JPH0518372B2 - - Google Patents

Description

[Detailed Description of the Invention] [Field of Industrial Application] The present invention relates to a method and apparatus for detecting defects in a pattern, and more specifically, a method for inspecting a pattern printed on an IC wiring board, etc., and a method used therefor. related to a device for

[Prior art]

ICs (integrated circuits) are created by screen-printing wiring patterns using conductive ink on ceramic substrates, for example, and stacking multiple layers of these, but as ICs have become more dense and multilayered in recent years, pattern defects inspection has become an important issue.

By the way, the conventional method for inspecting wiring patterns has been to use human visual inspection.
Such a method has problems such as a decrease in the yield of finished products due to oversight of pattern defects and low reliability, and also has low efficiency and productivity.

Therefore, as in JP-A-55-156804 and JP-A-57-210627, a defect-free pattern, that is, an original pattern drawn according to the design, is used as a reference, and the pattern to be inspected is superimposed on it for inspection. The apparatus for determining the surplus and missing parts of the target pattern also performs position correction at the time it is imaging a pre-specified part of the same pattern to be inspected arranged in plurality, as in the invention of JP-A No. 57-34402. Furthermore, as disclosed in Japanese Patent Application Laid-Open No. 168313/1983, the pattern to be inspected is scanned according to the designed pattern data, and if a scanning result different from the pattern data is detected, it is considered as a defect. An apparatus has been proposed that automatically inspects patterns and detects defects using techniques such as the following.

[Problem to be solved by the invention] In the case of an inspection device for an IC mask, since the IC mask is created by etching, the boundaries of the pattern are relatively clear and linear, and the binary values of the pattern to be inspected are It is sufficient to simply compare the image data with a standard pattern that serves as a reference for inspection.

However, when screen printing a wiring pattern on a ceramic substrate, it is inevitable that the boundaries of the pattern will exhibit minute irregularities due to ink bleeding, screen mesh, etc. 156804 and Japanese Patent Application Laid-Open No. 57-210627, it is determined that most of the irregularities at the boundaries of patterns are defects. Therefore, inspection of patterns screen printed on ceramic substrates requires relatively more advanced technology than inspection of IC masks.

In addition, in a method such as JP-A No. 59-168313, in which digitized pattern data given as coordinate data is used as an inspection standard, and this is compared with a binary image of the pattern to be inspected, the pattern data is It is necessary to convert data etc. into pixel format data, and this requires a considerable amount of time, so it is difficult to say that it is practical from the standpoint of real-time inspection.

In addition, since the pattern to be inspected is scanned according to the pattern data converted to pixel format, it is necessary to precisely match the reference position, and a special distance meter is required for this purpose. There are drawbacks such as difficulty in application.

Furthermore, when the invention of JP-A No. 57-34402 is applied to a printed pattern on a ceramic green sheet before firing, position correction is performed over the entire surface of the pattern to be inspected from the perspective of expansion and contraction of the green sheet.
In other words, it is necessary to constantly perform the process as the part being imaged moves. Therefore, a problem arises in that the processing time becomes long and the inspection efficiency decreases. Further, positional correction of the pattern to be inspected is normally performed by appropriately processing an image of the pattern to be inspected captured and inputted by an imaging device, targeting the edge portion of a straight line portion orthogonal to the X-axis and the Y-axis. but,
Depending on the pattern, there may be few straight lines, and in such cases, there is no guarantee that positional correction can be performed freely at any position, and positional correction can only be performed at limited positions.

Furthermore, conventionally, the entire pattern to be inspected on a single sheet is processed at the same slice level (binarization level in the case of binarization). teeth,
Since the underlying color and pattern are transmitted through and input as an image, in order to obtain the optimal binarized image, depending on the inspection position, even within the pattern to be inspected on the same sheet, it is necessary to It is necessary to change the encoding level.

However, in order to store appropriate position information for position correction or binarization level information, etc. with each pattern, these data and the image data of each pattern have different data formats, so they must be the same. It is necessary to store each data as separate data in one memory or in different memories, which causes problems such as an increase in the size of the device and a long time for searching and reading data during actual use.

The present invention has been made in view of the above-mentioned circumstances, and can be used even in patterns with few straight parts without determining as defects the ink bleeding of wiring patterns by screen printing, unevenness of pattern boundaries caused by mesh, etc. Positioning can be easily performed, high-speed processing is possible, and patterns can be easily changed, and the binarization level, position correction method, pattern range (window) for position correction, etc. An object of the present invention is to provide a pattern inspection method and apparatus that can individually set each pattern as a standard for inspection.

[Means for solving problems]

The present invention creates a standard pattern for detecting a missing part and a standard pattern for detecting a protruding part for each part of a pattern to be inspected (unit of field of view of an imaging device) and stores it in a memory. The blank area (synchronization signal area, etc.) when each standard pattern is stored above shows the optimum binarization level for each inspection target area, the range (window) on the pattern for position correction, and its method. etc. are written and stored as control data, and at the time of actual inspection, each standard pattern is read out, and the control data stored in the blank area is also read out to inspect each part.

That is, in the pattern inspection method of the present invention, a standard pattern for detecting protrusions and a standard pattern for detecting missing parts are created by enlarging and reducing the binary image of the inspection reference pattern to a size corresponding to the judgment criterion, and then information about the binarization threshold of the pattern to be inspected, the window coordinates for position correction, and the position correction method necessary for inspection using the standard pattern is stored in the memory when the image of each pattern is stored in the memory. Write in the blank space of , store it in memory, image the pattern to be inspected,
The captured image of the pattern to be inspected is binarized according to the information regarding the binarization threshold, and the position error between each of the two standard patterns stored in the memory and the binarized pattern to be inspected is calculated. The position is corrected in the window area defined by the information on the window coordinates for position correction according to the information on the position correction method, and the images of both standard patterns and the inspection target pattern converted into a binary image are It is characterized by detecting defects in the pattern to be inspected by calculating the logical product of

Further, the pattern inspection device of the present invention is a pattern inspection device that compares a pattern to be inspected with an inspection reference pattern to detect defects thereof, in which a binary image of the inspection reference pattern is enlarged and reduced to a size corresponding to the judgment criterion, respectively. A standard pattern creation device that creates a standard pattern for detecting protrusions and a standard pattern for detecting missing parts, and at least an inspection target necessary for inspection using the standard pattern, both standard patterns created by the standard pattern creation device. A memory for writing and storing information regarding the pattern binarization threshold, window coordinates for position correction, and position correction method in the blank area where each pattern image is stored, and a memory for storing the pattern to be inspected. a movable inspection table on which the inspection table is placed; an imaging device that captures an image of the pattern to be inspected; and a binarizer that binarizes the image of the pattern of the inspection target captured by the imaging device in accordance with the information regarding the binarization threshold value. A digitization circuit converts the positional error between each of the two standard patterns stored in the memory and the pattern to be inspected binarized by the binarization circuit into information regarding the window coordinates for the position correction. means for correcting the position in a window area defined by the method according to the information regarding the position correction method, and performing an inspection by calculating the logical product of each of the images of the two standard patterns and the pattern to be inspected which is converted into a binary image. The present invention is characterized by comprising a defect determination circuit that detects defects in the target pattern.

[Effect]

In the present invention, irregularities at pattern boundaries are not judged as defects, and the position of the pattern to be inspected can be easily adjusted even in patterns with few straight parts.Furthermore, each inspection part of the pattern to be inspected can be individually set in advance. Inspection can be performed under optimal conditions according to the optimal binarization level of the pattern to be inspected, the range (window) on the pattern for position correction, the method thereof, etc.

The storage of this information utilizes the surplus memory for storing standard patterns, allowing for effective use of resources.

〔Example〕

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below based on drawings showing embodiments thereof.

FIG. 1 is a block diagram showing the overall structure of a pattern inspection apparatus according to the present invention. Hereinafter, first, the configuration of the apparatus of the present invention will be explained.

The inspection table 14 is placed horizontally on a base (not shown), and the inspection reference pattern BP or the inspection target pattern DP can be placed on the top surface of the table 14 and moved in two orthogonal directions in the horizontal direction. . That is, the inspection table 14 has a three-layer structure,
A pulse motor 15c fixed to the lowest layer support 141 fixed to the base moves the middle layer Y-direction moving table 143 in the depth direction (hereinafter referred to as the Y-axis direction) in FIG. The pulse motor 15b fixed to the top layer moves the X-direction moving table 142 in the left-right direction in FIG. It is configured to move in each direction. Therefore, the top layer X-direction moving table 142 is connected to the support table 141 fixed on the base.
It is possible to move in both the X and Y axes directions.

Above the examination table 14, a two-dimensional imaging device 1 such as a CCD image sensor or an ITV camera is supported by a base via an appropriate vibration isolator (not shown) with the optical axis of its lens system directed vertically downward. Furthermore, a ring-shaped illumination lamp 1l whose light emitting area is centered on the optical axis of the lens system of the imaging device 1 is fixed, but the height position of the ring-shaped illumination lamp 1l is determined by the lens system of the imaging device 1. The position is such that the light does not directly enter the area.

The imaging signal captured by the imaging device 1 is supplied to the binarization circuit 2 after being corrected for image distortion due to aberrations of the lens system in an image distortion correction circuit (not shown).

The binarization circuit 2 binarizes the image signal provided from the above-described imaging device 1 to create a pattern image. The binarization level at this time, ie, the threshold value, is given from the image processing control circuit 7, which will be described later, but the value is not a constant value and can be changed. The output signal of this binarization circuit 2, ie, the binary image signal, is given to a standard pattern creation circuit 3 and a position correction circuit 6.

The standard pattern creation circuit 3 enlarges and reduces the binary image signal provided from the binarization circuit 2 to create approximate patterns of a standard pattern for detecting protrusions and a standard pattern for detecting missing parts. The creation of a rough pattern by the standard pattern creation circuit 3 is performed as follows. FIG. 2 is an explanatory diagram showing the concept.

First, the inspection reference pattern BP is imaged by the imaging device 1 and converted into a binary image signal by the binarization circuit 2.
An enlarged pattern LP and a reduced pattern SP are created from the above. However, the "enlargement/reduction" at this time is different from optical enlargement/reduction in the usual sense, and is performed by a method as shown in FIG. That is, for example, for a binary pattern represented by a 5×5 matrix of dots 11 to 55 as shown in FIG. 3a, only the dot 33 located at the center is "1" as shown in FIG. 3b. , the other dots are "0", the enlargement process is expressed as a logical sum image of each dot and four dots above, below, left and right of it, and the reduction process is expressed as a logical product image. To explain this with reference to the drawings, in FIG. 3B, the logical sum of the dot 33 and each of the dots 23, 32, 34, and 43 above, below, and to the left and right is "1". Therefore, Figure 3b
The enlarged image is as shown in Fig. 3c. On the other hand, the third
In FIG. b, the logical product of the center dot 33 and each of the dots 23, 32, 34, and 43 above, below, and to the left and right is "0". Therefore, the reduced image of FIG. 3b is all "0".

The general enlarged pattern LP and the reduced pattern SP created by such a method become patterns that can be called thicker lines and thinner lines, respectively, as shown in Fig. 2, but at this stage, they are just rough patterns. It is.

The pattern modification device 4 is used to modify the rough pattern created by the above-mentioned standard pattern creation circuit 3 into standard patterns RLP and RSP for actual pattern inspection. That is, the pattern correction device 4 is equipped with an image monitor, on which the rough pattern created by the standard pattern creation circuit 3 is displayed. The final standard patterns, that is, the standard pattern RLP for detecting protrusions and the standard pattern RSP for detecting missing parts, are created by making the following corrections. Specifically, for example, if the upper wiring pattern of the inspection reference pattern BP in FIG. Make the necessary corrections. The standard pattern RLP created by being corrected by this pattern correction device 4,
The RSP is sent to the position correction setting device 5.

The position correction setting device 5 sets a position correction calculation window for the standard patterns RLP and RSP created as described above. This position correction calculation window is for aligning the standard patterns RLP, RSP and the pattern to be inspected DP, and as shown by the broken lines in Fig. 4a and b, the images of the standard patterns RLP, RSP are It is possible to set it by controlling the cursor on the top. The position correction setting device 5 calculates the address on the image of the position correction calculation window thus set and sends it to the image processing control circuit 7.

The position correction setting device 5 also performs selection and setting of a position correction method, that is, an algorithm for position correction. The position correction algorithm is used for standard pattern inspection in actual pattern inspection.
This is an algorithm for correcting the positional deviation of the image between RP and the pattern to be inspected DP, and for example, one of the following two methods can be selected. The first method is to calculate the average value of the coordinates of the wiring pattern edges on the images of both the inspection reference pattern BP and the pattern to be inspected DP, and correct the position of the pattern to be inspected DP so that the two average values match. The pattern to be inspected DP and the standard pattern RLP,
This is a method to correct the deviation from RSP. Also the second
This method uses a projection histogram of dots of a wiring pattern. Specifically, as shown in FIG. 5, the wiring patterns on the standard patterns RLP and RSP (shown by solid lines) represented as dot matrix images and the wiring pattern on the inspection target pattern DP (shown by broken lines) ) Create a histogram of the dot distribution when projected in both the X-axis and Y-axis directions. Then, the histogram is sliced using a predetermined ratio of peak values as the slice level in each histogram, and the differences ΔX and ΔY between the median values at the slice level are determined. This ΔX and ΔY
Let be the deviation between the two patterns. Therefore, ΔX
The pattern to be inspected so that ΔY and ΔY become 0.
This is a method of correcting the position of the DP to correct the deviation between the two patterns.

The coordinate values of the position correction calculation window and the position correction algorithm thus set by the position correction setting device 5 are sent to the image processing control circuit 7.

During actual pattern inspection, the position correction circuit 6 processes an image of the inspection target pattern DP captured by the imaging device 1 and converted into a binary image by the binarization circuit 2, and performs the above-mentioned position correction. Position correction processing is performed according to the position correction calculation window and position correction algorithm set by the setting device 5.

The image processing control circuit 7 uses standard patterns RLP,
At the time of RSP creation, the above-mentioned position correction calculation window is placed in the blank space such as the part for the synchronization signal on the storage area of each one screen when the standard patterns RLP and RSP are stored in the standard pattern storage device 9 described later. Image pattern data is created in which information such as coordinates, position correction algorithm, and binarization level are written as control parameters. The image pattern data of the standard patterns RLP and RSP in which the control parameters have been written in this way is sent to the standard pattern storage device 9 and stored therein.

On the other hand, at the time of pattern inspection, the above-mentioned control parameters are read from the blank parts of the standard patterns RLP and RSP read from the standard pattern storage device 9 and temporarily stored in the image memory 11, and the binarization circuit 2 and the position correction circuit 6 are operated.

The standard pattern storage device 9 is the image processing control circuit 7
This is a large-capacity memory for storing the image pattern data of the standard patterns RLP and RSP in which the control parameters are written in the blank spaces.
High-speed read processing is possible. FIG. 6 is a schematic diagram of standard pattern data stored in this standard pattern storage device 9. As shown in FIG. This standard pattern data is configured, for example, in the form of a 512 x 512 x 8-bit cube, that is, in a state in which 8 layers of 512 x 512-bit memory planes are stacked, and each layer's 512 x 512-bit memory plane is standard. Used to store one screen of pattern RP. One memory plane, which is a storage area for each screen, is divided into an area AP for storing image pattern data and an area AS for storing a synchronization signal. This area AS is a blank area in which the image itself is not stored, and the above-mentioned control parameters, specifically information such as the coordinates of the position correction calculation window, position correction algorithm, and binarization level, are written in this area. It is rare.

Note that this standard pattern storage device 9 includes:
Instead of a large capacity memory as described above, it is of course also possible to use, for example, a disk memory device connected to a dedicated interface and data bus for transferring image data.

Image memories 10 and 11 are both memories for temporarily storing pattern data, and basically have the same configuration as the standard pattern storage device 9 described above, but their storage capacity is the same as that of one screen. be. The image memory 10 stores an inspection target pattern imaged by the imaging device 1, binarized by the binarization circuit 2, and position-corrected by the position correction circuit 6.
A binary image of DP is stored in the image memory 11, and an image of one of two types of standard patterns read from the standard pattern storage device 9, that is, enlarged and reduced standard patterns RLP and RSP, is selected as necessary. be remembered. The stored contents of both image memories 10 and 11 are provided to a determination circuit 12. The determination circuit 12 compares the stored contents of both image memories 10 and 11, that is, the image of the pattern to be inspected DP and the standard pattern RLP or RSP, to detect defects (missing and/or protruding) in the pattern to be inspected DP. Note that this result is provided to a display device (not shown) and is also recorded in a storage device.

Note that the inspection table control device 13 controls the inspection table 14, more specifically, each pulse motor 15b, 15.
Control c. Further, the control arithmetic unit 8 is in charge of overall control of each of the above-mentioned component circuits and the like.

Here, a method of defect determination processed by the determination circuit 12 will be explained. This is an invention disclosed by the present inventors in Japanese Patent Application No. 60-94353.

That is, in FIG. 2, the aforementioned enlarged pattern LP
is a standard pattern for detecting protrusions RLP, and the reduced pattern SP is a standard pattern for detecting missing parts RSP.

When calculating the logical product of the inverted pattern of the standard pattern RLP for detecting protrusions and the pattern DP to be inspected, an image W ₁ = (= DP∩ ) is obtained.

On the other hand, when calculating the logical product of the standard pattern RSP for missing part detection and the inverted pattern of the pattern DP to be inspected, the image W ₂ (=
RSP∩) is obtained.

The determination circuit 12 detects defects according to the results of such arithmetic processing.

In such processing, the inspection reference pattern
By appropriately setting the enlargement ratio of the standard pattern RLP for detecting protrusions relative to BP or the reduction ratio of the standard pattern RSP for detecting missing parts relative to the inspection reference pattern BP (both specifically expressed as the number of pixels). Even in the inspection of a pattern in which the edge of the pattern exhibits minute irregularities, the irregularities on the edge are not determined to be defects.

Regarding the operation of the apparatus of the present invention configured as described above, the flowchart shown in FIG. 7 shows the procedure for creating standard patterns RLP and RSP, and the flowchart shown in FIG.
This will be explained according to the flowchart shown in the figure.

First, the control arithmetic unit 8 creates traverse data. That is, by setting the coordinates of each inspection target position of the inspection target pattern DP in the control arithmetic unit 8, data for moving the inspection table 14, which is necessary when the imaging device 1 takes an image of the position, is created.

Next, the inspection reference pattern BP is placed on the inspection table 14, and standard patterns RLP and RSP are created.
The control calculation device 8 drives and controls the examination table control device 13 according to the above-mentioned traverse data to control the examination table 14.
While moving the inspection reference pattern BP, the imaging device 1 images each inspection position of the inspection reference pattern BP. The captured image is converted into a binary image by the binarization circuit 2, and the optimum level of the binarization level at this time differs depending on the background of the image, etc., so it is appropriately set via the control arithmetic unit 8. The binarized image of the inspection reference pattern BP is sent to the standard pattern creation circuit 3.

The binary image of the inspection reference pattern BP given to the standard pattern creation circuit 3 is enlarged/reduced using the method shown in FIG. are automatically created as rough standard patterns for detecting missing parts. Further, this rough standard pattern is manually modified using the pattern correction device 4 according to the inspection accuracy, for example, parts that require more rigorous inspection or parts that can be inspected relatively roughly. corrected by intervention. As a result, a standard pattern RLP for detecting a protruding part and a standard pattern RSP for detecting a missing part used for inspecting the pattern DP to be inspected are created.

Standard pattern RLP created in this way,
Window coordinates and a position correction algorithm for position correction calculation are set in the RSP. In other words, during actual inspection, the pattern to be inspected DP and the standard pattern
The window used to correct the positional deviation between RLP and RSP is the standard pattern RLP,
Once set on the RSP image, the position correction setting device 5 calculates the coordinates on the screen.

Next, the image processing control circuit 7 displays the binary level of the standard patterns RLP and RSP, the position on the pattern to be inspected DP, and the window coordinates for position correction calculation in the blank areas of the images of both the created standard patterns RLP and RSP. and position correction algorithm are written and sent to the standard pattern storage device 9.

As described above, the creation of the standard patterns RLP and RSP for one inspection position of the pattern to be inspected DP and the storage of the standard patterns in the standard pattern storage device 9 are completed, so the control calculation device 8 uses the inspection table control device 13 according to the traverse data. The examination table 14 is controlled so that the next examination position is imaged by the imaging device 1.
move. Then, the same process as described above is repeated to create standard patterns RLP and RSP at the inspection position and store them in the standard pattern storage device 9.

In this way, when the standard patterns RLP and RSP for all inspection positions are created for the inspection reference pattern BP for a specific inspection object, each of these standard patterns RLP and RSP and the traverse used to create them are The data are organized together with appropriate codes, such as product numbers, etc. This consolidated data is stored and stored in an external storage device as a unit.

Next, the procedure for actual inspection will be explained.

If the data regarding the inspection object is not stored in the standard pattern storage device 9, it is prepared by loading it from the external storage device into the standard pattern storage device 9.

First, the control calculation device 8 reads the traverse data from the standard pattern storage device 9 to start moving the inspection table 14, and also reads out the standard pattern RLP or RSP at the first inspection position of the inspection object and stores it in the image memory 11. Then, the binarization level, the coordinates of the position correction calculation window, and the position correction algorithm are read from the blank part of the standard pattern RLP or RSP stored in the image memory 11, and the binarization level is read out from the blank part of the standard pattern RLP or RSP. , the coordinates of the position correction calculation window and the position correction algorithm are transferred to the position correction setting device 5. Thereafter, when the inspection table 14 is moved so that the first inspection position of the inspection object is moved to the position where the image is captured by the imaging device 1, the control calculation device 8 causes the imaging device 1 to perform imaging, and the result is obtained. The resulting image signal is converted into a binary image by a binarization circuit 2. The binarization level at this time has already been given.

The image of the pattern to be inspected DP binarized by the binarization circuit 2 is then sent to the position correction circuit 6.
This position correction circuit 6 performs position correction according to the coordinates of the position correction calculation window already given to it and the position correction algorithm, that is, the image of the pattern to be inspected DP and the standard pattern RLP or RSP.
Correction is performed so that the images match in position. The pattern to be inspected after this position correction
The DP image is sent to the image memory 10. and,
The determination circuit 12 calculates the logical product of the image of the standard pattern RLP or RSP stored in the image memory 11 and the image of the pattern to be inspected DP stored in the image memory 10 as described above, thereby determining the pattern to be inspected DP. detect defects in

In this way, when the inspection for one inspection position of the inspection object is completed, the control calculation device 8 moves the inspection table 14 according to the traverse data so that the next inspection position is within the field of view of the imaging device 1, The same process as described above is repeated to perform defect inspection at the inspection position. The above-described defect inspection process is repeated for all inspection positions of one sheet of inspection object.

〔effect〕

As described above, according to the present invention, even within the same pattern to be inspected, pattern defects can be detected under optimal conditions (binarization threshold, reference position for position correction, method thereof, etc.) corresponding to each inspection part. Since inspection can be performed, more accurate pattern inspection is possible than in the past. Since this condition is stored using the surplus memory for storing the standard pattern, resources can be used effectively.

In addition, the standard pattern is created in advance and stored in the storage device, and the inspection is performed by simultaneously reading out the information representing the optimum conditions for the actual inspection, which has also been stored in advance. , pattern inspection can be performed at high speed.

Furthermore, the present invention has excellent effects such as being able to avoid erroneous judgments due to unevenness at pattern boundaries.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the configuration of the device of the present invention;
Figure 2 is a schematic diagram showing the standard pattern creation method and pattern defect detection method, Figure 3 is an explanatory diagram of the method of enlarging/reducing the binary image using logical sum and AND, and Figure 4 is position correction. FIG. 5 is an explanatory diagram of an example of the position correction method. FIG. 6 is a schematic diagram showing the configuration of the storage area of standard pattern data stored in the standard pattern storage device. The figure is a flowchart for explaining the operation of the apparatus of the present invention when creating a standard pattern, and FIG. 8 is a flowchart for explaining the operation of the apparatus of the present invention when inspecting a pattern to be inspected. DESCRIPTION OF SYMBOLS 1... Imaging device, 2... Binarization circuit, 3... Standard pattern creation circuit, 4... Pattern correction device, 5... Position correction setting device, 6... Position correction circuit, 7... Image processing control circuit, 8... Control calculation device , 9... Standard pattern storage device, 10, 11... Image memory, 12... Judgment circuit, 13... Inspection table control device, 14... Inspection table.

Claims (1)

[Scope of Claims] 1. In a pattern inspection method in which a pattern to be inspected is compared with an inspection reference pattern to detect its defects, a protruding image in which a binarized image of the inspection reference pattern is enlarged and reduced to a size corresponding to a determination criterion, respectively. A standard pattern for part detection and a standard pattern for missing part detection are created, and both standard patterns are used to determine the threshold for binarization of the pattern to be inspected, window coordinates for position correction, and position correction required for inspection using the standard patterns. Write information regarding the method into the blank space in the memory when the image of each pattern is stored in the memory, image the pattern to be inspected, and transfer the imaged image of the pattern to be inspected to the above-mentioned image. Binarize according to the information regarding the binarization threshold, and calculate the positional error between each of the two standard patterns stored in the memory and the binarized inspection target pattern with information regarding the window coordinates for position correction. The pattern to be inspected is corrected in accordance with the information regarding the position correction method in the window area defined by A pattern inspection method characterized by detecting defects in. 2. In a pattern inspection device that compares a pattern to be inspected with an inspection reference pattern to detect its defects, a binary image of the inspection reference pattern is enlarged and reduced to a size corresponding to the judgment criterion, respectively, and a standard for protrusion detection is used. A standard pattern creation device that creates a standard pattern for detecting patterns and missing portions, and a threshold value for at least the binarization of the pattern to be inspected that is necessary for inspecting both standard patterns created by the standard pattern creation device using the standard pattern. ,
A memory that writes and stores information regarding the window coordinates for position correction and the position correction method in the blank space where each pattern image is stored, and a movable inspection table on which the pattern to be inspected is placed. an imaging device that images the pattern to be inspected; a binarization circuit that binarizes the image of the pattern to be inspected captured by the imaging device according to information regarding the binarization threshold; The positional error between each of the stored standard patterns and the inspection target pattern binarized by the binarization circuit is calculated in the window area defined by the information regarding the window coordinates for position correction. means for correcting the position according to information regarding the position correction method; and a defect detecting a defect in the pattern to be inspected by calculating a logical product between each of the images of the two standard patterns and the pattern to be inspected which is converted into a binary image. A pattern inspection device comprising: a determination circuit.