JPS627588B2 - - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION The present invention relates to a method for automatically inspecting two-dimensional patterns using a computer.

In general, on the production line, the appearance of products or parts (shape, dimensions, scratches, etc.), misalignment of labels affixed to products, mistakes, dirt, or omissions in characters and symbols printed on labels and packaging boxes, etc. Furthermore, it is necessary to inspect for foreign substances that have entered the line. Conventionally, for the purpose of automatically performing this type of inspection, the image to be inspected obtained by scanning the pattern to be inspected with a one-dimensional image sensor and the reference image obtained by scanning the reference pattern are compared to determine the pattern to be inspected. Various methods have been proposed for determining pass/fail. In this type of inspection method, if only a specific part of the object to be inspected needs to be inspected in detail, when comparing the entire pattern included in the image, information on parts that do not need to be inspected becomes noise. It becomes impossible to conduct an accurate inspection. Therefore, it is common practice to divide the image into multiple areas and inspect only the necessary inspection area, but conventionally, for example, as shown in Figure 1a, the screen is divided into areas k ₁ with the edge of the image as a reference. When pattern _B is to be inspected, the area _k2 is set as the inspection area. However, with this method, if the position of the object to be inspected shifts, the pattern will not fit within the inspection area correctly, as shown in Figure b.
In this case, to inspect pattern B, inspection area k ₂
Even if specified, it was not possible to conduct an appropriate inspection. In addition, as shown in Figure c, when patterns are lined up in multiple rows or when there is a continuous pattern near the pattern to be inspected, the specific pattern to be inspected (for example, the character B ), and information on other patterns becomes noise, making it impossible to perform accurate inspection.

An object of the present invention is to determine the coordinates of the center position of an area to be inspected based on the horizontal and vertical edges of the entire pattern included in the image, and to set an inspection frame around this center position. The object of the present invention is to propose an automatic pattern inspection method that allows a specific portion to be inspected accurately at all times by setting the area inside this inspection frame as the inspection area.

The inspection method of the present invention will be explained in detail below with reference to the drawings.

Referring to FIG. 2, there is shown a schematic configuration of an apparatus for carrying out the inspection method of the present invention. In the figure, 1 is the main body of the automatic pattern inspection apparatus, and 2 is for conveying the objects to be inspected 3, 3... A conveyor, 4 is connected to the power supply in the inspection device main body 1 via a cord _L1 , and is a lighting device that illuminates the object to be inspected 3 at the inspection position, 5 is connected to the inspection device main body 1 via a cord _L2 This is a position detection sensor. Position detection sensor 5
are floodlights 5 arranged opposite to each other with the conveyor 2 in between.
a and a light receiver 5b, when the object 3 to be inspected comes to the inspection position, the edge of the object 3 is detected and the light receiver 5
b generates a position detection signal (start signal).

Reference numeral 6 denotes a camera that photographs the pattern to be inspected of the object to be inspected 3 and obtains an electrical image.
One-dimensional image sensor 7 as shown in FIG.
, a condensing lens 9 that focuses the image of the pattern to be inspected 8 on the light receiving surface 7 a of the image sensor 7 , and a circuit 10 that drives the image sensor 7 .
As such a camera, for example, one commercially available under the name of a semiconductor camera can be used. The one-dimensional image sensor 7 is a solid-state image sensor that does not use an electron beam for scanning, has a self-scanning function, and integrates an array of photodiodes _DP and a scanning circuit of a MOS shift register on a single silicon substrate. This is what I did. Figure 4 shows the equivalent circuit of this image sensor. In the figure, D _P is a photodiode arranged in a row on the light receiving surface, C is a capacitance connected in parallel to each photodiode D _P , and D is a capacitance connected in parallel to each photodiode D P. A diode connected in series with each photodiode D _P , R _L is the load resistance, C _O is the output capacitance, V _T is the DC power supply,
SR is a shift register. In this image sensor, when one clock pulse is applied to the shift register SR, the shift register SR sequentially applies a scanning pulse to each circuit of the photodiodes D _P , D _P , etc., and automatically scans the photodiode D _P array sequentially from the end. scan. Each photodiode D
The diode connected in series with _P is always in a reverse bias state, and only the diode D of the circuit scanned by the scan pulse is turned on, and the capacitance C is charged to the voltage of the power supply V _T . The conductivity of the photodiode D _P increases due to the incidence of light, and a charge corresponding to the amount of incident light flux is discharged from the capacitance C, so that the terminal voltage of the capacitance C decreases. When a clock pulse is applied again after one frame time and a scanning pulse is applied to the circuit of each photodiode, each capacitance C is recharged. At this time, the charging current flowing through the capacitance C is equal to the drop in the terminal voltage of the capacitance C. ,
In other words, it is proportional to the amount of incident light flux, and a signal proportional to the amount of incident light flux is output as a video signal E _V in the form of a continuous pulse train.
is extracted as. Since the photodiode operates in a charge accumulation mode, the video signal E _V is a signal proportional to the product of light intensity and repetitive scanning time. An example of an image sensor that is actually used has 64 photodiodes with a light receiving area of 50 μm x 50 μm arranged in a straight line at 50 μm intervals, enabling high-speed operation up to 2 MHz.
The electrical signal output with respect to the amount of incident light flux is linear.

The camera 6 incorporating the image sensor 7 as described above is placed facing the object to be inspected on the conveyor 2, and the conveyor 2 is moved in the scanning direction Y of the image sensor 7.
When the shift register SR is moved in the direction of the arrow X perpendicular to , and clock pulses of a constant period are applied to the shift register SR, the entire surface of the object to be inspected can be scanned and an image of the object to be inspected can be obtained. In this case, the resolution of the image is determined by the frequency of the clock pulse and the number of photodiodes in the image sensor. In the method of the present invention, for example, as described above, the number of photodiodes (one frame) is 64, and one field is composed of 256 clock pulses. In this case 1
The total number of picture elements in the field is 256 x 64.

Referring to FIG. 5, the electrical configuration of the apparatus for carrying out the method of the present invention is shown in a block diagram, and FIG. 6 shows the configuration of the operation display panel section 1a of the inspection apparatus main body 1. There is. Image sensor 7
The peak value of each pulse of the video signal E _V obtained from is proportional to the brightness and darkness of each picture element. The signal obtained from this image sensor 7 is input to a binarization circuit 11, as shown in FIG. Binarization circuit 1
1 converts each pulse of the video signal E _V into a white or black signal depending on whether its peak value is below or above a certain threshold level, and is a binary signal. The image represented by the video signal E _V ' obtained at the output side of the circuit 11 is a binary image consisting of white or black and without gray areas. The output E _V ' of the binarization circuit 11 is input to a central processing unit (CPU) 14 through an input circuit 13 of a microcomputer 12 housed in the inspection apparatus main body 1. The microcomputer 12 also includes a reference image memory (RAM) 15 that stores a reference image, an image memory (RAM) 16 that stores an image to be inspected, and an operation for comparing both images. An arithmetic memory (RAM) 17 used for performing the test and a program memory (ROM) 18 for storing programs are provided. The image and the image to be inspected are sent to a monitor television 21 provided on the operation display panel 1a through a video signal generation circuit 19 and a blanking circuit (a circuit that erases from the screen a portion corresponding to an address in which no image is stored in memory).
are now displayed vertically.

The operation display panel 1a also includes a switch 22 for instructing designation of an inspection area, a comparison processing method changeover switch 23 for initially changing the processing method when comparing a reference image and an image to be inspected, and a reference image. A digital switch 24 for setting an allowable deviation for setting an allowable value of deviation between the histogram of the image and the histogram of the image to be inspected, and a writing push button switch 25 for instructing writing of the position of the inspection area and the deviation.
, an inspection area designating digital switch 26 that specifies the center position and size of an image inspection area, a deviation readout pushbutton switch 27 that instructs reading of deviations, and a pushbutton switch 27 that instructs to read deviations.
A digital display section 28 consisting of a light emitting diode (LED) is provided which displays the deviation of the area designated by the digital switch 26 when the switch 22 is pressed. Processing method setting switch 2
3. The contents of the instructions given by the digital switch 24 for setting the allowable deviation value, the push button switch 25 for writing the deviation instruction, and the digital switch 26 for specifying the inspection area position are input to the central processing unit 14 via the input circuit 29. There is. A digital display 28 for displaying deviation values is connected to the central processing unit 14 via an output circuit 30, and displays the deviation in the area specified by the digital switch 26 in percentage when the push button switch 27 is pressed. I'm starting to do that. The operation display panel 1a is further provided with a counter 34 having LED display sections 31 to 33 for displaying the total quantity inspected, the quantity of non-defective products, and the quantity of defective products, respectively. 35. A counter reset button 36 is provided below the display section of the counter 34, and the reference image memory 15 and the image memory 1 to be inspected are placed on the sides of this button.
A system reset button 37 for clearing the contents of 6 is provided. Further, above the display of the counter 34, a good product indicator light 38 and a defective product indicator light 39 are provided, which light up when the object to be inspected is a good product and a defective product, respectively, and below the monitor television 21. A push button switch 40 for starting the conveyor 2 and a push button switch 41 for stopping the conveyor 2 are provided. Further, below these pushbutton switches, a power switch 42 and a power indicator light 43 that lights up when the power is turned on are provided.

Next, an automatic pattern inspection method using the above device will be explained with reference to the flowchart shown in FIG. Let the direction of movement (horizontal direction of the screen) be the x-axis direction.

To start the inspection, first turn on the power switch 42 and turn on the system reset switch 37.
Press to clear memory 15, 16, etc. Next, the number of inspection areas to be set and the center position of each inspection area are specified according to the object to be inspected (step a in FIG. 7). To specify the center position of this inspection area,
This is done by switching the switch 22 to the inspection area designation side and specifying the coordinates of the center position of the inspection area using the digital switch 26. Commands from the switch 22 and pushbutton switch 26 are sent to the input circuit 29.
The data is sent to the central processing unit CPU 14 through the program, and the CPU 14 specifies the inspection area according to the program using the method described later.

After specifying the inspection area as described above, a pattern comparison method is determined (step b in FIG. 7). There are various ways to compare patterns, but
In this example, as will be described later, an area comparison method that compares the area of white or black of a pattern in an inspection area, a uniaxial histogram comparison method that compares histograms of white or black in one axis direction of a pattern, and a different Comparing two axial histograms 2
The inspection can be performed using three types of comparison methods: the axial histogram comparison method. The comparison method for this pattern is set by switching the comparison processing method setting switch 23 to "area comparison method", "1-axis method" or "2-axis method",
The command from this switch is sent through the input circuit 29.
It is given to the CPU 14. The CPU 14 causes pattern comparison processing to be performed according to a predetermined program. After determining the pattern comparison processing method, the conveyor 2 is started to take an image of the object to be inspected to be used as a reference for inspection, and the data of the reference image is taken in (step c in FIG. 7). Ingesting this data is
It starts as soon as the position sensor 5 generates a signal and ends when 256 clock pulses have been applied. The image obtained from the camera 6 is converted by the binarization circuit 11 into a binarized image consisting of black or white picture elements, and this binarized image is displayed above the screen of the monitor television 21 (the seventh Step d) in the diagram. Next, the operator looks at this image on the TV screen and determines whether it is suitable as a reference image (step e in Figure 7), and if it is not suitable as a reference image, then After making necessary changes and adjusting the lighting conditions, the system reset switch 37 is pressed to clear the memory 15 again, and then the reference image data is imported.
If the reference image displayed on the monitor television 21 is appropriate, place an object to be inspected that appears to be normal on the conveyor 2, and import its image data in the same manner as described above (see Fig. 7). step f). This binary image of the normal object to be inspected is displayed at the bottom of the screen of the monitor television 21 (step g in FIG. 7). Note that whether or not the image signal given from the camera 6 should be used as a reference image is determined by the operator, and the image data is activated by the output signal of the position detection sensor 5. That is, only the image obtained by starting scanning based on the first output of the position detection sensor after the system reset switch 37 is pressed is stored in the reference image memory 15 as a reference image.
The image obtained by starting scanning based on the output of the position detection sensor generated thereafter is stored in the image to be inspected memory 16 as an image to be inspected. The contents of reference image memory 15 are held until system reset switch 37 is pressed again, and therefore the reference image on monitor television 21 is also held until system reset switch 37 is pressed. The contents of the image to be inspected memory 16 are rewritten each time an output from the position detection sensor 5 is generated and data of a new image to be inspected is input, and the image to be inspected on the monitor television 21 is also updated each time. Replaced with the inspection image.

Next, the CPU 14 sets inspection areas at designated positions for each of the binarized reference image and the image to be inspected, and displays the frame of each inspection area on the monitor television 21. The method of setting this inspection area will be explained with reference to FIGS. 8 and 9.
Assume now that the reference image is as shown in FIG. 8, and that only the letter "B" among the patterns included in this image is to be inspected. To set the inspection area, first detect the vertical and horizontal edges u, d, l, r of the patterns "A to H" included in the image, and then detect the area Q surrounded by these edges. Determine the coordinates of the center position of the inspection area by considering the coordinate system within. The coordinate axes of this coordinate system are edges u, d
Any method that can specify the coordinates of the position of each point in the area Q surrounded by This is the way to do it. In this example, the ninth
As shown in the figure, the edges d and l are the x-axis and the y-axis, respectively, and the lower left corner of the region Q is the origin 0. Then, set the lower right corner of area Q to (100, 0) and the upper left corner (0,
100), the x-axis and y-axis are divided into 100 equal parts, and the coordinates (X ₁ , Y ₁ ) of the center position α of the inspection area are set by the digital switch 2b. In the example shown, X ₁ = 45, Y ₁
=85, and a rectangular inspection frame β of a size surrounding the letter "B" is set around this center position α.
The size and shape of the inspection frame β can be appropriately set depending on the size and shape of the pattern included in the inspection area, and the area inside this inspection frame β is defined as the inspection area k. The size of the inspection frame β is set by writing its width w and height h in advance using a digital switch, so that when the center position α is determined, the inspection frame β is automatically determined around it. Program it.

Detecting the edges of the entire pattern included in the image is
This can be done by creating and storing histograms of the area of the pattern in the x-axis and y-axis directions, and detecting the addresses of the edges of these histograms. In this case, the area of the pattern can be determined by taking the area of the black part or by taking the area of the white part, but in special cases where a pattern that appears as a white outline on a black background is to be inspected. , and take the area of the black part. In FIG. 8, Hx indicates the histogram in the x-axis direction (horizontal direction) of the pattern included in the image, and Hy indicates the histogram in the y-axis direction (vertical direction). In this case, the y-axis direction histogram Hy may be created for the entire screen in the y-axis direction, but as shown in the figure, it is created only for a portion of a certain width above and below to find the lower left corner and upper right corner of the area Q. It will be easier to program if you use this method.

The above histograms Hx and Hy can be created, for example, by counting and storing the number of black pulses output from the binarization circuit for each clock pulse, or by counting and storing the number of black pulses output from the binarization circuit, or by calculating the number of black pulses output from the reference image memory and the image memory to be inspected. It can be created by picking up addresses storing picture elements, counting and storing them for each scanning line in the horizontal and vertical directions.

In this way, in the present invention, when specifying the inspection area, the horizontal and vertical edges of the entire pattern included in the image are taken as a reference, so the entire position of the object to be inspected may be slightly shifted at the same time on the TV screen. The pattern to be inspected can be placed within a predetermined inspection frame even when the pattern is displayed, and the pattern to be inspected and the reference pattern can always be accurately matched to improve inspection accuracy.

After specifying the inspection area, the reference pattern and the pattern to be inspected are compared for each inspection area (step i in FIG. 7). As mentioned above, there are three types of comparison processing methods, and these methods will be explained below.

(b) Area comparison method This method calculates the white or black area S ₀ of the reference pattern included in each inspection area of the reference image and the white or black area S 0 of the inspection pattern included in each corresponding inspection area of the inspection image. This method compares the area with the area _S1 , and in this case, the area of the black part of the pattern is usually taken. Then, the absolute value of the difference between the area S ₁ of the reference pattern and the area S ₂ of the pattern to be inspected |S ₁ −S ₂ |
Calculate the deviation d=(|S ₁ - S ₂ |/S ₁ )×100(%) by dividing by the reference pattern area S ₁ ,
The quality of the object to be inspected is determined by comparing this deviation d with a preset allowable deviation d ₀ .

(b) Uniaxial Histogram Comparison Method This method is a method in which the histograms of patterns included in each inspection area in one axis direction, for example, the x-axis direction, are superimposed to see if they match. For example, if the histogram in the x-axis direction of a certain reference pattern is Hxs in FIG. 10, and the histogram in the x-axis direction of the pattern to be inspected is Hx, then both histograms are superimposed with their center position x ₀ aligned, The area sx (area between unmatched parts) between the unmatched parts of both histograms is calculated. Then, divide this sx by the area S of the histogram of the reference pattern, and the deviation d=sx/S×
Calculate 100 (%). This deviation is compared with the allowable deviation to determine whether the object to be inspected is good or bad.

(c) Two-axis direction histogram comparison method In this method, the histogram of the reference pattern and the pattern to be inspected included in each inspection area in the first axis direction (for example, the x-axis direction) is
The area sx between the mismatched parts is calculated by overlapping and comparing them in the same manner as shown in Figure 0, and the area sx between the mismatched parts is calculated in the second axis direction (for example, the y axis) that is at an angle to the first axis of both patterns. The histograms of the direction) are also superimposed and compared in the same way, and the second
The area between the mismatched parts of the axial histogram sy
Calculate. Then, the larger of sx and sy, max (sx, sy), is used as the judgment material, and the deviation d=
Calculate max(sx, sy)/S×100(%).

By comparing histograms in two axial directions that have different orientations, it is possible to detect defects in patterns for which differences do not appear in pattern areas or histograms in only one axis direction, thereby increasing inspection accuracy.

After the deviations of all inspection areas have been calculated, it is determined whether the allowable deviation has already been set (step j in FIG. 7). Since this permissible deviation has not been set at first, the process then proceeds to step k in FIG. 7 and reads out the deviation for each inspection area calculated in step i. Based on this read data, the operator obtains data indicating the range of variation in deviation due to variation in non-defective products (step 1 in FIG. 7). If it is determined that sufficient data has not been obtained to know the variation range of the deviation of non-defective products (step m in FIG. 7), the process returns to step f again and image data of a normal inspection object is captured. Steps g to m are repeated below, and when enough data is obtained to show the range of variation in deviation of non-defective products, the allowable deviation is set for each inspection area based on the obtained data (see Figure 7). step n). Setting of this allowable deviation is performed using the digital switch 24 and write push button switch 25 on the operation panel 1a. After setting the allowable deviation, image data of the object to be inspected is taken in (step o in FIG. 7), and the process returns to step g in FIG. Thereafter, steps h to j are performed in sequence, and in step j, since the allowable deviation has already been set, the process proceeds to step p. step p
The system compares the deviation between the reference pattern and the inspected pattern with the allowable deviation for all inspection areas, and outputs a non-defective signal indicating that the inspected item is non-defective if the deviation is less than the allowable deviation in all inspection areas. (Step q in Figure 7). When this non-defective product signal is output, the non-defective product indicator light 38 on the operation display panel lights up, and the count value displayed on the non-defective product quantity display section 32 of the counter 34 increases by one (step r in FIG. 7). If the deviation in any of the inspection areas is larger than the allowable deviation in step p, a defective product signal indicating that the object to be inspected is defective is output (step s in FIG. 7). When this defective product signal is output, the defective product indicator lamp 39 lights up and the count value of the defective product quantity display section 33 of the counter 34 increases by one (step t in FIG. 7). The count value of the total quantity display section 31 of the counter increases by one each time a non-defective product signal or a defective product signal is output, and displays the total quantity of the inspected objects (step u in FIG. 7). ). Further, when a defective product signal is output, a signal for removing the defective product from the conveyor is outputted as necessary (step v in FIG. 7).

After the non-defective product signal or the signal for removing defective products is output, the process returns to step O, and image data of the next object to be inspected is taken in, and the same inspection as above is repeated.

In the method of the present invention, as described above, the edges of the entire pattern are detected when specifying the inspection area.
At the time of this detection, if even a slight stain in the background is recognized as one pattern, it may become impossible to accurately set the inspection area. In order to avoid this, the detection sensitivity may be set so as to ignore portions smaller than a certain area when detecting the edges of the pattern.

In the method of the present invention, an image is obtained by scanning the object to be inspected with an image sensor, but the image obtained by scanning with the image sensor is a continuous line approximated by discontinuous points or line segments. , resulting in so-called quantization errors. Furthermore, when an image obtained by scanning with an image sensor is binarized, errors occur because gray parts are replaced with white or black. Furthermore, when capturing images of objects being conveyed by a conveyor, it is generally difficult to maintain a constant position at which the image sensor starts scanning. Even if they are the same, microscopically, the same images are not necessarily obtained every time. These errors can be reduced by increasing the number of light-receiving elements and the frequency of the clock pulse of the image sensor to increase the resolution, but increasing the resolution requires a long processing time and is not practical. In order to compensate for these errors without particularly increasing the resolution, the correction amount is set so that the area of the reference pattern or histogram has a certain width, and items that fall within this width are judged as good products. Just do it like this. This correction amount can be set by giving an appropriate range to the allowable deviation value.

Next, referring to FIGS. 11A and 11B,
In the above embodiment, the main part of a flowchart for creating a computer program for comparing a reference pattern and a pattern to be inspected using an area comparison method is shown. In FIG. 11A, part a is the process of determining whether or not data has been input to the reference image memory, and part b is the process of loading the data of the reference image into the memory.
Part c determines whether or not the inspection area has already been specified, and if the specification has not been made, the process ends, and if the specification has been made, it instructs to proceed to the next step. It's a process. Part d is a process of creating an x-axis direction histogram of the pattern included in the reference image and detecting the left edge and right edge (both horizontal edges) of the entire pattern included in the reference image from this histogram. Part e is a process in which a y-axis direction histogram is created for at least the upper and lower fixed width portions of the entire pattern included in the reference image, and the upper and lower edges (both ends in the vertical direction) of the pattern are determined from this histogram. Part f is a process of constructing a coordinate system with the lower left corner of the area surrounded by the detected upper, lower, left, and right edges as the origin and the upper right corner as the point (100, 100). The part g has the specified coordinates (X ₁ ,
This is the process of displaying an inspection frame with a designated height and width centered on Y ₁ ) along with the reference image on the TV monitor, and the part h is the process of determining the area of the reference pattern within each inspection area. The part i determines whether the designation of all inspection areas and the calculation of the area of the reference pattern within the inspection area have been completed, and if they have not been completed, the process returns to g, and if they have been completed, the process returns to g. next j
This is the process of instructing the next step. Part j is a process of determining whether or not the setting of the inspection area is appropriate, and if not, proceeding to part k, and if appropriate, proceeding to part l in Figure 11B. be. Part k is a process of correcting the coordinates of the center of the inspection area, the height and width of the inspection frame, and the number of inspection areas, and the operator is instructed to perform this correction. If this correction is to be made, the process returns to the step b and reads the binarized image into the reference image memory again. In FIG. 11B, parts l to q are the process of specifying the inspection area and calculating the area of the pattern to be inspected within the inspection area in the same manner as described above for the pattern to be inspected, where l corresponds to b, and parts m to q q
correspond to d to h, respectively. r is the difference between the area S ₁ of the reference pattern in the inspection area and the area S ₂ of the pattern to be inspected |S ₁ - _{S 2} | is the area S ₁ of the reference pattern
Deviation d = (｜S ₁ − S ₂ ｜ / S ₁ ) × 100 (%)
This is the process of calculating. s determines whether or not all inspection areas have been completed, and if not, returns to part p, and if completed, returns to the next t
This is the process of instructing the user to proceed to the section. The process of t is a process of determining whether or not a pass/fail judgment has been instructed. If a pass/fail judgment has not been instructed, the deviation is displayed and the process ends, and the pass/fail judgment is completed. If there is an instruction to perform , it is instructed to proceed to the next part u. The u part compares the deviation calculated in r with the set tolerance deviation, and if the deviation is larger than the tolerance deviation, outputs a defective product signal and ends the process, and if the deviation is less than the tolerance deviation, the next step is This is the process of instructing to proceed to part v of . Then, the v part determines whether or not the comparison between the deviation and the allowable deviation has been completed for all inspection areas, and if the comparison has not been completed, returns to u, and if the deviation is less than the allowable deviation in all the inspection areas, then This is the process of outputting a non-defective signal and ending the inspection.

In the above explanation, the deviation was calculated by dividing the difference between the area of the standard pattern and the area of the pattern to be inspected by the area of the standard pattern. It is also possible to do so.

Referring now to FIG. 12, various examples of applications of the method of the present invention are illustrated. Figure a shows a case where the inspection target is inspected for printing leakage or stains, and figure b shows a case where a foreign object (in the example shown, a box with different printed characters) is mixed into the line. It is. Figure c also shows inspection of packs such as tablets (lack of tablets, etc.).
Figure d shows a case where the camera is placed horizontally to inspect characters and stains printed on the product. Further, Fig. 4(e) shows a case where an object to be inspected is placed on a turntable T and inspected, and an object such as a bottle or a cylindrical body is inspected. In addition, Fig. 4(f) shows a case where the positional shift of a label affixed to a bottle is inspected.

As described above, according to the present invention, the edges in the horizontal and vertical directions of the entire pattern included in the reference image and the image to be inspected are detected, and the coordinates of the center position of the inspection area are determined based on the detected edges. is determined, the pattern to be inspected can be accurately placed within the inspection area even if the position at which the image of the object to be inspected is shifted slightly, and there is an advantage that an appropriate inspection can be performed at all times. Furthermore, since the inspection area is set by determining the center position and setting an inspection frame around it, it is possible to set an inspection area that includes only a specific pattern to be inspected, no matter what the pattern of the object to be inspected. , inspection accuracy can be improved by inspecting only the necessary parts in detail.

[Brief explanation of the drawing]

1A to 1C are explanatory diagrams showing a state in which an image is divided into a plurality of inspection areas in a conventional automatic pattern inspection method; FIG. 2 is a perspective view showing the appearance of an apparatus for carrying out the method of the present invention; The figure is an explanatory diagram showing a state in which an object to be inspected is imaged by a camera in the method of the present invention, Figure 4 is a circuit diagram showing the configuration of an image sensor used in the method of the present invention, and Figure 5 is a method of the present invention. A block diagram showing a schematic configuration of an apparatus for carrying out the
FIG. 6 is a front view showing the configuration of an operation display panel of an apparatus implementing the present invention, FIG. 7 is a flowchart showing the flow of an embodiment of the present invention, and FIGS. 8 and 9 are a method of the present invention. FIG. 10 is an explanatory diagram illustrating a method of specifying an inspection area in FIG.
1A and 1B are flowcharts for creating a computer program used in the present invention,
Figures 12a to 12f are perspective views showing various applications of the present invention. DESCRIPTION OF SYMBOLS 1... Pattern automatic inspection device main body, 2... Conveyor, 3... Inspected object, 4... Lighting device, 5... Position detection sensor, 6... Camera, 7... Image sensor, u,
d... Vertical edge of the entire pattern included in the image, l, r... Horizontal edge of the entire pattern included in the image, α... Center position of the inspection area, β... Inspection frame.

Claims (1)

[Claims] 1. Images obtained by scanning a reference object and an inspection object with a one-dimensional image sensor are binarized to create a reference image and an inspection image consisting of white or black picture elements. In an automatic pattern inspection method for determining the quality of an object to be inspected by comparing a reference pattern and a to-be-inspected pattern included in the reference image and the to-be-inspected image, respectively, The horizontal and vertical edges of the entire pattern are detected, the coordinates of the center position of the area to be inspected are determined based on the detected edges, and an inspection frame of a predetermined size is set around the center position. and set the area inside the inspection frame as the inspection area,
An automatic pattern inspection method comprising comparing a reference pattern and a pattern to be inspected included in corresponding inspection areas of the reference image and the image to be inspected. 2. To detect the edges in the horizontal and vertical directions of the entire pattern included in the reference image and the image to be inspected, create a horizontal and vertical histogram of the area of the white or black part of the pattern, and 2. The automatic pattern inspection method according to claim 1, wherein the automatic pattern inspection method is carried out by detecting the end of the pattern. 3. The reference pattern and the pattern to be inspected are compared by comparing the areas of white or black portions of the reference pattern and the pattern to be inspected.
Automatic pattern inspection method described in Section. 4. A patent characterized in that the reference pattern and the pattern to be inspected are compared by superimposing and comparing histograms in one axis direction of the areas of the white or black portions of the reference pattern and the pattern to be inspected. An automatic pattern inspection method according to claim 1 or 2. 5 The comparison between the reference pattern and the pattern to be inspected is based on two different areas of the white or black portions of the reference pattern and the pattern to be inspected that are angular to each other.
3. The automatic pattern inspection method according to claim 1, wherein the automatic pattern inspection method is carried out by superimposing and comparing two axial histograms. 6. When the histograms are superimposed and compared, the area between the portions of the superimposed histograms that do not match is calculated, and the area is used as data for determining the quality of the inspected object. An automatic pattern inspection method according to claim 4 or 5.