

Conventionally, in the inspection of the quality of printed characters, for example, a reference image including a standard character which is a non-defective product is used as a judgment standard, and whether or not the printed character to be inspected that is read matches the standard character is compared. The quality of the printed characters is judged. Characters, symbols, and patterns printed on the work or the label attached to the work are optically read by, for example, an image pickup unit such as a line sensor, and are generated as image data (video signal) of a still image by photoelectric conversion. ..

Since the line sensor has a configuration in which a plurality of imagers are arranged in a row, the line sensor itself or the work is moved to take an image by scanning. For example, when the work is a cylindrical resin tube, in order to read the characters printed on or affixed to the side surface of the resin tube, the resin tube is rotated and read. At this time, if there is an eccentricity of the rotation axis in the resin tube or a deviation in the sticking direction, the read image may be tilted in the image data and the position may be displaced with respect to the reference character. ..

Japanese Patent No. 3725207

When determining the inclination or the like generated in the read inspection image data by comparison with the reference, it is necessary to correct the misalignment. For example, in Patent Document 1, the read image data (pixel group) is divided into a certain number of line block images, and position shift correction is performed in block units. In order to perform position correction, a plurality of feature points must be included in each line block image, and it is difficult to set the image separation depending on the image to be inspected.

There is also misalignment correction using a strip-shaped line block image separated at equal intervals in the horizontal direction of the image, but the longer the length of the strip-shaped line block image, the larger the misalignment correction amount on the end side. The amount of arithmetic processing increases, and high performance is desired to realize high-speed processing time. Further, in the band-shaped line block image, for example, when the image is taken by the line sensor, the inspection image read from the label having the bending in the middle may cause a vertical positional shift in the middle of the character string. It is not possible to correct a partial misalignment such that a part of the character string described in the column is misaligned vertically near the center of one strip-shaped line block image.

Therefore, the present invention provides an image inspection device that corrects the positional deviation of the inspection target by combining the block images that include the inspection target and are vertically and horizontally divided so that the alignment points for the positional deviation correction satisfy the set number. It is an object of the present invention to provide the image inspection method.

The image inspection apparatus according to the present invention gives coordinate information to a reference image including an inspection target, and vertically and horizontally divides the alignment point detection unit that detects the alignment point from the reference image and the inspection image including the inspection target. In the block image, the density of the pixels at the alignment point is compared with the density of the pixels in the vicinity of the coordinates corresponding to the alignment point in the block image, and the displacement amount due to the difference is calculated. The amount calculation unit and the pixel from which the misalignment amount can be calculated are defined as the points at which the misalignment amount can be calculated, and when the points at which the misalignment amount can be calculated are less than the set number in one block image, the above-mentioned The inspection image has a block joining portion that repeats coupling with adjacent block images until the set number is exceeded, and a point where the misalignment amount exceeding the set number can be calculated with the inspection target of the reference image as a reference position. A correction amount detecting unit for obtaining an alignment correction amount for correcting the misalignment of the inspection target is provided, and a block image of the inspection image corrected by the alignment correction amount is compared with the reference image. , Judge the quality of the inspection image.

According to the present invention, an image inspection apparatus and an image inspection apparatus that perform alignment correction of an inspection target by combining them so that the alignment points for positioning deviation correction satisfy a set number in a block image that includes an inspection target and is vertically and horizontally divided. , The image detection method can be provided.

FIG. 1 is a diagram conceptually showing a configuration example of an image inspection device according to an embodiment. FIG. 2 is a diagram for explaining block image correction. FIG. 3 is a diagram for explaining an image combination in which an alignment point is included in a block image. FIG. 4 is a flowchart for explaining image position deviation correction by the image inspection device of the embodiment. FIG. 5 is a diagram for explaining an image inspection using a block image for a color image.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
The image inspection apparatus according to the present embodiment is a block image in which a reference image including a reference character and a reference pattern to be inspected is vertically and horizontally divided, and a block in which an imaged inspection image including the same inspection target is vertically and horizontally divided in the same division as the reference image. Divide into images.

The image inspection device includes a block image correction unit. The block image correction unit is used for each block image with respect to the alignment point (POS point), which is a feature point set in advance on the coordinates provided in the reference image, and the vicinity of the region corresponding to the POS point on the inspection image. , So-called template matching is performed to calculate the amount of misalignment in each of the X and Y directions of the coordinates. In the following description, the alignment point for which the amount of misalignment is calculated is referred to as a POM point. When the number of POM points in one block image does not reach the preset number, the images are combined with the adjacent block images until the set number is exceeded. For block images with more than a predetermined number of POM points, including combined block images, the amount of misalignment is added up and divided by the number of POM points to obtain the average value, and the sign is inverted to correct the alignment. The amount. The quality / defect of the inspection image is determined by comparing the image block of the comparison image composed of the inspection image corrected by the alignment correction amount with the block image of the reference image.

[First Embodiment]
FIG. 1 is a diagram conceptually showing a configuration example of an image inspection device according to the first embodiment.
The image inspection device 100 includes an image pickup unit 1, an image processing unit 2, a control unit 3, a display unit 4, an input unit 5, and a storage unit 6.
In the present embodiment, the image pickup unit 1 optically reads the printed characters, symbols, and patterns, and generates image data (digital signal) of a still image by photoelectric conversion.

The image pickup unit 1 captures a still image in frame units with a CCD image sensor or a so-called digital camera using a CMOS image sensor, or captures images using a line sensor in which the image pickup elements are arranged in a line. In this embodiment, the image pickup unit 1 using the line sensor is used. The line sensor moves (including parallel movement and rotational movement) the line sensor itself or an object to be inspected and scans to capture characters, symbols, and patterns. In particular, the image pickup unit 1 using a line sensor is suitable for printing on a curved surface or reading characters on a label attached to the curved surface.

The display unit 4 uses, for example, a liquid crystal display monitor. The display unit 4 displays various information such as an operation screen, an inspection status, and a determination result according to the control of the control unit 3. The input unit 5 uses, for example, various switches, a keyboard, a mouse, and other input devices in combination. Further, as the input unit 5, a touch panel may be provided on the screen of the display unit 4 and used.
The storage unit 6 stores programs and application software for operating the control unit 3. Further, the coordinate information of the alignment point, which is a feature point described later, and the alignment correction amount of the block image are also stored.

The image processing unit 2 performs CDS (correlation double sampling) processing, AGC (gain control) processing, and the like on the image data (reference image REM, inspection image DI) output from the image pickup unit 1. At this time, the density (brightness) of each pixel is quantified into a lightness value (gray scale) of 256 gradations by quantization. This brightness value is a pixel value. The image processing unit 2 outputs the image data of the reference image to the alignment point detection unit 16 and the storage unit 6, and outputs the image data of the inspection image to the block division unit 11. The image processing unit 2 may be integrally configured with the control unit 3.

The control unit 3 includes a block division unit 11, a block image correction unit 12, a comparison image generation unit 13, a comparison unit 14, a determination unit 15, and an alignment point detection unit 16. The control unit 3 can also be configured as a general-purpose personal computer by using a dedicated program or application software.

The block division unit 11 gives coordinate information (XY coordinates) to the image data (1 frame) of the reference image and the inspection image output from the image processing unit 2, and provides the reference image 31 (as shown in FIG. 2). REM), the frame of the inspection image 32 (DI) is divided vertically and horizontally to generate a plurality of block images.

It is assumed that the position and size of the block image on the frame are defined by the coordinate information, and the coordinate information is also given to the inspection target in the block image. In the following description, each of the vertically and horizontally divided partial images may be referred to as a block image, or may also be referred to as a sub-line block image because the line block divided into strips is vertically divided. The block division unit 11 gives the same coordinate information to the reference image and the inspection image, and then performs vertical and horizontal division in the same division to generate a block image. In this division, it is assumed that the same inspection target is included in the image in the reference image and the inspection image. In FIG. 2, the frame portion 41 is the inspection target.

The block image correction unit 12 sets the alignment point (POS point), which is a feature point set in advance on the coordinates provided in the reference image, and the POS point on the inspection image for each block image with respect to the inspection image. By performing so-called template matching on the vicinity of the corresponding region, the amount of positional deviation is calculated in each of the X direction and the Y direction of the coordinates. If the number of points (POM points) for which this misalignment can be calculated is less than the predetermined number, the POM points of the combined block images are combined with the adjacent block images. Then, it continues to be combined with the adjacent block image until the total value of the POM points exceeds the set number. For block images (non-combined) with more than the set number of POM points even if they are not combined, the amount of misalignment of the POM points in the block is added up for each X and Y coordinates, and the average value is divided by the number of POM points. By reversing the obtained code, the alignment correction amount in each of the X direction and the Y direction of the block image is obtained. Further, in the combined block image, the alignment correction amount is calculated in the same manner as described above by using the POM points included in all the combined blocks.

The alignment point detection unit 16 sets coordinates (coordinate information) on the reference image. Next, in order to perform alignment, the alignment point (POS point) formed by the extremely small pixel group shown in FIG. 3 is detected from the reference image. The alignment points used for image comparison are the same as the feature points, and may be known such as characteristic patterns including characters and ruled lines, edges thereof, or those having different brightness from the surroundings. The alignment point detection unit 16 creates map data by associating the alignment point (POS point) with the position information (coordinate information) of each block image of the reference image, and stores it in the storage unit 6.

The block image correction unit 12 includes a position shift amount calculation unit 21, a block coupling unit 22, and a correction amount calculation unit 23.
The misalignment amount calculation unit 21 calculates the misalignment amount around the POS point by template matching. As the calculation method, the density of the pixel at the POS point of the reference image is compared with the density of the pixel in the vicinity of the coordinates corresponding to the POS point in the inspection image. This comparison, that is, the total value of the absolute values of the differences in density for each pixel is calculated. Based on the magnitude of the total value, the amount of misalignment at the POS point and the pixel (point) in the vicinity of the coordinates corresponding to the POS point in the inspection image is calculated.

The points where the amount of misalignment can be calculated are recorded as POM points (points where the amount of misalignment can be calculated) in the block image. If there is a significant misalignment in the images, or if the symbol that should have existed at the POS point position is missing, the difference between the compared images is large and the total value of the differences is not sufficiently small. It shall not be accepted as a POM point.

The block connecting unit 22 integrates the number of POM points in one block image of the inspection image based on the calculation result of the misalignment amount calculation unit 21. Further, it is determined whether or not there are four or more POM points in one block image of the inspection image, and the images are combined with the adjacent block images until the total of the POM points becomes the set four or more.
For each block image cut out by division, four or more POM points are not always calculated. Therefore, if the block image has less than 4 POM points, it is combined with the adjacent block image until the total number of POM points is 4 or more. In this embodiment, four POM points are set as an example, but the number is not limited to four, depending on the shape, image quality, resolution, and the like of the inspection target in the inspection image. The number is set as appropriate.

This will be described with reference to FIG. Here, a block image having four settings is taken as an example. In the block image SB1, four block images P1, P2, P3, and P4 are connected in series. In this example, the block images P1, P2, and P4 both have one POM point that can be used for alignment. Further, the block image P3 has four POM points that can be used for alignment. Therefore, the block images P1, P2, and P4 have insufficient numbers of POM points in order to perform alignment correction.

First, as shown in the block image SB2, the block image P1 and the block image P2 are combined to form a block image P12. This block image P12 has two POM points, but it is still insufficient for the set number. On the other hand, the block image P3 and the block image P4 are combined to form the block image P34. There are five POM points in the block image P34, and four or more conditions are satisfied.

However, since the block image P12 still has insufficient POM points for the set number, it is combined with the adjacent block image P34 to form the block image P as shown in the block image SB3. In this block image P, there are seven POM points, and four or more conditions are satisfied.

Further, in the combination of adjacent block images, the priority and the combination order may be set. For example, as the first engagement order, one set is combined and sequentially combined from any end of the arrangement of the block images, for example, from the block image at the right end toward the left side. As the second combination order, when the block images are adjacent to each other on both sides, the block images having more POM points are preferentially combined. As the third joining order, the block images having the most (or few) POM points are sequentially joined so as to spread on both sides from the starting point.

The correction amount calculation unit 23 uses the position shift amount information of the POM points in the uncombined or combined block image in which the POM points of the inspection image satisfy the condition of four or more, and is the inspection target of the reference image. The correction amount in the X direction and the Y direction for approaching the position of the same specific part of the inspection target of the inspection image to the position of the specific part of the inspection image is calculated. The correction amount is calculated by adding up the amount of misalignment of the POM points in the block for each of the X and Y coordinates, dividing by the number of POM points to obtain the average value, and multiplying the value by -1.

As a specific example, the frame portion 41 of the inspection target existing in the block image 42a of the reference image 31 (REM) shown in FIG. 2 is set as the reference position. The alignment correction amount for the position of the frame portion 41 of the block image 43a of the inspection image 32 (DI) to approach the position of the frame portion 41 of the reference image 31 is calculated.

As shown in FIG. 2, the comparative image generation unit 13 corrects each block image 43a to 43n of the inspection image 32 using the alignment correction amount (movement in the X and Y directions), and performs correction (movement in the X and Y directions) to the reference image. The inspection target of the comparative image 33 is formed so as to be close to the inspection target of. That is, the comparison image 33 in which the block image of the inspection image 32 is position-corrected in the XY direction is generated. Specifically, the block image 44a of the comparison image 33 is an image obtained by correcting the block image 43a of the inspection image 32 (DI) by the alignment correction amount.

The comparison unit 14 compares the inspection target whose position in each block image 44a to 44n of the comparison image 33 whose inspection image 32 has been corrected is corrected with the inspection target of the reference image 31 on a pixel-by-pixel basis. The determination unit 15 takes the difference between the brightness values of the pixels of the reference image and the pixels of the comparison image in the comparison result of the reference image and the comparison image, and determines the pixels that deviate from the preset threshold range as defective pixels. When the number of defective pixels exceeds a preset number, a defect determination is performed on the inspection image. The determination result is displayed on the display unit or output to other devices.

Further, the comparative image generation unit 13 uses FIG. 2 as an example of the frame portion 41 in the block image of the reference image 31 with respect to the partial frame of the frame portion 41 having the inclination in each block image of the inspection image 32. A rotation correction unit that rotates the coordinates and applies rotation correction may be provided so as to match the direction of the partial frame.

The image inspection by the image inspection apparatus 100 of this embodiment will be described with reference to the flowchart shown in FIG.
First, image data (reference image REM) including characters, symbols, and patterns to be inspected for non-defective products captured by the image pickup unit 1 according to the instruction of the control unit 3 is input to the image processing unit 2 (step S1). ).

Next, the reference image REM detects the alignment point (POS point) consisting of the feature points having the positioning information in the alignment point detection unit 16 (step S2). Further, the control unit 3 creates position information (coordinate information) of the POS point as map data with respect to the reference image, and stores the position information (coordinate information) of the POS point in the storage unit 6 together with the reference image REM (step S3).

Next, the imaging unit 1 captures characters, symbols, and patterns to be inspected to generate an inspection image (step S4). The captured inspection image is subjected to the above-mentioned image processing by the image processing unit 2, and the inspection image DI including the image data in which the gradation and the like are quantified is output to the block division unit 11. The block division unit 11 divides the inspection image DI into a block image having a preset division size (for example, 16 pixels × 128 pixels) (step S5). At this time, the coordinate information of XY is given to the inspection image DI. The division size of the block image is an arbitrary size and is appropriately set depending on the inspection target.

Next, the misalignment amount calculation unit 21 detects the misalignment amount of the divided block image as described above (step S6). Next, the block connecting unit 22 calculates the number of POM points for which the amount of misalignment can be calculated, and determines whether or not the calculated number of POM points is equal to or greater than the set number (step S7). If the detected POM points do not reach the set number (NO), the adjacent block images are combined so that four or more POM points are included in the block image (step S8). Further, the correction amount calculation unit 23 calculates the alignment correction amount of each block image from the position deviation amount of the POM point (step S9).

Next, each block image of the inspection image (DIB) is corrected using the alignment correction amount to form a comparative image 33 that is close to the block image of the reference image (step S10).
Next, the comparison image 33 and the reference image 31 (REMA) based on the block image are compared (step S11). In this comparison, each pixel of the inspection image is compared with the threshold data, the pixel deviating from the preset threshold range is determined as a defective pixel, and the result is displayed on the display unit or output to another device (step S12). .. Next, it is determined whether or not the quality determination of all the inspection images has been completed (step S13). If the quality determination of all the images is not completed (NO), the process returns to step S4, the next inspection image is imaged, and the inspection is continued. When the quality determination of all the images is completed (YES), the image inspection is terminated.

As described above, in the image inspection device of the present embodiment, the same inspection image in the captured inspection image is tilted and misaligned with respect to the inspection target such as characters and patterns included in the reference image. In this case, since the inspection image is divided into blocks, the correction amount for alignment can be calculated in units of the block images. It is possible to realize highly accurate position correction as opposed to the conventional line block image correction.

If the number of alignment points in one block image is less than the set number, the block images are combined until the set number is reached, and the alignment correction amount for correcting the misalignment is calculated. It is possible to prevent the block from being corrected to a misplaced position or not being corrected at all.

Further, in the conventional correction of the line block image, when the inspection target of the captured inspection image has an inclination with respect to the inspection target of the reference image, the inclination is adjusted even if there is no pixel defect such as missing characters. Was determined to be defective, but since the alignment is performed to eliminate the positional deviation in block image units, unnecessary defect determination can be reduced.

[Modified example of the first embodiment]
Next, the image inspection apparatus of the modification of the first embodiment will be described.
In the first embodiment described above, the position of the inspection target of the inspection image is corrected and the comparison is performed with respect to the inspection target of the reference image. In this modification, the position of the inspection target of the reference image is corrected and the comparison is performed with respect to the position of the inspection target of the inspection image. That is, the sign is not inverted in the calculation for obtaining the correction amount, and is used as the correction amount of the reference image for the inspection image. The image inspection device of this modification is the same as the device configuration of the first embodiment described above, and the calculation of the correction amount in the correction amount calculation unit is different.

In this modification, the alignment point is detected from the reference image including the inspection target. At this time, the coordinates are set in the reference image. The reference image is divided into block images by vertical and horizontal division. For each block image, the X direction and Y of the coordinates with respect to the alignment point (POS point), which is a feature point set in advance on the coordinates of the reference image, and the vicinity of the area corresponding to the POS point on the inspection image. Calculate the amount of misalignment for each direction.

The alignment point at which these misalignments can be calculated is defined as the POM point. When the number of POM points in one block image does not reach the preset number, the images are combined with the adjacent block images until the set number is exceeded. For block images with more than a predetermined number of POM points, including combined block images, the amount of misalignment is added up and divided by the number of POM points to obtain the average value, which is used as the alignment correction amount. The quality / defect of the inspection image may be determined by comparing the image block of the comparison image composed of the reference image corrected by the alignment correction amount with the block image of the inspection image.
Also in this modification, the same effect as that in the first embodiment described above can be obtained.

[Second Embodiment]
A second embodiment will be described with reference to FIG.
The image inspection apparatus of the present embodiment inspects the images in the three R, G, and B block images 201, 202, and 203 of one color block image. For R, G, and B images, block division, detection of alignment points (POS points), calculation of misalignment amount, combination of adjacent block images, and misalignment are corrected as in the first embodiment. The amount of alignment correction for this is calculated. In the present embodiment, since the image for the monochromatic image in the first embodiment described above is simply changed to the color image, the R, G, and B block images include one overlapping inspection target. include. Therefore, in the R, G, and B block images of one color block image, the same part of the same inspection target is included in the same position (coordinate position).

In the present embodiment, the R, G, and B images of the reference image and the inspection image are each divided into block images of the same size (for example, 16 pixels × 128 pixels). After that, the POS points of the R block image, the G block image, and the B block image of the reference image are detected respectively.
The number of POM points in one color block image is the sum of the POM points in the R, G, and B block images on the same coordinates. When the number of POM points in one color block image is four or more, the alignment correction amount is obtained by the same calculation method as in the first embodiment.

Further, as in the first embodiment described above, if the total POM points of the R, G, and B block images in one color block image are less than four even if the total POM points are added up, the total number of POM points is less than four. By combining with a color block image adjacent to the color block image, it is possible to form a comparison image with respect to the POM point without any positional deviation for each color.

The present invention is not limited to the above-described embodiment and the above-mentioned modification, and can be variously modified without departing from the gist thereof. In addition, each embodiment and modification may be carried out in combination as appropriate, in which case the combined effect can be obtained.

1 ... Imaging unit, 2 ... Image processing unit, 3 ... Control unit, 4 ... Display unit, 5 ... Input unit, 6 ... Storage unit, 11 ... Block division unit, 12 ... Block image correction unit, 13 ... Comparative image generation unit , 14 ... Comparison unit, 15 ... Judgment unit, 16 ... Alignment point detection unit, 21 ... Position deviation amount calculation unit, 22 ... Block coupling unit, 23 ... Correction amount calculation unit, 31 ... Reference image, 32 ... Inspection image, 33 ... Comparative image, 41 ... Frame portion, 42a to 42n, 43a to 43n, 44a to 44n ... Block image.

Claims (7)

An alignment point detection unit that gives coordinate information to the reference image including the inspection target and detects the alignment point from the reference image,
In the block image obtained by vertically and horizontally dividing the inspection image including the inspection target, the density of the pixels at the alignment point is compared with the density of the pixels in the vicinity of the coordinates corresponding to the alignment point in the block image. The misalignment amount calculation unit that calculates the misalignment amount due to the difference,
Pixels that can calculate the amount of misalignment are defined as points where the amount of misalignment can be calculated, and if the number of points for which the amount of misalignment can be calculated is less than the set number in one block image, until the number exceeds the set number. , A block joining part that repeats joining with adjacent block images,
Correction amount detection for obtaining an alignment correction amount for correcting the position deviation of the inspection target of the inspection image having a point where the position deviation amount exceeding the set number can be calculated with the inspection target of the reference image as the reference position. Department and
An image inspection device for determining whether the inspection image is good or bad by comparing the block image of the inspection image corrected by the alignment correction amount with the reference image. An alignment point detection unit that gives coordinate information to the reference image including the inspection target and detects the alignment point from the reference image,
A block division unit that divides the inspection image including the inspection target into block images by vertical and horizontal division, and
The density of the pixels at the alignment point in the block image is compared with the density of the pixels in the vicinity of the coordinates corresponding to the alignment point in the block image, and the misalignment amount due to the difference is calculated. Quantitative unit and
The pixel from which the misalignment amount can be calculated is defined as the point at which the misalignment amount can be calculated, and if the point at which the misalignment amount can be calculated is less than the set number, the block image and the adjacent block image are displayed until the set number is exceeded. The block connection part that repeats the connection and
A position for correcting the positional deviation of the inspection target included in the block image of the inspection image having a point where the position deviation amount exceeding the set number can be calculated with the inspection target included in the reference image as the reference position. A correction amount detection unit that obtains the combined correction amount, and
A comparative image forming unit that forms a comparative image in which the block image of the inspection image is corrected by the alignment correction amount by the correction amount detection unit.
A comparison unit that compares the inspection target included in the comparison image with the inspection target included in the reference image and calculates a comparison result based on the difference in pixel values.
When the number of pixels whose difference in pixel values in the comparison result by the comparison unit deviates from a predetermined threshold value exceeds an arbitrary set number, a determination unit that determines a defect in the inspection image and a determination unit.
An image inspection device equipped with. The correction amount detection unit uses the point that the position deviation amount exceeding the set number can be calculated to correct the position deviation of the reference image in the block image of the inspection image with respect to the inspection target. The image inspection apparatus according to claim 1, wherein the image inspection apparatus is calculated and the average alignment correction amount is calculated by dividing the alignment correction amount by the total number of points for which the misalignment amount can be calculated. When the block images are adjacent to each other on both sides, the block coupling portion is preferentially coupled to the block image having the most points from which the displacement amount can be calculated, or the reference. The image inspection apparatus according to claim 1, wherein the block images are sequentially combined from the image and the block image at the end of the inspection image, or the block images are combined in any combination order. An alignment point detection unit that gives coordinate information to the reference image including the inspection target and detects the alignment point from the reference image,
The density of the pixels at the alignment point in the block image obtained by vertically and horizontally dividing the reference image is compared with the density of the pixels in the vicinity of the coordinates corresponding to the alignment point in the inspection image including the inspection target, and the difference is obtained. The misalignment amount calculation unit that calculates the misalignment amount due to
Pixels that can calculate the amount of misalignment are defined as points where the amount of misalignment can be calculated, and if the number of points for which the amount of misalignment can be calculated is less than the set number in one block image, until the number exceeds the set number. , A block joining part that repeats joining with adjacent block images,
Correction amount detection for obtaining an alignment correction amount for correcting the position deviation of the inspection target of the reference image having a point where the position deviation amount exceeding the set number can be calculated with the inspection target of the inspection image as a reference position. Department and
An image inspection device for determining the quality of an inspection image by comparing the block image of the reference image corrected by the alignment correction amount with the inspection image. An image inspection method that is processed by software set in the computer .
A step of giving coordinate information to a reference image including an inspection target captured by the computer and detecting an alignment point from the reference image,
A step of dividing an inspection image including the inspection target into block images by vertical and horizontal division , associating the alignment points with the coordinate information of each block image, and storing them in a storage unit.
The density of the pixel at the alignment point is compared with the density of the pixel near the coordinates corresponding to the alignment point in the block image read from the storage unit , and the positional deviation due to the difference in the comparison is compared. The process of extracting the pixels whose amount can be calculated as the points where the amount of misalignment can be calculated, and
If the number of points for which the amount of misalignment detected in the inspection image can be calculated is less than the set number in one block image, the step of repeating the combination with the adjacent block images until the set number is exceeded. ,
With the inspection target of the reference image as the reference position, the alignment correction amount for correcting the positional deviation of the inspection target for each block image of the inspection image having a point where the displacement amount exceeding the set number can be calculated. The required process and
An image inspection method including a step of comparing a block image of the inspection image corrected by the alignment correction amount with the reference image to determine whether the inspection image is good or bad. An image inspection method that is processed by software set in the computer .
A step of giving coordinate information to a reference image including an inspection target captured by the computer and detecting an alignment point from the reference image,
A process of dividing the reference image into block images by vertical and horizontal division, associating the alignment points with the coordinate information of each block image, and storing the image in a storage unit.
The density of the pixel at the alignment point in the block image read from the storage unit is compared with the density of the pixel near the coordinates corresponding to the alignment point in the inspection image including the inspection target. Then, the process of extracting the pixels that can calculate the amount of misalignment due to the difference in the comparison as the points where the amount of misalignment can be calculated, and
When the number of alignment points detected in the reference image is less than the set number in one block image, the step of repeating the combination with the adjacent block image until the set number is exceeded, and the step of repeating the combination.
A step of obtaining an alignment correction amount for correcting a misalignment of the inspection target for each block image of the reference image having an alignment point exceeding the set number with the inspection target of the inspection image as a reference position.
An image inspection method including a step of comparing a block image of the reference image corrected by the alignment correction amount with the inspection image to determine whether the inspection image is good or bad.

Images