JP2015228094A - Substrate counting method, substrate counting program, and substrate counter - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a substrate counting method, a substrate counting program, and a substrate counter that make it possible to easily precisely count a substrate.SOLUTION: A substrate counting method includes the steps of: obtaining the image of the end surface of a plurality of sheets of substrates stacked in one direction; integrating the brightness of each of the pixels constituting the image for each of the rows of pixels in one direction orthogonal to the other in the image to calculate an integrated value; detecting the substrate in the image based on the integrated value; and counting the number of sheets of the detected substrate to obtain a count value.

Description

  The present invention relates to a substrate counting method, a substrate counting program, and a substrate counting apparatus.

In the printed circuit board manufacturing process, there is an operation of counting (that is, counting) the number of stacked printed circuit boards when the printed circuit boards are shipped or stocked. The substrate counting operation is performed by the operator viewing the end face of the printed circuit board and counting it one by one. Alternatively, the substrate counting operation is performed by an optical sensor counter that scans laser light in one direction. As shown in FIG. 17, this type of optical sensor counter scans a laser beam in the thickness direction (vertical direction) of a plurality of printed circuit boards 501 at the end surface 501a of each printed circuit board 501. The number of printed circuit boards is calculated from the intensity of the reflected laser light.
Moreover, there exists what was disclosed by patent document 1 as another prior art regarding an optical sensor counter. Patent Document 1 describes a card counter that automatically counts the number of plastic cards by scanning a laser beam.

JP 2009-59010 A

By the way, when the operator counts the printed circuit boards one by one, the reliability of the counting work is limited, and there is a possibility that a counting error due to a human error may occur.
In addition, when this counting operation is performed by the conventional method using the above-described optical sensor counter, the reflection intensity and the reflection direction of the laser beam are likely to vary depending on the state of the end face of the printed circuit board, and an error occurs in the count value. It was easy. In particular, in the case of a printed circuit board with a router processed on the end face or a multilayer printed board in which cross sections of a plurality of laminated films appear on the end face, unevenness or material varies at each position of the end face, and the reflection intensity of laser light and The variation in the reflection direction tends to be large. For this reason, the boundary position of the printed circuit board cannot be detected correctly, and there are cases in which the counting process cannot be performed due to a large error.
Accordingly, the present invention has been made in view of such circumstances, and provides a substrate counting method, a substrate counting program, and a substrate counting apparatus that can perform substrate counting easily and with high accuracy. Objective.

  In order to solve the above problems, a substrate counting method according to an aspect of the present invention includes a step of acquiring images of end surfaces of a plurality of substrates stacked in one direction, and brightness of each pixel constituting the image. A step of calculating an integrated value for each pixel row in the other direction orthogonal to the one direction in the image, a step of detecting a substrate in the image based on the integrated value, and the detected substrate And counting the number of sheets to obtain a count value.

  The substrate counting program according to an aspect of the present invention includes a step of acquiring images of the end faces of a plurality of substrates stacked in one direction, and the luminance of each pixel constituting the image as the one direction in the image. A step of calculating an integrated value by integrating the pixel rows in other orthogonal directions; a step of detecting a substrate in the image based on the integrated value; and a counter value by counting the number of detected substrates. And a step of causing the computer to execute.

  A substrate counting device according to an aspect of the present invention includes an image acquisition unit that acquires images of end surfaces of a plurality of substrates stacked in one direction, and the luminance of each pixel constituting the image. An integrated value calculating unit that calculates the integrated value by integrating each pixel row in the other direction orthogonal to the direction; a substrate detecting unit that detects a substrate in the image based on the integrated value; and A count value acquisition unit that counts the number of sheets and acquires the count value.

  According to one embodiment of the present invention, substrates can be easily counted with high accuracy.

It is a block diagram showing an example of composition of substrate counting device 1 concerning an embodiment. It is a flowchart which shows the board | substrate counting method which concerns on embodiment. It is a flowchart which shows the procedure of a count calculation process. It is a figure which shows a mode that a board | substrate end surface is imaged using the board | substrate counter. It is a figure which shows the image which performed each process of gray scale conversion and smoothing, and the horizontal projection value of this image. It is a figure which shows the image which performed the image processing of the outline emphasis of a board | substrate, and the edge projection value of this image. It is a graph which shows the calculation method of the thickness of the board | substrate in an image. It is a graph which shows the method of detecting a board | substrate boundary position. It is a graph which shows the method of detecting a board | substrate boundary position. It is a graph which shows the method of detecting a substrate center position. It is a figure which shows the positional relationship of a board | substrate center position and a board | substrate boundary position. It is a figure which shows the 1st method of deleting an overdetection part. It is a figure which shows the state by which the count result was displayed on the display apparatus. It is a figure which shows the state by which the count result was displayed on the display apparatus. It is a figure for demonstrating the modification of embodiment. It is a figure for demonstrating the modification of embodiment. It is a figure for demonstrating a prior art example.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that, in each drawing described below, parts having the same configuration are denoted by the same reference numerals, and repeated description thereof is omitted.
<Configuration>
FIG. 1 is a block diagram showing a configuration example of a substrate counter 1 according to an embodiment of the present invention. A substrate counter 1 shown in FIG. 1 is, for example, a portable information terminal (ie, a computer device that is miniaturized to the extent that a user can carry it), and detects a plurality of printed boards (hereinafter referred to as boards) and the number of the printed boards. It is a device that counts. The substrate counting device 1 includes an imaging device 2, an arithmetic processing device 3, a display device 4, and a storage device 5.
The imaging device 2 is, for example, a digital camera built in the substrate counting device 1 and has a function of imaging a subject from the back side of the substrate counting device 1. The imaging device 2 can image the entire end surfaces of a plurality of substrates stacked in one direction (for example, the vertical direction) as a subject.

  The arithmetic processing device 3 includes an image acquisition unit 31, an image processing unit 32, an integrated value calculation unit 33, a substrate detection unit 34, a count value acquisition unit 35, and a calculation result output unit 36. The image acquisition unit 31 has a function of taking an image captured by the imaging device 2 into the arithmetic processing device 3. The image processing unit 32 has a function of performing image processing such as gray scale, smoothing, and contour (edge) enhancement on the image acquired by the image acquisition unit 31. The integrated value calculation unit 33 integrates the luminance of each pixel constituting the image for each pixel column in the other direction (for example, the horizontal direction) orthogonal to one direction for the image subjected to the image processing by the image processing unit 32. Thus, the integrated value is calculated. The substrate detector 34 has a function of detecting a substrate in the image based on the integrated value calculated by the integrated value calculator 33. The count value acquisition unit 35 has a function of counting the number of substrates detected by the substrate detection unit 34 and acquiring the count value. The calculation result output unit 36 has a function of outputting a calculation result such as a count value to the display device 4 and causing the display device 4 to display the calculation result. The calculation result output unit 36 also has a function of outputting a calculation result such as a count value to the storage device 5 and storing the calculation result in the storage device 5. The arithmetic processing unit 3 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory) in order to realize these functions.

  The display device 4 includes an image display unit 41 and an operation unit 42 that are arranged on the front side of the substrate counting device 1 (that is, the side opposite to the back side). The image display unit 41 has a function of displaying an image acquired by the image acquisition unit 31, a count value, a mark indicating a substrate position, a line indicating a substrate boundary position, and the like. The operation unit 42 is an operation for the user to input various instructions to the substrate counter 1 such as a plus (+) button, a minus (−) button for correcting the count value, and an imaging button for instructing imaging. Functions as a button. For example, the display device 4 is a touch panel display device, and the operation unit 42 is a GUI (Graphical User Interface) using a touch panel. When the user directly touches the operation button displayed on the touch panel type display device with a finger or a pen, an instruction corresponding to the content of the operation button is input to the substrate counter 1.

  The storage device 5 includes a data storage unit 51 and a program storage unit 52. The data storage unit 51 has a function of storing various data acquired by the arithmetic processing device 3 such as an image acquired by the image acquisition unit 31 and an image subjected to image processing by the image processing unit 32. The program storage unit 52 stores a program for realizing each function of the imaging device 2, the arithmetic processing device 3, and the display device 4. In order to store various data and programs in this manner, the storage device 5 has a nonvolatile storage memory such as an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), or a flash memory.

<Operation>
Next, an operation example of the substrate counter 1 shown in FIG. 1 will be described.
FIG. 2 is a flowchart showing a substrate counting method according to an embodiment of the present invention. FIG. 3 is a flowchart showing the procedure of the count calculation process. FIG. 4 is a schematic diagram showing how the substrate end face is imaged using the substrate counting apparatus 1.
In step S1 of FIG. 2, images are acquired by imaging the end faces of a plurality of substrates to be counted. Here, when the user touches the photographing button 421 shown in FIG. 4 with a finger or the like, the imaging device 2 (see FIG. 1) images the end surfaces 101a of the plurality of substrates 101. And the image acquisition part 31 (refer FIG. 1) acquires the imaged image.

  In this step S1, as shown in FIG. 4, the user is required to make a plurality of images so that the horizontal direction (X-axis direction) of the plurality of substrates 101 as the subject matches the horizontal direction (X′-axis direction) of the image. It is preferable to adjust the inclination of the substrate counter 1 relative to the substrate 101. Examples of the adjustment method include a method in which the user moves the substrate counting apparatus 1 by hand. Alternatively, this inclination adjustment may be automatically performed by the image acquisition unit 31.

  Of the information displayed on the display device 4, discard of the immediately preceding counting result (that is, the previous counting result is not present) can be executed by the user touching the redo button 422. For example, it is assumed that the count of the bundle A of substrates is executed, the number of counted sheets is 25, and the total number of counted sheets is 25 (first counting). Next, it is assumed that the count of the bundles B of the substrates is executed and the number of counted sheets is 30 and the total number of counted sheets is 55 (second count). Here, when the redo button 422 is pressed, the previous counting result is discarded, and the counting number displayed on the display device 4 is 0, and the total counting number is 25. Even if this redo button 422 is pressed, the image of the bundle B of substrates displayed together with the immediately preceding counting result does not change.

  In addition, of the information displayed on the display device 4, discarding (that is, clearing) of both the previous counting result and the total number of counting can be executed by the user touching the clear button 423. For example, it is assumed that, as described above, the first count is performed, and then the second count is performed. Here, when the clear button 423 is pressed, both the previous counting result and the total number of counts are discarded, and the number of counts displayed on the display device 4 is 0 and the total number of counts is also 0. Even if this clear button 423 is pressed, the image of the bundle B of substrates displayed together with the previous counting result does not change.

The image acquired by the image acquisition unit 31 may be either a color image or a grayscale image. In this description, it is assumed that a color image is acquired.
Next, the process proceeds to step S2 in FIG. In step S2 of FIG. 2, the substrate count calculation process is performed using the image acquired in step S1. In this step S2, for example, a plurality of steps S11 to S19 shown in FIG. 3 are performed.

  In step S11 of FIG. 3, image processing of gray scale and smoothing is performed on the color image acquired in step S1 of FIG. These processes are performed by the image processing unit 32 shown in FIG. Gray scale conversion may be performed by a simple average method that takes an average value of each luminance of R (red), G (green), and B (blue), or each luminance of R, G, and B is weighted. You may carry out by the weighted average method which takes an average value. When gray scale conversion is performed by a weighted average method, for example, an NTSC coefficient can be used as a coefficient for weighting each luminance of R, G, and B.

Next, the process proceeds to step S12 in FIG. In step S12, the luminance of each pixel constituting the image is integrated for each pixel column in the horizontal direction (X′-axis direction) of the image that has been subjected to the grayscale and smoothing image processing in step S11. Then, an integrated value (that is, a horizontal projection value) is calculated. The horizontal projection value is calculated by the integrated value calculation unit 33 shown in FIG.
FIGS. 5A and 5B are diagrams illustrating an image subjected to gray scale processing and smoothing processing, and a horizontal projection value of the image. The horizontal axis of FIG.5 (b) shows the horizontal projection value computed by step S12, and a vertical axis | shaft shows each position of the orthogonal | vertical direction of an image. As shown in FIGS. 5A and 5B, in the image obtained in step S12, the position where the luminance at the position corresponding to the substrate (hereinafter referred to as the substrate position) corresponds to the boundary of the substrate (hereinafter referred to as the substrate boundary position). Therefore, the horizontal projection value at the substrate position is larger than the horizontal projection value at the substrate boundary position.

Next, the process proceeds to step S13 in FIG. In step S13, image processing for emphasizing the outline of each substrate is performed on the image that has been subjected to grayscale and smoothing image processing in step S11. The image processing for contour enhancement is performed by the image processing unit 32 shown in FIG.
Next, the process proceeds to step S14 in FIG. In step S14, as shown in FIG. 5, the luminance of the image that has been subjected to the contour enhancement image processing in step 13 is integrated in the horizontal direction of the image to calculate an integrated value (that is, a horizontal projection value). . Furthermore, a correction may be made so that the value increases as the change in luminance increases with respect to the horizontal projection value of an image in which the outline of each substrate is emphasized. The horizontal projection value is calculated and corrected by the integrated value calculation unit 33 shown in FIG. Hereinafter, the horizontal projection value calculated in step S14 is referred to as an edge projection value.

  FIGS. 6A and 6B are diagrams illustrating an image subjected to image processing for emphasizing the outline of the substrate and edge projection values of the image. In FIG. 6B, the horizontal axis indicates the edge projection value, and the vertical axis indicates each position in the vertical direction of the image. As shown in FIGS. 6A and 6B, in the image obtained in step S13, the brightness of the contour is emphasized more than the brightness of other positions, so the horizontal projection value of the board boundary position is the board position. The value is larger than the horizontal projection value of.

Next, the process proceeds to step S15 in FIG. In step S15, the thickness of the substrate in the image is calculated based on the edge projection value calculated in step S14.
FIG. 7 is a graph showing a method for calculating the thickness of the substrate in the image. In FIG. 7, the horizontal axis indicates each position in the vertical direction of the substrate, and the vertical axis indicates the edge projection value. In step S15, for example, as shown in FIG. 7, the autocorrelation of the edge projection value is calculated, and the shift amount when the autocorrelation value becomes the maximum value within the search range is set as the thickness of the substrate. The search range of the substrate thickness (hereinafter referred to as substrate thickness) is given as a ratio to the assumed substrate thickness. For example, the lower limit of this ratio is a default value (that is, an initial setting value) that is 0.5 times the assumed substrate thickness, and can be arbitrarily set within a range of 0.1 to 1.0 times the assumed substrate thickness. To do. The upper limit of this ratio is a default value 1.5 times the assumed substrate thickness, and can be arbitrarily set within a range of 1.5 to 3.0 times the assumed substrate thickness. The substrate thickness is calculated by the substrate detector 34 shown in FIG.

Next, the process proceeds to step S16 in FIG. In step S16, the substrate boundary position is detected based on the edge projection value calculated in step S14.
8 and 9 are graphs showing a method for detecting the substrate boundary position. The horizontal axis in FIG. 8 indicates each position in the vertical direction of the substrate, and the vertical axis indicates the edge projection value calculated in step S14. 9A and 9B, the horizontal axis indicates the edge projection value (that is, the maximum value) of the maximum point shown in FIG. 8, and the vertical axis indicates the frequency.
For example, as shown in FIG. 8, the maximum point of the edge projection value is detected. The range in which one maximum point is detected at each position in the vertical direction of the image is given as a ratio to the substrate thickness calculated in step S15. For example, this ratio is set to a default value of 1 times the substrate thickness, and can be arbitrarily set within a range of 0.5 to 2 times the substrate thickness.

  Further, as shown in FIG. 9A, a histogram is created for the maximum value at the maximum point. Then, as shown in FIG. 9 (b), the value A of the two-region division is obtained from the histogram by the discriminant analysis method, and only the value B or more obtained by multiplying the value A by the designated ratio α is recognized as the effective maximum value C. To do. A maximum point corresponding to an effective maximum value C is detected as a substrate boundary position. For example, the designated ratio α is 0.5 as a default value, and can be arbitrarily set within a range of 0.1 to 2.0. The substrate boundary position is detected by the substrate detection unit 34 shown in FIG.

Next, the process proceeds to step S17 in FIG. In step S17, the center position of the substrate (hereinafter referred to as the substrate center position) is detected based on the horizontal projection value calculated in step S12.
FIG. 10 is a graph showing a method for detecting the substrate center position. The horizontal axis in FIG. 10 indicates each position in the vertical direction of the substrate, and the vertical axis indicates the horizontal projection value calculated in step S12. Here, as shown in FIG. 10, the maximum point of the horizontal projection value calculated in S12 is detected and set as a substrate center position candidate. Since the maximum point of the horizontal projection value calculated in S12 is not clear, the position of the maximum point is calculated from the zero cross point of the smoothing differentiation. The width of the smoothing differential calculation is given as a ratio to the substrate thickness calculated in step S15. For example, the ratio of the width is 0.25 as a default value, and can be arbitrarily set within a range of 0.1 to 1.0.

Next, the process proceeds to step S18 in FIG. In step S18, the substrate in the image is detected using the results of steps S16 and S17.
FIG. 11 is a diagram illustrating a positional relationship between the substrate center position and the substrate boundary position. As shown in FIG. 11, if the board | substrate boundary position detected by step S16 exists between the board | substrate center positions of two adjacent points, it will determine with "board | substrate detection." If it is determined as “substrate detection”, a position shifted by “substrate thickness ÷ 2” from the substrate boundary position used for this detection is registered as the substrate position of the detected substrate.

  However, if the interval between the detected substrate position and the substrate position registered immediately before is out of the specified range, “substrate detection” is not performed. The specified range of the interval is given as a ratio to the substrate thickness in the image calculated in step S15. For example, the lower limit value of the ratio of the designated range is 0.67 as a default value, and can be arbitrarily set within a range of 0.1 to 2.0. The upper limit value of the ratio of the designated range is 2.0 as a default value, and can be arbitrarily set within a range of 0.5 to 5.0.

Next, the process proceeds to step S19 in FIG. In step S19, regarding “board detection”, if there is an overdetection portion, it is deleted.
FIG. 12 is a diagram illustrating a first method for deleting an overdetection portion. The horizontal axis in FIG. 12 indicates each position in the vertical direction of the image. As shown in FIG. 12, the first method of deleting the overdetection portion is to check the interval between the substrate positions along the vertical direction of the image, and if there is a place where the interval between the substrate positions is more than a specified value, From there, all the detection positions ahead are excluded. That is, the “coordinates where the substrate is reflected in the image” is used as a starting point, and the substrate position interval is confirmed by scanning up and down along the vertical direction. The threshold value for exclusion at the substrate position interval is given as a ratio to the substrate thickness calculated in step S15. For example, the threshold for exclusion by the substrate interval is three times the substrate thickness.

  Further, as a second method of deleting the overdetection portion, an average color tone of a range in which the substrate position is detected (hereinafter referred to as a substrate detection range) is calculated, and the color tone of each substrate position is an average color tone of the substrate detection range If it deviates greatly from the above, that part is excluded. The threshold for exclusion by color tone is given by the color distance (RGB distance). For example, if there is a substrate position having a color tone that exceeds 128 in RGB distance from the average color tone of the substrate detection range, the substrate position is excluded as an overdetection portion. In the present embodiment, it is preferable to perform at least one of the first and second methods for deleting the overdetection portion. The substrate detection unit 34 (see FIG. 1) deletes the overdetection portion.

  After performing Step S19, the process proceeds to Step S3 in FIG. In step S3, the calculation result output unit 36 (see FIG. 1) outputs the calculation processing result obtained in step S2 to the display device 4, and causes the display device 4 to display the calculation processing result. Here, for example, as shown in FIG. 13, the substrate position is indicated by a rectangular mark 411, and the substrate boundary position is indicated by a solid line 412. In the image display unit 41, the rectangular mark 411 and the solid line 412 are displayed over the image of the substrate end face. Further, the counted number of substrates (for example, 24 sheets) and the updated total number of counted sheets (for example, 223 sheets) are also displayed on the image display unit 41, respectively.

  Next, the process proceeds to step S4 in FIG. In step S4, the calculation result output unit 36 (see FIG. 1) outputs the result of the calculation process obtained in step S2 to the storage device 5, and the number of substrates obtained in step S2 and the updated number are updated. The total number of counts is recorded in the data storage unit 51. In this embodiment, the order of step S3 and step S4 may be interchanged, and step S3 and step S4 may be performed in parallel.

  Next, the process proceeds to step S5 in FIG. In step S5, the user confirms whether or not the counted number displayed on the image display unit 41 is correct. As shown in FIG. 13, the substrate position is a rectangular mark 411, and the substrate boundary position is a solid line 412, which are superimposed on the image of the substrate end face. For this reason, the user can easily confirm whether or not the counting result of the number of substrates is correct by visually recognizing the overlapping state of the image, the rectangular mark 411, and the solid line 412. If the counting result is correct, the flowchart shown in FIG. 2 is terminated.

  If there is an error in the counting result, for example, if the counting result is smaller than the actual number of substrates, the process proceeds to step S6. In this case, as shown by the arrow in FIG. 14, a part of the rectangular mark 411 is not displayed on the image of the substrate end face. Therefore, in step S6, the + button 424 of the operation unit 42 is touched with a finger or the like to correct the direction to increase the number of substrates. Thereafter, the flowchart shown in FIG. 2 ends.

  Similarly, for example, when there are more counting results than the actual number of substrates, the process proceeds from step S5 to step S7. In this case, an extra rectangular mark is displayed in the image displayed on the image display unit 41. Therefore, in step S7, the minus button 425 of the operation unit 42 is touched with a finger or the like to correct the direction so as to reduce the number of substrates. Thereafter, the flowchart shown in FIG. 2 ends.

<Effect of embodiment>
According to the embodiment of the present invention, the horizontal projection value is calculated by integrating the luminance of each pixel constituting the image for each pixel column in the horizontal direction. Then, the calculated horizontal projection values are compared in the vertical direction, and a bright portion is detected as a position where the substrate exists (that is, the substrate position). Since the counting of the substrate is not performed only by the user's vision, but is performed using arithmetic processing, human error can be prevented and counting can be performed easily.

  Unlike the case of detecting only one horizontal position of the substrate with an optical counter that scans the laser light in one direction, the local unevenness of the substrate end surface is obtained by using the luminance information of the two-dimensional image. It is possible to reduce errors due to differences in colors and materials. Thereby, the detection accuracy of a board | substrate can be raised and the counting precision of a board | substrate can also be raised as a result. Since the accuracy of substrate detection and counting is improved, for example, the number of substrates packed in a plastic bag can be counted through the plastic bag without being taken out of the plastic bag.

  In the display device, the detected substrate position and substrate boundary position are displayed superimposed on the captured image. As a result, the user can visually and easily confirm whether or not the detection and counting of the substrate in the image have been performed correctly. If an error is found in the counting result by this confirmation, the user can correct the counting result by touching an operation unit (+ button, − button, etc.) displayed on the display device. Thereby, since an accurate result is obtained, the cumulative count value of the substrate can be accurately grasped.

In this embodiment, various parameters (ratio for determining the search range of the substrate thickness, ratio for determining the detection range of the maximum point of the edge projection value, and specified ratio for determining the effective maximum value of the edge projection value) The default value and the settable range are exemplified for the ratio for determining the width of the smoothing differential calculation, the ratio of the designated range for determining “substrate detection”, and the like.
Here, the present embodiment can be applied to counting processing of various printed circuit boards. However, depending on the thickness and type of the printed circuit board, erroneous detection of the circuit board may occur if the above various parameters are left at the default values. Conceivable. In that case, the occurrence of erroneous detection may be reduced by adjusting the values of the various parameters described above. By adjusting various parameters by feedback so as to improve the substrate detection accuracy, it is possible to realize a highly accurate substrate counting apparatus or substrate counting program that is easy for the user to use.

  As described above, according to the present embodiment, it is possible to easily count the substrates with high accuracy. It has a counting processing function that takes advantage of the feature that the substrate has a plate shape (that is, a shape in which the end surface is long in the horizontal direction), and it is possible to count a substrate that is difficult to count with a conventional optical counter. In addition, even if the counting result is different from the actual number of substrates, the user can distinguish the difference portion at a glance and can correct the counting result.

<Modification>
(1) In the present embodiment, a case has been described in which a color image is acquired, converted into a gray scale, and then the luminance of the image is integrated in the horizontal direction. However, in this embodiment, the integration in the horizontal direction may be performed before the gray scale, not after the gray scale. For example, the brightness of the color image shown in FIG. 15A is set to be horizontal for each of B (blue), G (green), and R (red) as shown in FIGS. 15 (b), 15 (c), and 15 (d). By integrating in the direction, each integrated value of B, G, R is obtained. Thereafter, the average value of each integrated value may be set to the integrated value after gray scale conversion. The average value may be a value obtained by simply averaging each integrated value, or may be a value obtained by weighting and averaging. Even in such a case, the same effects as those of the above-described embodiment can be obtained.

(2) Further, in the present embodiment, a case has been described in which the color image is acquired in step S1 of FIG. However, in the present embodiment, the acquired image is not limited to a color image, and may be a grayscale image. That is, the image may be a grayscale image from the beginning, or a color image that has been grayscaled in the imaging apparatus may be acquired. In this case, it is of course unnecessary to make the acquired image grayscale, and only smoothing image processing is performed. Even in such a case, the same effects as those of the above-described embodiment can be obtained.

(3) In the present embodiment, as shown in FIG. 3, using both the horizontal projection value calculated in step S12 and the edge projection value calculated in step S14, the detection of the substrate in the image, The count value was calculated. However, in the present invention, the method for detecting the substrate in the image and calculating the count value is not limited to this. For example, the detection of the substrate in the image and the calculation of the count value may be performed using only the horizontal projection value calculated in step S12. In this case, steps S13 to S16 can be omitted, and the process proceeds to step S17 after step S12. In step S17, the center position of the substrate is calculated using the horizontal projection value. For example, the maximum point of the horizontal projection value is set as the center position of the substrate in the vertical direction of the image. In step S18, “substrate detection” is determined by calculating the center position of the substrate. Even in such a case, the substrate can be counted easily and with high accuracy.

(4) Similarly, in the present invention, for example, the detection of the substrate in the image and the calculation of the count value may be performed using only the edge projection value calculated in step S14. In this case, step S12 can be omitted, and the process proceeds to step S17 after step S16. In step S17,
The center position of the substrate is calculated using the substrate boundary position calculated in step 16 instead of the horizontal projection value calculated in step S12. For example, in the vertical direction of the image, an intermediate point between two substrate boundary positions is set as the center position of the substrate. In step S18, “substrate detection” is determined by calculating the center position of the substrate. Even in such a case, the substrate can be counted easily and with high accuracy.

(5) In the present embodiment, the case where the end face of the substrate is imaged by the digital camera built in the substrate counter 1 has been described. However, the present embodiment is not limited to this. The digital camera may not be incorporated in the substrate counter (that is, the substrate counter and the digital camera may be provided separately). In this case, the image captured of the end face of the substrate with the digital camera may be output to the substrate counter via a wired or wireless signal line, or the image captured with the digital camera is recorded on a recording medium. May be read by the substrate counter. In either case, the same effects as those of the above-described embodiment can be obtained.

(6) Moreover, in this embodiment, the imaging device 2 was a digital camera, and the case where the image to be used is the image which imaged the end surface of the several board | substrate with the digital camera was demonstrated. However, in the present embodiment, the image used with the imaging device is not limited to this.
For example, as illustrated in FIG. 16, the imaging device may be a line sensor 20. The line sensor 20 is used to image a plurality of locations separated from each other in the horizontal direction among the end surfaces 101a of the plurality of substrates 101. When there is one line sensor 20, the line sensor 20 is scanned in the horizontal direction. Moreover, when there are two or more line sensors 20, their arrangement positions may be fixed. The images captured by such a method are a plurality of images in which the end surfaces 101a of the plurality of substrates 101 are taken along a vertical line from a plurality of positions separated from each other in the horizontal direction. Even when these images are used, it is easier and more accurate to count the substrate than when only one horizontal position of the substrate is detected by an optical counter that scans laser light in one direction. Can be done.

(7) Moreover, in this embodiment, the case where the board | substrate made into the object of a count was a printed circuit board was demonstrated. However, the present embodiment is not limited to this. The board may be a board other than the printed board, for example, a plastic card board or a board made of other materials. In either case, the same effects as those of the above-described embodiment can be obtained.

  In order to verify the effect of the present invention, the present inventor has confirmed whether or not the number of substrates has been erroneously detected in the substrate state assumed when the printed circuit board is counted. The results are shown in Table 1.

For evaluation, press-processed products, router-processed products (both sides), and router-processed products (multilayer) were prepared. Then, the number of substrates was detected according to the procedure described in the embodiment. The press-processed product refers to a substrate that has been processed by press processing in which the outer shape of the substrate is extracted with a mold. As a feature of the pressed product, its end face is often rough and bright white.
The router processed product (both sides) refers to a double-sided board whose outer shape is processed by router processing. As a characteristic of the router processed product (both sides), its end face is smooth, and the color is often darker and gray compared to the press processed product. Furthermore, a router processed product (multilayer) refers to a multilayer substrate whose outer shape is processed by router processing. As a characteristic of router processed products (multilayer), in addition to the characteristics of router processed products (double-sided), the layer of the substrate can be seen from the end surface because of the multilayer substrate (that is, the cross section of multiple laminated films appears on the end surface) ).

As shown in Table 1, in the press-processed product and the router-processed product (both sides), the end surface had a horizontal length longer than 25 mm, and the vertical length was black marking for 2.5 printed circuit boards. In the state, a false detection occurred. On the other hand, in the router processed product (multilayer), the number of substrates could be detected without any problem even if black marking longer than 25 mm was present on the end face. Moreover, when a press-processed product, a router-processed product (both sides), and a router-processed product (multilayer) were mixed with each other, some misdetections occurred depending on the combination.
Regarding the other conditions, the number of substrates could be detected without any problem in any of the press-processed product, the router-processed product (both sides), and the router-processed product (multilayer). However, in order to correctly detect the number of substrates, it is necessary to keep the distance between the substrate end surface, which is a subject, and the imaging device that images the substrate constant.

DESCRIPTION OF SYMBOLS 1 Board | substrate counter 2 Imaging device 3 Processing unit 4 Display unit 5 Storage device 31 Image acquisition part 32 Image processing part 33 Integrated value calculation part 34 Substrate detection part 35 Count value acquisition part 36 Calculation result output part 41 Image display part 42 Operation Unit 51 data storage unit 52 program storage unit 101 substrate 101a end surface 411 rectangular mark 412 (indicating substrate position) solid line 421 (indicating substrate boundary position) shooting button 422 redo button 423 clear button 424 + button 425 -button

Claims (11)

Acquiring images of end faces of a plurality of substrates stacked in one direction;
Integrating the luminance of each pixel constituting the image for each pixel column in the other direction orthogonal to the one direction in the image, and calculating an integrated value;
Detecting a substrate in the image based on the integrated value;
And counting the number of detected substrates to obtain a count value.   The substrate counting method according to claim 1, further comprising a step of displaying a mark representing the position of the detected substrate so as to overlap the image.   The substrate counting method according to claim 1, further comprising: displaying the count value on a display unit.   The substrate counting method according to claim 3, further comprising a step of correcting the count value displayed on the display unit via a GUI. In the step of detecting the substrate,
2. The boundary position or center position of the plurality of substrates in the image is detected from the integrated value, and the substrate is detected based on the positional relationship between the center position or the boundary positions. The substrate counting method according to claim 4. In the step of detecting the substrate,
Determining whether the interval between the detected position of the first substrate and the position of the second substrate detected adjacent to the first substrate is within a preset interval range; 6. The substrate counting method according to claim 1, wherein when the determination is made, the detection of the second substrate is invalidated. In the step of detecting the substrate,
7. The method according to claim 1, wherein whether or not the detected color tone of the substrate is within a preset color tone range is determined, and if not, the detection of the substrate is invalidated. The substrate counting method according to any one of the above.   The substrate counting method according to any one of claims 1 to 7, wherein the image is an image obtained by capturing an end face of the plurality of substrates with a digital camera.   8. The image according to claim 1, wherein the image is an image obtained by imaging a plurality of locations separated from each other in the other direction among end surfaces of the plurality of substrates by a line sensor. 9. The substrate counting method according to claim 1. Acquiring images of end faces of a plurality of substrates stacked in one direction;
Integrating the luminance of each pixel constituting the image for each pixel column in the other direction orthogonal to the one direction in the image, and calculating an integrated value;
Detecting a substrate in the image based on the integrated value;
A substrate counting program for causing a computer to execute the step of counting the detected number of substrates to obtain a count value. An image acquisition unit for acquiring images of end faces of a plurality of substrates stacked in one direction;
An integrated value calculation unit that calculates the integrated value by integrating the luminance of each pixel constituting the image for each pixel row in the other direction orthogonal to the one direction in the image;
A substrate detector for detecting a substrate in the image based on the integrated value;
And a count value acquiring unit that counts the number of detected substrates to acquire a count value.