JPS6210838Y2 - - Google Patents

Description

[Detailed Description of the Invention] The present invention relates to an apparatus for automatically inspecting two-dimensional patterns using a computer.

In general, on the production line, there may be problems such as product appearance (shape, dimensions, scratches, etc.), misalignment of labels attached to products, mistakes, stains, or omissions of characters or symbols printed on labels or packaging boxes, etc. Furthermore, it is necessary to inspect for foreign substances mixed in on the line. Conventionally, in order to perform this type of inspection automatically, a camera with a built-in one-dimensional image sensor captures images of a reference object and an object to be inspected to obtain a reference image and an image to be inspected. Various automatic pattern inspection apparatuses have been proposed that determine the quality of an object to be inspected by comparing patterns included in the images. In this type of device, when comparing a reference image and an image to be inspected, in many cases, rather than comparing both images as they are, at least one inspection area is set in both images and the corresponding inspection is performed. A method is used to compare the reference pattern and the pattern to be inspected included within the area. In this case, the reference pattern and the pattern to be inspected are compared for each inspection area, and if there is even one inspection area in which the deviation exceeds the allowable value, the object to be inspected is determined to be defective. By setting the inspection area in the image in this way, only the necessary portions can be inspected in detail, so it is possible to more clearly determine whether the pattern of the object to be inspected is good or bad. However, with conventional equipment, it was difficult to set the allowable deviation value for each inspection area, so in most cases a common allowable deviation value was set for all inspection areas, but in this case, it was difficult to set the allowable deviation value for each inspection area. It was difficult to set acceptable tolerances. Also, since the tolerance between the reference pattern and the pattern to be inspected varies depending on the pattern, if a common tolerance is set for all inspection areas,
There is a risk that some inspection areas will be judged more strictly than necessary and some inspection areas will be judged too leniently, making it difficult to perform an appropriate inspection. Furthermore, with conventional equipment, it was not possible to read the deviation for each inspection area, so if a pattern was determined to be defective, it was not possible to know which inspection area's pattern was defective, and it was difficult to investigate the cause of the defect. I couldn't do it.

An object of the present invention is to provide an automatic pattern inspection device that can set different allowable deviations for each inspection area and also read out the deviations of each inspection area.

The apparatus of the present invention will be explained in detail below with reference to the illustrated embodiments.

FIG. 1 schematically shows the configuration of the inspection device of the present invention. In the figure, 1 is the main body of the automatic pattern inspection device, 2 is a conveyor for conveying the objects to be inspected 3, 3, etc., and 4 is the inspection device. A lighting device is connected to the power supply in the apparatus main body 1 via the cord _L1 to illuminate the object to be inspected 3 at the inspection position, and 5 is a position detection sensor connected to the inspection apparatus main body 1 via the cord _L2 . It is. The position detection sensor 5 consists of a light emitter 5a and a light receiver 5b which are arranged opposite to each other with the conveyor 2 in between. When the object to be inspected 3 comes to the inspection position, the edge of the object to be inspected 3 is detected, and the light receiver 5b detects the position. Generates a 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.
As shown in Fig. 2, the one-dimensional image sensor 7
, 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 D _P and a scanning circuit of a MOS shift register on a single silicon substrate. This is what I did. Figure 3 shows the equivalent circuit of this image sensor. In the figure, D _P is the photodiode arranged in a row on the light receiving surface, C is the capacitance connected in parallel to each photodiode D _P , and D is the 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. That is, the signal is proportional to the amount of incident light flux, and a signal proportional to the amount of incident light flux is extracted as a video signal output _EV in the form of a continuous pulse train. 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.
If the shift register SR is moved in the direction of the arrow X perpendicular to , and a clock pulse of a constant period is 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, the total number of picture elements in one field is 256×64.

Referring to FIG. 4, the electrical configuration of the automatic pattern inspection apparatus of the present invention is shown in a block diagram, and FIG.
The configuration is shown. The peak value of each pulse of the video signal E _V obtained from the image sensor 7 is proportional to the brightness and darkness of each picture element. This image sensor 7
The signal obtained from this is input to the binarization circuit 11, as shown in FIG. The binarization circuit 11 converts each pulse of the video signal _EV into a white or black signal depending on whether its peak value is below or above a certain threshhold level. The image represented by the video signal E _V ' obtained at the output side of the binarization circuit 11 is a binarized 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 for storing reference images.
, a test image memory (RAM) 16 for storing the test image, a calculation memory (RAM) 17 for use in performing calculations for comparing both images, and a program. A program memory (ROM) 18 is provided, and the reference image and inspected image stored in the reference image memory 15 and inspected image memory 16 are connected to a video signal generation circuit 19 and a blanking circuit (where the image in the memory is input). A circuit for erasing the part corresponding to the unlit address from the screen) 20 through the operation panel 1a
The images are displayed vertically side by side on a monitor television receiver 21 installed in the .

The operation panel 1a also includes an inspection area setting method changeover switch 2 for changing the inspection area setting method.
2, a comparison processing method switching switch 23 that switches the processing method when comparing the reference image and the inspected image, and an allowable deviation setting digital switch 24 that sets the allowable value of the deviation between the reference pattern and the inspected pattern. , a deviation writing pushbutton switch 25 that instructs to write the deviation, an inspection area setting digital switch 26 that specifies the position and size of the inspection area to be set on the image, and a deviation reading pushbutton switch 26 that instructs the reading of the deviation. button switch 27, and digital switch 26 when push button switch 27 is pressed.
A digital display 28 consisting of a light emitting diode (LED) is provided to display the deviation of the area specified by the inspection area setting method changeover switch 22 and a comparison processing method changeover switch 2.
3. The contents of the instructions given by the digital switch 24 for setting the allowable deviation, the push button switch 25 for writing the deviation, and the digital switch 26 for setting the inspection area are sent to the central processing unit 1 via the input circuit 29.
4 is entered. Further, the digital display 28 for displaying the deviation value is connected to the output circuit 3 in the central processing unit 14.
0, and when the pushbutton switch 27 is pressed, the deviation of the area specified by the digital switch 26 is displayed in %. The operation panel 1a is further equipped with LEDs that display the total quantity inspected, the quantity of non-defective products, and the quantity of defective products.
A counter 34 having displays 31 to 33 is provided, and this counter is connected to the central processing unit 14 via an output circuit 35. counter 3
There is a counter reset button 3 below the display section 4.
6, and a system reset button 37 for clearing the contents of the reference image memory 15 and the image memory 16 to be inspected is provided on the side of this button. Further, above the display of the counter 34, a good product indicator light 38 and a defective product indicator light 39 are provided, which turn on when the object to be inspected is a good product and a defective product, respectively. A push button switch 40 for starting the conveyor 2 and a push button switch 41 for stopping the conveyor 2 are provided below. 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, the flow of automatic pattern inspection carried out by the above-mentioned apparatus will be explained according to the flowchart of FIG. In the following description, the scanning direction of the image sensor (vertical direction of the screen) is assumed to be the y-axis direction, and the moving direction of the conveyor 2 (horizontal direction of the screen) is assumed to 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, it is determined how to define the inspection area according to the pattern of the object to be inspected (step a in FIG. 6).

That is, in order to improve inspection accuracy, instead of comparing the reference image and the image to be inspected as they are, inspection areas are set in both images and patterns are compared for each inspection area. In this embodiment, both horizontal edges or both horizontal edges and vertical edges of the entire pattern included in the image are detected, and an inspection area is set based on the detected edges. By detecting the edge of the entire pattern and determining the position of the inspection area based on the detected edge in this way, even if the position at which the image of the object to be inspected is slightly shifted, the inspection area will always be accurately aligned with the reference image. Since the image to be inspected can be made to correspond to the inspection area, inspection accuracy can be improved.

In this embodiment, by switching the inspection area setting method changeover switch 22, the inspection area can be set using the following three methods.

(b) Automatic segmentation method This method inspects a pattern to be inspected in which individual unit patterns such as letters A, B, and C are arranged at intervals, as shown in Figure 7a. In this case, the left end L and right end R (horizontal ends) of each unit pattern are respectively detected, and the area between the left end and right end of each unit pattern is set as the inspection area. In the illustrated example, with this method, the area between the left edge L and the right edge R of the entire pattern is divided into five areas b ₁ to
Three areas b ₁ , b _{3 , and} b ₅ are set as inspection areas. Note that this method cannot be applied when the patterns are continuous because the leading and trailing ends of the unit pattern cannot be detected.

(b) Specified division method This method uses the captured image (the image displayed on the monitor TV) as shown in Figure 8a.
In this method, the left end L and right end R of the pattern to be inspected are detected, and the area between the left end L and right end R is divided into an appropriate number of parts at specified positions.
In the illustrated example, the area between the left end L and right end R of the pattern is the part between letters A and B, b ₁ and b ₂
The test area is divided into two areas, and both of these areas are used as inspection areas. The division position can be specified by the digital switch 26, with the left end of the entire pattern included in the image being 0% and the right end being 100%. In the example shown in FIG. 8a, the dividing position between areas b ₁ and b ₂ is specified at a position 30% from the left end of the pattern. This division method is suitable when the pattern to be inspected is a continuous figure or pattern, and the inspection importance of some parts is high.If the area of the area of high importance is set small, the area can be examined in particular detail. In the example shown in FIG. 8a, region b ₁ can be examined more closely than region b ₂ .

(c) Constant division method This division method is a method in which the area between the left end L and right end R of the entire pattern to be inspected is equally divided into a predetermined number of divisions, and the division position is 0% from the left end of the pattern. is specified as a percentage according to the number of divisions. In the example shown in FIG. 9a, the area between the left and right ends of the pattern is divided into four inspection areas b ₁ to b ₄ at 25%, 50%, and 75% positions.

After setting the division method as described above, the pattern comparison processing method is determined (step b in FIG. 6). In this example, when comparing the reference pattern and the pattern to be inspected included in each inspection area, two methods are used: a method that compares histograms in one axis direction (hereinafter referred to as the one-axis method), and a method that compares histograms in one axis direction (hereinafter referred to as the one-axis method). It is possible to select between a method of comparing histograms (hereinafter referred to as the two-axis method) and a method of comparing the areas of patterns included in the reference image and the image to be inspected (hereinafter referred to as the area comparison method). The pattern comparison method is set by switching the comparison processing method changeover switch 23 to "one-axis method,""two-axismethod," or "area comparison method," and the command given by this switch is applied to the input circuit. The signal is input to the CPU 14 through 29. CPU1
4 performs pattern comparison processing using a method set by a predetermined program as described later.

After determining the pattern comparison processing method, the conveyor 2 is started to image an object to be used as a reference for inspection (reference object), and data of the reference image is captured (step c in FIG. 6). This data acquisition starts at the same time as the position detection sensor 5 generates a signal, and ends when 256 scans have been performed. The image obtained from the camera 6 is the binarization circuit 1
1 is converted into a binary image consisting of black or white picture elements, and this binary image I is displayed on the monitor television 21.
is displayed at the top of the screen (step d in Figure 6). Next, the operator looks at this image on the television screen and determines whether it is suitable as a reference image (step e in FIG. 6). If the reference image is inappropriate, take necessary measures such as changing the reference object or adjusting the lighting conditions, and then import the reference image data again (steps in Figure 6). f). If the reference image displayed on the monitor television 21 is appropriate, one of the objects to be inspected that appears to be normal is placed on the conveyor 2, and its image data is captured in the same manner as described above. This normal test object 2
The digitized image is displayed at the bottom of the screen of the monitor television 21 (step g in FIG. 6). 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 output of the position detection sensor that occurs first after the system reset switch 37 is pressed is stored as a reference image in the reference image memory 15, and the image that is obtained by starting scanning based on the output of the position detection sensor that occurs after that is stored as a reference image. The image obtained by starting scanning with the output is stored as the image to be inspected in the image memory 16 to be inspected.
is memorized. 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. Swap images.

Next, the CPU 14 detects the left and right edges of the pattern to be inspected (for example, three letters of ABC) from each of the binarized reference image and the image to be inspected, and specifies the inspection area using the specified method. (Step h in Figure 6). When setting this inspection area, the left end and right end of the pattern are detected using a histogram of the area of the pattern created in the x-axis direction of the binarized image. For example, when performing automatic division, for a binarized image as shown in FIG. 7a, x-axis direction histograms of the area of each unit pattern H _x1 , H _x2 and H _x as shown in FIG.
Create ₃ . In this case, the area of the pattern can be calculated by taking the area of the white part or by taking the area of the black part, but except for special cases where a pattern of white characters appears on a black background. It is preferable to take the black area. After creating a histogram as shown in FIG. 7b, the leading edge L and trailing edge R of the histograms H _x1 , H _x2 and H _x3 are detected, and the area to be inspected is determined as the inspection area b ₁ ,
Divide into b ₃ and b ₅ . In addition, in the case of specified division,
As shown in Figure 8b, the left end L of the histogram H _x1
and the right edge R of the histogram H _x3 , and divides the area between the left edge L and the right edge R into inspection areas b ₁ and b ₂ at a specified position with the left edge L as a reference. Similarly, in the case of fixed division, the left end L of the histogram H _x1 and the right end R of the histogram H _x3 are detected and the area between the left end L and the right end R is divided into four equal parts, as shown in FIG. do.

The above histogram can be created by counting the number of black pulses from the output of the binarization circuit, or by counting the addresses storing black picture elements from the contents of the reference image memory and the image memory to be inspected. It can be created by

After setting the inspection area, the CPU 14 compares the reference pattern and the pattern to be inspected for each inspection area using the 1-axis method, 2-axis method, or area comparison method according to a predetermined program (step i in FIG. 6). ). Next, this comparison processing method will be explained with reference to FIGS. 11 to 13.

First, when performing comparison processing using the uniaxial method, histograms of the areas of patterns included in each inspection area of the reference image and the image to be inspected in one axis direction are compared. In this example, an x-axis direction histogram has already been created in order to divide the image.
Compare the axial histograms for each inspection area.
In addition, when using the two-axis method, a histogram in the y-axis direction is also created, and both the histograms in the x-axis direction and the y-axis direction are compared. FIG. 10 shows histograms H _x and H _y in the x-axis direction and y-axis direction, taking as an example the case where the inspection area includes the character A.

When comparing the histograms of each inspection area of the reference image and the image to be inspected, two
The two histograms are overlapped by aligning their centers, and the area between the areas where the two histograms do not match is calculated. For example, when the x-axis direction histogram _Hxs of the reference pattern included in a certain inspection area of the reference image is as shown in FIG. Directional histogram H _x
If the histograms are as shown in figure b, then to compare these histograms, superimpose the center position x ₀ of both histograms as shown in figure c, and then compare (area of the shaded part in Figure 11c,
Hereinafter, it will be referred to as the area between the mismatched parts. ) Calculate s _x .
In the present invention, this area s _x is used as the degree of difference between the two histograms H _xs and H _x (that is, the degree of difference between the reference pattern and the pattern to be inspected) and is used as data for determining pass/fail.
To make a pass/fail judgment using the uniaxial method, for example, divide this area s _x by the total area S of the x-axis direction histogram H _xs of the reference pattern, and calculate the deviation d _x = (s _x /
S)×100(%), set the deviation d _x in advance, and compare it with the allowable deviation d ₀ .

When comparing using the two-axis method, the y of the reference pattern and the pattern to be inspected is determined in exactly the same way as above.
The axial histograms are superimposed and compared, and the area s _y between the mismatched portions of the histograms of both patterns is calculated as the degree of difference, and this area s _y is also used as data for determination. In this case, for example, the area s indicating the degree of difference in the histograms in the x-axis direction is
Area s _y showing the degree of difference between the histograms in _{the x} and y axis directions
The _deviation d= _{ max( s _x , s _y /S}×100
(%) and compare this deviation d with the allowable deviation d ₀ .

In the above explanation, the deviation is expressed as a percentage by dividing the area between the mismatched portions of the histograms of the reference pattern and the test pattern by the total area of the histogram of the reference pattern, but the mismatch between the histograms of the reference pattern and the test pattern The inter-part areas s _x and s _y themselves may be treated as deviations, and such cases are also included in the present invention. Incidentally, as in the above embodiment, the area between the mismatched portions, s _x ,
When treating s _y divided by the total area S of the reference pattern as a deviation, when using the two-axis method, set a common tolerance for histograms in both the x-axis and y-axis directions. However, if the area between the mismatched parts itself is used as the deviation, x
It is necessary to set allowable deviations in each of the axial and y-axis directions.

By comparing the reference pattern and the pattern to be inspected using the two-axis method, it is possible to determine the quality of the pattern to be inspected, which cannot be determined using the one-axis method. For example, if the reference pattern P _s is as shown in Figure 12a, and the inspected pattern P _i is as shown in Figure 12b, there is a difference between the x-axis direction histograms H _xs and H _x of the two patterns. Although not shown, a clear difference appears in the y-axis direction histograms H _ys and H _y .

When comparing patterns using the area comparison method, count the number of black or white picture elements in the reference pattern and the pattern to be inspected, calculate the black or white area of both patterns, and calculate the calculated area of both patterns. Let the difference be the pattern dissimilarity. Then, a deviation is calculated by dividing this degree of difference by the black or white area of the reference pattern, and this deviation is compared with an allowable deviation. In this case as well, the difference in area between the two patterns itself may be treated as a deviation.

The pattern comparison process described above is performed for each inspection area, and the deviation between the reference pattern and the inspected pattern is calculated for each inspection area (6th
Step j) in the figure.

After the deviations of all inspection areas have been calculated, it is determined whether the allowable deviation has already been set (step k in FIG. 6). Since this permissible deviation is not set at first, the process then proceeds to step 1 in FIG. 6 and reads out the deviation for each inspection area calculated in step j. Based on the read data, the operator obtains data indicating the range of variation in deviation due to variation in non-defective products (step m in FIG. 6). If it is determined that sufficient data has not been obtained to know the range of deviation of non-defective products (step n in Fig. 6), step f is performed again.
Return to , and import the image data of the normal inspected object. The following steps g to n are carried out, and when enough data is obtained to show the range of deviation of non-defective products, the allowable deviation is set for each inspection area based on the obtained data (see Figure 6). Step o). When setting the allowable deviation, specify the test area using the test area setting digital switch 26 on the operation display panel 1a, and set the allowable deviation of the test area using the allowable deviation value setting digital switch 26.
Set by 4. Next, the deviation writing pushbutton switch 25 is pressed to input the data set in the digital switches 26 and 24 to the computer 12, and the allowable deviation value is stored in the computer's memory. The same operation is performed for each inspection area, and the allowable deviation of each inspection area is memorized.

After setting the allowable deviation, import the image data of the object to be inspected (Step P in Figure 6), and
Return to step g in the figure. Thereafter, steps h to k are performed in sequence, and since the allowable deviation has already been set in step k, the process proceeds to step q. In step q, the deviation between the reference pattern and the pattern to be inspected is compared with the allowable deviation for all inspection areas, and if the deviation is less than the allowable deviation in all the inspection areas, a non-defective signal indicating that the inspected object is a good product is issued. is output (step r in FIG. 6). 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 displayed on the non-defective product quantity display section 32 of the counter 34 increases by one (step s in FIG. 6). If the deviation in any of the inspection areas is larger than the allowable deviation in step q, a defect signal indicating that the object to be inspected is defective is output (step t in FIG. 6). 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 u in FIG. 6). 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 v in FIG. 6). ). Further, when a defective product signal is output, a signal for removing the defective product from the conveyor is output (step w in FIG. 6).

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

When collecting data to determine permissible deviations,
When a defective product signal is output, it may be necessary to know the deviation between the reference pattern and the pattern to be inspected in each inspection area. In such a case, in the apparatus of the present invention, by specifying the inspection area whose deviation is required to be known using the inspection area setting digital switch 26 and pressing the deviation reading pushbutton switch 27, the digital display 28 displays the inspection area. The deviation of the area can be displayed.

In the above description, the reference image and the image to be inspected are displayed vertically on the monitor television receiver 21, but it is also possible to display a display indicating each inspection area superimposed on these images.

In the apparatus of the above embodiment, the reference image and the image to be inspected after being binarized are displayed side by side on the monitor television receiver 21, so that it is possible to see the image actually being processed by the computer, and the image to be inspected can be inspected. It is possible to monitor whether or not this is being done appropriately.

In the above embodiment, the digital switch 26 is used as a switch to set the position and size of the inspection area, and the digital switch 24 is used as a switch to set the allowable deviation value. This switch is equipped with a switch dial for each digit and allows the number 0 to 9 of each digit to be set individually, and is widely used in devices that set conditions in digital quantities. However, in the present invention, the inspection area setting switch and the tolerance deviation setting switch provided on the operation display panel 1a are not limited to such digital switches.
It is also possible to use a switch that is provided with pushbuttons corresponding to each number from 0 to 9 and sets the digital amount by sequentially pushing the pushbuttons corresponding to the numbers of each digit, starting from the highest digit. In this case, it is necessary to provide a display to display the set digital quantity. Also, the deviation writing switch and the deviation reading switch are the push button switches 25 and 2 shown in the above embodiment.
7, and a key switch (keyboard type switch) or the like may also be used.

Referring now to FIG. 14, various examples of applications of the apparatus of the present invention are shown. Figure a shows the case of inspecting the object to be inspected for printing leakage or stains, and figure b shows the case of inspecting the line for foreign matter (in the illustrated example, a box with different printed characters). This is the case. Figure c shows a case where a pack of tablets, etc. is inspected (for missing tablets, missing tablets, etc.), and figure d shows a case where the camera is placed horizontally to inspect characters and dirt printed on the product. This is the case. Furthermore, FIG. 5e shows a case where an object to be inspected is placed on a turntable T and is inspected, and an object having a circular cross section, such as a bottle or a cylinder, is inspected. Further, Fig. 5(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, when a plurality of inspection areas are set in the reference image and the image to be inspected, a permissible deviation can be set for each inspection area, so that accurate inspection can be performed. In addition, since the deviation can be read out and displayed for each inspection area, it is possible to accurately set the allowable deviation for each inspection area. It can be used as a reference for quality control by checking whether the product is defective or not.

[Brief explanation of drawings]

FIG. 1 is a perspective view showing the appearance of an embodiment of the present invention, FIG. 2 is an explanatory diagram showing a state in which an object to be inspected is imaged by a camera in the apparatus of the present invention, and FIG.
The figure is a circuit diagram showing the configuration of an image sensor used in the device of the present invention, FIG. 4 is a block diagram showing the schematic configuration of an embodiment of the present invention, and FIG. Front view showing the configuration,
Figure 6 is a flowchart showing the flow of inspection using the device of the present invention, Figures 7a and b are explanatory diagrams explaining how to divide an image by the automatic division method, and Figures 8a and b are by the specified division method. An explanatory diagram explaining how to divide an image, Figures 9a and b are explanatory diagrams explaining how to divide an image by the constant division method, and Figure 10
The figure is an explanatory diagram showing the histogram in the x-axis direction and the y-axis direction of the pattern to be inspected, Figures 11a to 11c are diagrams explaining the method of comparing histograms, and Figures 12a,
13b is an explanatory diagram showing a reference pattern and a pattern to be inspected that can be inspected only by the two-axis method together with a histogram, and FIGS. 13a to 13f are perspective views showing various application examples of the present invention. 1... Main body of automatic pattern inspection device, 2... Conveyor, 3... Object to be inspected, 4... Lighting device, 5
... Position detection sensor, 6 ... Camera, 7 ... Image sensor, 12 ... Computer, 21 ... Monitor TV receiver, 24 ... Digital switch for setting tolerance deviation, 25 ... Push button switch for writing deviation , 26...Digital switch for setting inspection area, 27...Push button switch for reading deviation, 28
...digital display, ...reference image, ...test image.

Claims (1)

[Scope of utility model registration request] A camera that images a reference object and an object to be inspected, and at least one inspection area set in the reference image and the image to be inspected, respectively, obtained by imaging the reference object and the object to be inspected by the camera, respectively. An automatic pattern inspection device comprising: a computer that compares a reference pattern and a pattern to be inspected included in the pattern to calculate a deviation between the two patterns; and an operation panel having switches for giving commands to the computer. The panel includes an inspection area setting switch that digitally sets the inspection area, and a tolerance that digitally sets the allowable deviation between the reference pattern of the inspection area set by the inspection area setting switch and the pattern to be inspected. A deviation setting switch, a digital display, a deviation writing switch for instructing input of the allowable deviation set by the allowable deviation setting switch into the computer, and an inspection set by the inspection area setting switch. An automatic pattern inspection apparatus comprising: a deviation readout switch for instructing the computer to display the deviation between the reference pattern of the area and the pattern to be inspected on the digital display.