JP2000209566A - Image processing check device and its method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce the setting burden on a user by quoting collectively and individually plural processing results of a certain type of processing via another type of processing. SOLUTION: An image check means consisting of an image processor 14 and a CPU 15 carries out the processing of the type set previously and checks an object based on the image data stored in a memory 12. The check means has two types of quoting functions. If a certain type of processing has plural processing results, one of two quoting functions makes another type of processing quote collectively and individually the said plural processing results. Furthermore, this quoting function can set at a time the collective and individual quoting of plural processing results of another type of processing. Meanwhile, another quoting function makes a spread sheet quote plural processing results of a certain type of processing.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing / inspection apparatus and method for use in determining the quality of a product in a production process.

[0002]

2. Description of the Related Art An image processing and inspection apparatus which can perform various visual inspections which have been conventionally performed by relying on the visual sense of a person, accurately, at high speed, and automatically, has recently been used as a production facility such as a factory. Many have been introduced.

FIG. 5 is a schematic configuration diagram of a conventional image processing / inspection apparatus. The image processing / inspection apparatus includes a TV camera 10 having a CCD (solid-state imaging device) for capturing an image of an object to be inspected, An A / D converter 11 for converting an output signal into a digital signal;
Image processing memory 12 and image display memory 1 for storing image data obtained by imaging with a V camera 10
3, an image processing device 14PA and a CPU 15PA that perform a predetermined type of processing using the image data in the memory 12 to perform the inspection of the inspection object, and an inspection result obtained by the image processing devices 14PA and the CPU 15PA. , An output circuit 16 for outputting the LUT (lookup table) 17 and a memory 13 via a D / A converter 18.
And a monitor 19 for displaying an image obtained from the screen on the screen.

[0004] The schematic operation of the image processing / inspection apparatus configured as described above will be described. An image signal obtained by imaging with the TV camera 10 becomes a gray value of a digital signal via an A / D converter 11. Memory 12 in pixel units,
13 is stored.

[0005] The image data stored in the image processing memory 12 is stored in an image processing device 14PA such as an ASIC (application-specific integrated circuit) or a CPU 15 specially designed.
It is accessed from the PA and processed according to the image processing procedure (sequence) preset by the user.

The results processed according to the image processing procedure are used by the CPU 15PA for various numerical operations and condition determinations, and the results of these numerical operations and condition determinations are output to an output circuit 16 (for example, a parallel I / O circuit or It is output to the outside as a test result via a serial I / O circuit).

On the other hand, the image data stored in the image display memory 13 is sent to a monitor 19 via an LUT 17 for calculating a display image from the image data and a D / A converter 18, and is sent to the monitor 19. The image is displayed on the screen. In this image display method, the CPU 15PA simply writes data such as fonts necessary for the information to be displayed in the memory 13, and the information such as characters, numerical values, and figures are displayed on the monitor 19.
It has the advantage that it can be easily displayed on a screen.
In addition to this method, in order to simplify the entire configuration, a method of directly connecting a TV camera to a monitor, characters,
To add and display information such as numerical values and figures,
There is also a method of displaying a signal from a V camera once through an analog circuit and then displaying the signal.

Next, the image processing will be described in more detail. An image processing sequence preset by a user is created by combining some basic image processing (hereinafter referred to as a checker) for each inspection. .

[0009] Generally used checkers are roughly divided into those which process grayscale images from a TV camera based on an image which has been binarized into black and white, and those which process grayscale images from a TV camera as they are. The former is called binary image processing, and the latter is called grayscale image processing.

The binarized image processing includes a window checker for obtaining a white or black area of a designated area in pixel units, a binarized edge detection checker for obtaining an object edge in pixel units, and a And a feature extraction checker that calculates various feature amounts such as the number of objects, the center of gravity of each detected object, the perimeter, and the angle of the principal axis of inertia.

On the other hand, in the gradation image processing, a gradation edge checker for finding an edge of an object, a most similar image is rotated around a set area or a rotation center coordinate using a template image as a reference image registered in advance. And a difference checker that detects a difference between two images and detects a deviation or difference from the result.

Generally, the binarized image processing is relatively simple in processing contents as compared with the grayscale image processing, and therefore has features such as low accuracy but short execution time. Such binarized image processing and grayscale image processing are often properly used depending on the inspection content.

FIG. 6 is a plan view showing the outline of the shape of the inspection object, and FIG. 7 is an explanatory diagram showing an example of the result of processing by the feature extraction checker on the four object inspection objects shown in FIG. However, in FIG. 6, A is the screen of the monitor 19, B is
Indicates a setting area of the feature extraction checker, C indicates a setting area of the matching checker, and D indicates an output coordinate of the matching checker.

A plurality of objects to be inspected (four in this case)
In order to inspect the parts 1 to 4, the number (the total number of lands) of the parts is determined, and the area, the center of gravity X,
When the feature extraction checker is set and executed so as to obtain the angles of Y and the principal axis of inertia, in the example shown in FIG. 6, a measurement result as shown in FIG. 7 is obtained.

In this measurement result, the inclination of each part can be obtained from the angle of the principal axis of inertia, but the orientation of the part cannot be obtained from the angle of the principal axis of inertia. For example, it cannot be determined from the angle of the inertia principal axis whether the projection of the component 1 is facing left or right, or facing up or down.

FIG. 8 is a diagram schematically showing a sequence for accurately obtaining the orientation of each component applicable to the example of FIG.
A conventional method for accurately determining the orientation of each component will be described with reference to FIG.

In the example of the sequence shown in FIG. 8, first, as shown in FIG. 7, the total number of lands is obtained, and then the area of each component, the center of gravity X, Y, and the angle of the principal axis of inertia are obtained by the characteristic extraction checker. (S10).

Next, for each component, the position and rotation of the component are corrected by the position / rotation correction checker using the center of gravity X, Y and the angle of the inertia principal axis (S11 to S1).
4). However, the processing for the parts with land numbers 1 to 4 is performed by the position / rotation correction checkers C1 to C4, respectively.

Next, for each part, the correlation coefficient, output X, Y
And a detection angle are obtained by the rotation matching checker (S15 to S18). However, these land numbers 1
The processing for the components No. to No. 4 is performed by the rotation matching checkers M1 to M4, respectively.

As described above, according to the conventional image processing / inspection apparatus in which various checkers are combined in accordance with the inspection, various visual inspections performed relying on human vision can be performed accurately without human intervention. This can be performed at high speed and automatically.

[0021]

However, the conventional image processing and inspection apparatus as described above has a problem that various settings are very complicated.

That is, since the sequence shown in FIG. 8 is applicable when the number of components to be inspected is four, the sequence is used for an inspection in which the number of components to be inspected is not always four. Cannot be applied. Because, when the number of parts to be inspected is five or more, one set of checkers is insufficient in the four sets of checkers in steps S11 to S18, and a processing result for the fifth part cannot be obtained. Conversely, if the number of components to be inspected is, for example, three, the processing result for executing the set of checkers for the land number 4 cannot be obtained from the feature extraction checker. This is because an error occurs. Therefore, such a method cannot be used when the number of articles included in the inspection target is indefinite, and even when the number of articles included in the inspection target is constant, It is necessary to set and execute the sequence in consideration of the number. For example, when the number of components is one, it is necessary to set and execute a sequence as shown in FIG.

In the sequence shown in FIG. 9, for example, the position
The quote setting of the processing result of the rotation correction checker C1 can be performed at once, but in the sequence shown in the example of FIG.
For each component, the reference setting of the processing result of the position / rotation correction checker for the rotation matching checker must be performed. This is shown in FIG. However, FIG.
FIG. 7B is a diagram showing how the feature extraction checker for the position / rotation correction checker C1 quotes the processing result for the component with the land number 1 and FIG. 9B shows the rotation matching checker M;
FIG. 7C is a diagram showing how the position / rotation correction checker C1 sets a reference to the processing result for the C.1, and FIG. 7C is a diagram showing the processing result of the rotation matching checker M1. Since such quotation setting is performed by the user, the trouble becomes more complicated as the number of articles included in the inspection target increases. If the template image of the matching checker cannot be shared between the checkers, a plurality of the same template images must be registered.

Further, some conventional image processing and inspection apparatuses have a spreadsheet function using a so-called spreadsheet (worksheet). In this type of image processing inspection apparatus, the processing result of the above-described sequence is referred to in a spreadsheet, and a spreadsheet function of the spreadsheet performs numerical calculations and pass / fail determination based on the processing result. FIG. 11 shows how to set the quotation of the processing result by the sequence for the spreadsheet. In the example shown in FIG. 11, the centroids X and Y, which are the processing results of the feature extraction checker, and the correlation function and the detection angle, which are the processing results of the rotation matching checker M1, are cited in the spreadsheet for the part having the land number 1. I have. However, when not only the parts of the land number 1 but also the parts of the land numbers 2 to 4 are quoted in the spreadsheet in the same manner as the parts of the land number 1, FIG.
As can be seen from the above, it is difficult to cite the processing results for such a plurality of parts in a spreadsheet, especially with a common layout.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an image processing / inspection apparatus and a method thereof that can reduce a user's setting burden.

[0026]

According to a first aspect of the present invention, there is provided an image processing / inspection apparatus for capturing an image of an object to be inspected and image data obtained by the image capturing means. A storage unit for storing, an image inspection unit for performing an inspection of the inspection object by performing a predetermined type of processing using image data of the storage unit, and a type of processing result in the inspection. A quoting means for quoting another type of processing, and when there is a plurality of the one type of processing results, collectively and individually quoting the plurality of processing results to the other type of processing; It is provided with.

With this configuration, when there are a plurality of processing results of one type, the plurality of processing results are collectively and individually quoted for other types of processing. The performance does not depend on the number of processing results, and even if the number of processing results fluctuates, it can be handled. Thus, it is not necessary to prepare a sequence for each number of processing results, and it is possible to reduce a user's setting burden.

According to a second aspect of the present invention, there is provided an image processing / inspection apparatus, comprising: an imaging unit for imaging an inspection object; a storage unit for storing image data obtained by the imaging by the imaging unit;
An image inspection unit that performs a predetermined type of process by using the image data of the storage unit to perform an inspection of the inspection target, and in the inspection, converts one type of processing result into another type of processing. When there are a plurality of processing results of the one type, a quoting unit that collectively and individually cites the plurality of processing results to the other type of processing is provided. The collective individual citation of the plurality of processing results for the types of processing can be set at once.

With this configuration, when there are a plurality of processing results of one type, the plurality of processing results are collectively and individually quoted for other types of processing. The performance does not depend on the number of processing results, and even if the number of processing results fluctuates, it can be handled. Thus, it is not necessary to prepare a sequence for each number of processing results, and it is possible to reduce a user's setting burden. In addition, since collective individual citation of a plurality of processing results for other types of processing can be set at once, it is possible to reduce the setting burden on the user.

The image inspection means performs a process of measuring the center of gravity of the object to be inspected and the angle of the principal axis of inertia using the image data, and the citing means performs the process of measuring the center of gravity and the inertia obtained in the process. A configuration may be adopted in which the image inspection means refers to the angle of the main shaft as the position correction amount and the rotation correction amount, respectively. In this configuration, when a plurality of articles are included in the inspection object, the respective angles of the center of gravity and the principal axis of inertia are measured by the image inspection means by the number of the articles, and the plurality of centers of gravity and the inertia are measured. Since the angles of the main shafts are collectively and individually referred to the image inspection means as the position correction amount and the rotation correction amount, the image inspection means uses the position correction amount and the rotation correction amount, and The position and rotation of the article can be corrected. As described above, it is not necessary to prepare a sequence for each number of processing results, and it is possible to reduce the setting burden on the user.

According to a fourth aspect of the present invention, there is provided an image processing / inspection apparatus, comprising: an imaging unit for imaging an inspection object; a storage unit for storing image data obtained by imaging by the imaging unit;
An image inspection means for performing an inspection of the inspection object by performing a preset type of processing by using image data of the storage means, and causing a worksheet to cite all or a part of the processing result in the inspection In the case where there are a plurality of processing results of one type to be referred to in the worksheet, a citation means for collectively and individually referencing the plurality of processing results to the worksheet is provided.

In this configuration, when there are a plurality of processing results of one type to be quoted in the worksheet, these plurality of processing results are collectively and individually quoted in the worksheet. Is no longer dependent on the number of processing results, and can be handled even if the number of processing results fluctuates. Accordingly, it is not necessary to prepare a worksheet for each number of processing results, and it is possible to reduce a user's setting burden.

According to a fifth aspect of the present invention, there is provided an image processing / inspection apparatus, comprising: an imaging unit for imaging an inspection target; a storage unit for storing image data obtained by imaging by the imaging unit;
An image inspection means for performing an inspection of the inspection object by performing a preset type of processing by using image data of the storage means, and causing a worksheet to cite all or a part of the processing result in the inspection In the case where there are a plurality of processing results of one type to be referred to in the worksheet, the plurality of processing results can be collectively and individually referred to in the worksheet by quoting means and the worksheet. Output means for outputting a calculation result as a test result.

In this configuration, when there are a plurality of processing results of one type to be quoted on the worksheet, these plurality of processing results are collectively and individually quoted on the worksheet. Is no longer dependent on the number of processing results, and can be handled even if the number of processing results fluctuates. Accordingly, it is not necessary to prepare a worksheet for each number of processing results, and it is possible to reduce a user's setting burden. Further, the calculation result obtained from the worksheet is output as the inspection result.

According to a sixth aspect of the present invention, in the image processing inspection method, an image of the inspection object is captured, and a predetermined type of processing is performed by using image data obtained by the imaging to perform the inspection. The step of performing the inspection, wherein in the inspection, one type of processing result is referred to another type of processing, and when there is a plurality of the one type of processing result, the plurality of processing results Are collectively and individually quoted in the other types of processing.

In this method, when there are a plurality of processing results of one type, these processing results are collectively and individually quoted in other types of processing, so that the once-set validity of the quotation is set. The performance does not depend on the number of processing results, and even if the number of processing results fluctuates, it can be handled. Thus, it is not necessary to prepare a sequence for each number of processing results, and it is possible to reduce a user's setting burden.

According to a seventh aspect of the present invention, there is provided the image processing inspection method, wherein a step of imaging the inspection target and a predetermined type of processing are performed by using image data obtained by the imaging. The step of performing the inspection, wherein in the inspection, one type of processing result is referred to another type of processing, and when there is a plurality of the one type of processing result, the plurality of processing results Are collectively and individually quoted in the other type of processing, and the collective individual quotation of the plurality of processing results for the other type of processing can be set at once.

According to this method, when there are a plurality of processing results of one type, these processing results are collectively and individually quoted for other types of processing, so that the once-set validity The performance does not depend on the number of processing results, and even if the number of processing results fluctuates, it can be handled. Thus, it is not necessary to prepare a sequence for each number of processing results, and it is possible to reduce a user's setting burden. In addition, since collective individual citation of a plurality of processing results for other types of processing can be set at once, it is possible to reduce the setting burden on the user.

According to an eighth aspect of the present invention, there is provided the image processing inspection method, wherein a step of imaging the inspection target and a predetermined type of process are performed by using image data obtained by the imaging. Performing the inspection of the above, wherein all or a part of the processing results in the inspection are cited in a worksheet, and when there are a plurality of one type of processing results cited in the worksheet, Are collectively and individually quoted in the worksheet.

In this method, when there are a plurality of processing results of one type to be quoted in the worksheet, these plurality of processing results are collectively and individually quoted in the worksheet. Is no longer dependent on the number of processing results, and can be handled even if the number of processing results fluctuates. Accordingly, it is not necessary to prepare a worksheet for each number of processing results, and it is possible to reduce a user's setting burden.

According to a ninth aspect of the present invention, there is provided an image processing and inspecting method, wherein an image of an inspection object is captured, and a predetermined type of processing is performed by using image data obtained by the imaging. Performing the inspection of the above, wherein all or a part of the processing results in the inspection are cited in a worksheet, and when there are a plurality of one type of processing results cited in the worksheet, Are collectively and individually quoted in the worksheet, and the calculation results obtained from the worksheet are output as inspection results.

In this method, when there are a plurality of processing results of one type to be quoted on the worksheet, these plurality of processing results are collectively and individually quoted on the worksheet. Is no longer dependent on the number of processing results, and can be handled even if the number of processing results fluctuates. Accordingly, it is not necessary to prepare a worksheet for each number of processing results, and it is possible to reduce a user's setting burden. Further, the calculation result obtained from the worksheet is output as the inspection result.

[0043]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a schematic configuration diagram of an image processing / inspection apparatus according to an embodiment of the present invention. explain.

The image processing / inspection apparatus includes a TV camera (imaging means) 10 having a CCD for imaging an inspection object, and an A for converting an output signal of the TV camera 10 to a digital signal.
A / D converter 11 and a TV via the A / D converter 11
An image processing memory (storage unit) 12 and an image display memory 13 for storing image data obtained by imaging by the camera 10, an image processing apparatus 14 and a CPU (image inspection unit) for inspecting the inspection target. Central processing unit) 15, the image processing unit 14 and the CPU 15
An output circuit (output means) 16 for outputting the inspection result obtained by the above-mentioned method, and a monitor 19 for displaying an image obtained from the memory 13 via the LUT 17 and the D / A converter 18 on a screen.

The image inspection means constituted by the image processing device 14 and the CPU 15 performs a predetermined type of processing using the image data in the memory 12 to inspect the inspection object. It has a type of quoting function (quoting means).

One of these two types of quoting functions is to cause one type of processing result to be referred to another type of processing in the above-described inspection. Then, the plurality of processing results are collectively and individually quoted in other types of processing. In addition, collective individual citation of the plurality of processing results for other types of processing can be set at once.

Another citing function is to cause a part of all the processing results in the above inspection to be cited in a spreadsheet. If there are a plurality of one type of processing results to be cited in the spreadsheet, these plural And have the spreadsheet quote the processing results individually. In the present embodiment, the processing result of the arithmetic function of the spreadsheet is output to the outside via the output circuit 16 as the inspection result.

However, in this embodiment, each checker described later is generated by the image processing device 14 and the spreadsheet is generated by the CPU 15.

FIG. 2 is a diagram showing an outline of a sequence of the image processing / inspection apparatus, FIG. 3 is a diagram showing a state of citation setting between checkers, and FIG. 4 is a diagram showing citation setting of a processing result by each checker to a spreadsheet. With reference to these drawings, the image inspection means constituted by the image processing device 14 and the CPU 15 will be described in further detail with reference to these drawings. However, this image processing and inspection apparatus has been dramatically popularized recently, for example, Windows (registered trademark of Microsoft Corporation in the United States)
GUI (Graphical User Interface) is used.

As shown in FIG. 2, the image inspection means includes a feature extraction checker, a plurality of quotations: a position / rotation correction checker (hereinafter simply referred to as a correction checker), and a plurality of quotations: a rotation matching checker (hereinafter simply referred to as a matching checker). Is used for inspection. However, the sequence of the present image processing and inspection apparatus shown in FIG. 2 can accurately determine the orientation of each component.
Although the sequence is apparently similar to the above sequence, the position / rotation correction checker C1 and the rotation matching checker M1 replace the correction checker and the matching checker, respectively.

The feature extraction checker shown in FIG. 2 is the same as the feature extraction checker shown in FIG. 8, and performs image processing using the image data in the memory 12, and as shown in FIG. In addition to obtaining the total number of lands to be inspected, the area of each component, the center of gravity X, Y, and the angle of the principal axis of inertia are obtained for each component to be inspected. However, the processing result by the feature extraction checker shown in FIG. 3A (measurement result by image processing)
Is executed for the inspection target as shown in FIG.

The correction checker shown in step S2 corrects the position and rotation of the component by using the center of gravity X and Y and the angle of the principal axis of inertia as the position correction amount and the rotation correction amount for each component. At this time, since there are a plurality of processing results of one type, the plurality of processing results are individually and collectively referred to by other types of processing by the above citing function.

For example, in FIG. 3A, since there are four processing results of the type of the center of gravity X, these four processing results are used as the "feature extraction checker: center of gravity X group" of the correction checker.
Are collectively and individually quoted (associated) in the data storage column (cell). At this time, "..." is displayed in the data storage column. When this portion is double-clicked, each value quoted in a pull-down menu format is displayed. Similarly, since there are also four processing results for the center of gravity Y and the principal axis of inertia, the processing results for the center of gravity Y and the principal axis of inertia are also stored in the data storage column of the “feature extraction checker: center of gravity Y group” of the correction checker, respectively. Feature extraction checker: Inertial principal axis group "is collectively and individually quoted in the data storage column.

Here, in the conventional quoting method shown in FIG. 10A, it is necessary to cite and set the processing results of the centers of gravity X and Y and the principal axes of inertia one by one in the position / rotation correction checker. As an example of the quote setting, there is a method of associating a value to be quoted with a designated position of the position / rotation correction checker by dragging and dropping. When quoted this way,
As shown in FIG. 10A, the quoted values are “feature extraction checker: land 1 barycenter X” and “feature extraction checker: land 1 barycenter Y” in the position / rotation correction checker C1.
And "feature extraction checker: land 1 inertia principal axis", and each is associated with a single value.

On the other hand, in the correction checker in which the quoting function according to the present embodiment operates, as shown in FIG. 3A, it is only necessary to associate the heading of the column to be quoted with the designated position of the correction checker by dragging and dropping. , The processing results of that column are collectively and individually quoted to the correction checker.
As a result, all of the processing results obtained for the same type of processing by the feature extraction checker are automatically referred to individually by the correction checker. As a result, as shown in FIG. 3A, the quoted values are, among the correction checkers, “feature extraction checker: centroid X group”, “feature extraction checker: centroid Y group”, and “feature extraction checker: It is expressed as "inertia principal axis group", and a plurality of values are associated with each.

The matching checker shown in step S3 of FIG. 2 rotates the pre-registered template image on the set center coordinates and compares it with the inspection object, thereby determining the degree of coincidence between the inspection object and the template image. The maximum value of the correlation coefficient shown is obtained, and then, in the state where the correlation coefficient becomes maximum, the outputs X and Y are obtained, and the rotation angle of the template image is obtained as the detection angle. In the present embodiment, the center of gravity of each component obtained from the feature extraction checker is set at the center of the center coordinates. At this time, since the correction result of the correction checker is referred to the matching checker based on the plurality of results of the feature extraction checker by the above citing function, matching is performed for each of the position and rotation correction results for the number of components. A checker is automatically generated, and the above processing is repeatedly executed.

As a result, as shown in FIG. 3C, a correlation coefficient, outputs X and Y and a detection angle are obtained for each component. In addition, basically, the result of the matching checker is one. However, since there are a plurality of processing results of the correction checker, the processing by the matching checker is repeatedly performed a plurality of times, and a result corresponding to the number of components of the feature extraction checker is obtained.
Here, it should be noted that the sequences in FIGS. 2 and 9 are apparently the same, and the user can configure the sequences without being conscious of the number of components to be inspected.

When the image inspection means finally obtains the processing result shown in FIG. 3C by the processing of each checker, a part of the whole processing result is automatically converted to a spreadsheet as shown in FIG. Quote

Here, the setting of the processing results by the checkers in FIGS. 4 and 11 to the spreadsheet is similar at first glance, but the setting of the citation shown in FIG. This is different from the quotation setting shown in FIG. 11 in that it is possible to cite a plurality of processing results as a group without being limited to this.

In the present embodiment, for example, as shown in FIG. 4, among the processing results of the feature extraction checker, the headings of the columns of “centroid X” and “centroid Y” which are desired to be quoted are respectively referred to as “features” in the spreadsheet. By dragging and dropping into the “Result” column of “Extraction checkerland barycenter X group” and “Feature extraction checkerland centroid Y group”, a plurality of processing results by the feature extraction checker are quoted and quoted in each column. Is determined by the number of processing results for each processing by the feature extraction checker. As a result, even if the number of articles to be inspected is indeterminate, inspection omissions, errors, and the like as in the related art do not occur, and good inspection results can be output. In addition,
Even if the numerical value of the direct processing result is dragged and dropped into the spreadsheet, the single processing result is quoted in the spreadsheet as in the related art.

Similarly, among the processing results of the matching checker, the “correlation coefficient” and “detection angle”
Column headings in the spreadsheet, "Results" of "Correlation coefficient group of rotation matching checker" and "Detection angle group of rotation matching checker"
By dragging and dropping into the columns, a plurality of processing results by the matching checker are quoted in each column, and the number of quoted processing results is determined by the number of processing results for each processing by the matching checker.

However, a plurality of processing results cited in the spreadsheet are displayed as "..." as in FIG.
If you double-click this part, the value of the processing result quoted in the pull-down menu format is displayed.

According to such a quoting function, it is possible to cite not only the above-mentioned checkers but also the processing results of various checkers desired to be quoted in a predetermined column of a spreadsheet.

Next, the spreadsheet generated by the CPU 15 will be described.
When the processing result of each checker performed on the inspection target is quoted, the arithmetic processing is performed by the arithmetic function of the spreadsheet, and the processing result is output to the outside via the output circuit 16 as the inspection result. It is.

In addition, the spreadsheet has a function of allowing a plurality of processing results of the same type to be collectively and individually associated with a single data even when there are a plurality of processing results of the same type. In FIG. 4, for example, four processing results are stored in the “result” column of “the center of gravity X group of the feature extraction checkerland”, and these processing results are represented by a single “upper limit” data. In accordance with the data “0” of “511” and the single “lower limit value”, it is determined individually whether or not each processing result falls within the range of the upper limit value and the lower limit value. The result of the determination is designed to be stored in the column of “determination” of “the center of gravity X group of the feature extraction checkerland”. Since there are a plurality of judgment results, they are displayed as “...”. Double-clicking this portion displays each judgment result in a pull-down menu format.

The spreadsheet has a function capable of citing and calculating various processing results.
For example, in a conventional spreadsheet, a predetermined operation expression can be applied to a single processing result, whereas in the spreadsheet of the present embodiment, a processing result for the same type of processing is obtained. Even if there are a plurality of processing expressions, it is possible to individually and collectively assign a single predetermined arithmetic expression to these processing results. In the example of FIG. 4, the FEx indicating the processing result specified by “the center of gravity X group of the feature extraction checkerland” and “result” is
The calculation formula of x * 10 is applied, and the processing result of the calculation by this calculation formula is stored in the “Result” column of “FEx * 10”. In this case, the following calculation result is stored.

FEx1 * 10 FEx2 * 10 FEx3 * 10 FEx4 * 10 At this time, if there are a plurality of objects to which the arithmetic expression is applied, a plurality of arithmetic results are stored. In addition, a restriction may be provided to prohibit an operation between a plurality of processing results and a single processing result, so that inconsistency does not occur in the operation result by the operation expression.

Further, the spreadsheet of the present embodiment has a function of outputting a desired processing result as an inspection result through a desired interface among the processing results obtained by the calculation function of the spreadsheet. .

That is, a desired interface is entered in the “output destination” column.
If "Serial" and "Parallel" are entered, the inspection result is output via the RS-232C interface and the parallel output port, respectively. In the example of FIG.
The value of “Result” of “FEy” is changed to “PM” via serial.
The result of “determination” of “a” is output to the outside via serial and parallel, and the “result” of “op1” is output to the outside via parallel.

The designation of the processing result desired to be output as the inspection result is performed by setting the processing result desired to be output to “output destination”.
Is performed simply by dragging and dropping the item. When such a designation is made, a black vertical band mark appears on the left side of the column where the processing result desired to be output is stored. It has become.

According to such a spreadsheet, for example, FEy {1} = 103.5, FEy {2} = 153.4, FEy {3} = 311.9, and FEy {3} = 311.9.
y {4} = 330.0, PMa {1} = 1, PMa {2} = 1, PMa {3} = 0, PMa {4} = 1
Is output via serial while
PMa {1} = 1, PMa {2} = 1, PMa {3} = 0, PMa {4} = 1, op1 {1} = 150
Inspection results such as 4, op1 {2} = 4037, op1 {3} = 1732, and op1 {4} = 4263 are output via parallel. However, it is assumed that the determination result is 1 if OK and 0 if NG.

Next, the schematic operation of the image processing / inspection apparatus will be described. First, an image of an object to be inspected is taken by the TV camera 10, and the image data obtained by this imaging is stored in the memory via the A / D converter 11. 12 and 13 are stored.

Next, image processing using the image data in the memory 12 is executed by the feature extraction checker (S
1). Thus, as shown in FIG. 3A, the total number of lands to be inspected is determined, and the area, the center of gravity X, Y, and the principal axis of inertia of each component are determined.

Next, for each component, the position and rotation of the component are corrected by the correction checker using the center of gravity X, Y and the angle of the principal axis of inertia (S2), and thereafter, the processing by the matching checker is executed. As a result, FIG.
As shown in (c), the correlation coefficient, output X, Y
And the detection angle are determined. When the processing result shown in FIG. 3C is finally obtained by the processing of each checker, a part of the entire processing result is automatically cited in the spreadsheet as shown in FIG.

Next, when the processing result of each checker performed on the inspection target is automatically cited in the spreadsheet, the calculation processing is performed by the calculation function of the spreadsheet, and the processing result is used as the inspection result. Output circuit 16
Output to the outside through

On the other hand, the image data stored in the memory 13 is sent to the monitor 19 via the LUT 17 and the D / A converter 18, and the image is displayed on the screen of the monitor 19.

As described above, according to the present embodiment, when there are a plurality of processing results of one type, the plurality of processing results are collectively and individually quoted in another type of processing or spreadsheet. The validity of the quote once set does not depend on the number of processing results, and it is possible to cope with the fluctuation of the number of processing results. This makes it possible to reduce the setting burden on the user. In addition, since collective individual citation of a plurality of processing results for other types of processing can be set at once, it is possible to further reduce the setting burden on the user. Further, by performing a simple output setting using a GUI on the spreadsheet in advance, it becomes possible to output the calculation result obtained by the spreadsheet as an inspection result.

In the present embodiment, the image processing and inspection apparatus is configured to include the image processing apparatus 14 and the CPU 15 as image inspection means in order to improve the processing speed of the CPU 15 and thus the entire apparatus. However, the present invention is not limited to this, and a configuration in which the CPU 15 is provided as the image inspection unit without the image processing device 14 may be used. In this case, each checker is generated by the CPU 15.

In this embodiment, the image processing device 14
Although a part of all the processing results performed in the inspection process by the CPU 15 is cited in the worksheet, the present invention is not limited to this, and a configuration in which all the processing results are cited in the worksheet may be used.

In the example shown in FIG. 3A, the X and Y coordinates (for example, the coordinates of the center of gravity) and the principal axis of inertia of a certain point are cited by the correction checker. , X, and Y coordinates, and position / rotation correction using three points.

In the example shown in FIG. 3B, the processing result of the correction checker is cited by the matching checker. However, such a quoting method is applied to a window checker, an edge checker, and the like. It is possible.

Further, in the example shown in FIG. 4, "centroid X" and "centroid Y" are cited in the spreadsheet. However, "area" and "major axis of inertia" are also cited in the spreadsheet. A configuration may be used.

[0083]

According to the first aspect of the present invention, an image pickup means for picking up an image of an inspection object, a storage means for storing image data obtained by the image pickup by the image pickup means, and utilizing the image data of the storage means. And an image inspection means for performing an inspection of the inspection object by performing a predetermined type of processing, and in the inspection, causing one type of processing result to be referred to another type of processing, When there are a plurality of processing results of one type, a quoting unit that collectively and individually cites the plurality of processing results to the other type of processing is provided, so that a user's setting load can be reduced. become.

According to the second aspect of the present invention, an image pickup means for picking up an image of an inspection object, a storage means for storing image data obtained by the image pickup by the image pickup means, and an image data stored in the storage means. An image inspection means for performing an inspection of the inspection object by performing a predetermined type of processing, and causing the one type of processing result to be referred to another type of processing in the inspection; When there are a plurality of types of processing results, a citation unit for collectively and individually quoting the plurality of processing results to the other type of processing is provided. Since the collective individual citation can be set at one time, the setting burden on the user can be further reduced.

According to the third aspect of the present invention, the image inspection means performs a process of measuring the center of gravity of the object to be inspected and the angle of the principal axis of inertia using the image data. Since the angle of the center of gravity and the angle of the principal axis of inertia obtained in the processing are referred to the image inspection means as the position correction amount and the rotation correction amount, respectively, it is possible to reduce the setting burden on the user.

According to the fourth aspect of the present invention, the image pickup means for picking up an image of the inspection object, the storage means for storing image data obtained by the image pickup by the image pickup means, and the image data in the storage means are utilized. Image inspection means for performing an inspection of the inspection object by performing a predetermined type of processing, and causing the worksheet to cite all or a part of the processing result in the inspection, When there are a plurality of processing results of one type, a quoting unit that collectively and individually cites the plurality of processing results in the worksheet is provided, so that it is possible to reduce the setting burden on the user.

According to the fifth aspect of the present invention, an image pickup means for picking up an image of an inspection object, a storage means for storing image data obtained by the image pickup by the image pickup means, and an image data stored in the storage means. Image inspection means for performing an inspection of the inspection object by performing a predetermined type of processing, and causing the worksheet to cite all or a part of the processing result in the inspection, When there are a plurality of processing results of one type, a quoting unit that collectively and individually cites the plurality of processing results in the worksheet, and an output unit that outputs a calculation result obtained by the worksheet as an inspection result This makes it possible to reduce the setting burden on the user, and outputs the calculation results obtained from the worksheet to the outside as inspection results. It becomes possible.

According to the sixth aspect of the present invention, the step of imaging the inspection object and the processing of a predetermined type are performed by using the image data obtained by the imaging to inspect the inspection object. Performing a step, wherein in the inspection, one type of processing result is referred to another type of processing, and when there is a plurality of the one type of processing result, Are collectively and individually quoted in the types of processing, so that the setting burden on the user can be reduced.

According to the seventh aspect of the present invention, the step of imaging the inspection object and the processing of a predetermined type are performed by using the image data obtained by the imaging to inspect the inspection object. Performing a step, wherein in the inspection, one type of processing result is referred to another type of processing, and when there is a plurality of the one type of processing result, Is collectively and individually quoted in the type of processing, and the collective individual quotation of the plurality of processing results for the other type of processing can be set at once, so that the setting burden on the user can be further reduced. Will be possible.

According to the eighth aspect of the present invention, the step of imaging the inspection target and the processing of a predetermined type are performed by using the image data obtained by the imaging to inspect the inspection target. Performing all of or part of the processing results in the inspection is cited in a worksheet, and when there are a plurality of one type of processing results cited in the worksheet, the plurality of processing results Are collectively and individually quoted in the worksheet, so that the setting burden on the user can be reduced.

According to the ninth aspect of the present invention, the step of imaging the inspection object and the processing of a predetermined type are performed by using the image data obtained by the imaging to inspect the inspection object. Performing all of or part of the processing results in the inspection is cited in a worksheet, and when there are a plurality of one type of processing results cited in the worksheet, the plurality of processing results Are collectively quoted individually in the worksheet, and the calculation result obtained by the worksheet is output as an inspection result, so that it is possible to reduce a user's setting load and to obtain the calculation obtained by the worksheet. The result can be output to the outside as an inspection result.

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram of an image processing inspection apparatus according to an embodiment of the present invention.

FIG. 2 is a diagram schematically illustrating a sequence of the image processing inspection apparatus according to the embodiment.

FIG. 3 is a diagram showing a state of setting quotes between checkers in the embodiment.

FIG. 4 is a diagram showing how a check result is set in a spreadsheet by each checker in the embodiment.

FIG. 5 is a schematic configuration diagram of a conventional image processing inspection apparatus.

FIG. 6 is a plan view schematically showing a shape of an inspection target.

FIG. 7 is an explanatory diagram illustrating an example of a processing result of a feature extraction checker for an inspection target of four components illustrated in FIG. 6;

8 is a diagram schematically showing a conventional sequence for accurately obtaining the orientation of each component applicable to the example of FIG.

FIG. 9 is a diagram schematically illustrating a conventional sequence for accurately determining the direction of one component.

FIG. 10 is a diagram showing a state of citation setting between checkers in the conventional image processing inspection apparatus shown in FIG.

FIG. 11 is a diagram showing how a check result is set to a spreadsheet by a checker in the conventional image processing and inspection apparatus shown in FIG.

[Explanation of symbols]

 Reference Signs List 10 TV camera 11 A / D converter 12, 13 Memory 14 Image processing device 15 CPU 16 Output circuit 17 LUT 18 D / A converter 19 Monitor

 ────────────────────────────────────────────────── ─── Continuing on the front page (72) Inventor Yuji Torimaru 1048 Kazuma Kadoma, Kadoma City, Osaka Prefecture Matsushita Electric Works F-term (reference) 5C052 AA17 DD08 GA01 GA03 GA09 GB01 GC00 GD03 5C054 CC03 FC01 FC05 FC15 FC16 GA04 GB01 GB12 HA05

Claims (9)

[Claims] An imaging unit configured to capture an image of an inspection target; a storage unit configured to store image data obtained by the imaging unit; and a preset type of process using the image data stored in the storage unit. Image inspection means for performing an inspection of the inspection object by performing the above-mentioned inspection, wherein in the inspection, one type of processing result is cited to another type of processing, and there is a plurality of the one type of processing result. An image processing / inspection apparatus comprising: a quoting unit that collectively and individually cites the plurality of processing results to the other type of processing. 2. An image pickup unit for picking up an image of an inspection object, a storage unit for storing image data obtained by the image pickup by the image pickup unit, and a preset type of processing using the image data of the storage unit Image inspection means for performing an inspection of the inspection object by performing the above-mentioned inspection, wherein in the inspection, one type of processing result is cited to another type of processing, and there is a plurality of the one type of processing result. Includes a quoting unit that collectively and individually cites the plurality of processing results to the other type of processing, and the collective individual quoting of the plurality of processing results for the other type of processing can be set at once. Image processing and inspection equipment. 3. The image inspection means performs a process of measuring the center of gravity of the object to be inspected and the angle of the principal axis of inertia using the image data, and the citing means performs the process of measuring the center of gravity and the inertia obtained in the process. 3. The image processing / inspection apparatus according to claim 1, wherein the image inspection means is configured to quote the angle of the main shaft as a position correction amount and a rotation correction amount, respectively. 4. An image pickup unit for picking up an image of an inspection target, a storage unit for storing image data obtained by the image pickup unit, and a preset type of processing using the image data of the storage unit Image inspection means for performing the inspection of the inspection object by performing the above-mentioned inspection, and causing all or a part of the processing results in the inspection to be cited in a worksheet, wherein one type of processing result to be cited in the worksheet is plural. In some cases, the image processing inspection apparatus includes a quoting unit that collectively and individually cites the plurality of processing results in the worksheet. 5. An image pickup unit for picking up an image of an inspection object, a storage unit for storing image data obtained by the image pickup by the image pickup unit, and a preset type of processing using the image data of the storage unit Image inspection means for performing the inspection of the inspection object by performing the above-mentioned inspection, and causing all or a part of the processing results in the inspection to be cited in a worksheet, wherein one type of processing result to be cited in the worksheet is plural. In some cases, the image processing inspection apparatus includes a quoting unit that collectively and individually cites the plurality of processing results in the worksheet, and an output unit that outputs a calculation result obtained from the worksheet as an inspection result. 6. The method according to claim 1, further comprising a step of imaging the inspection target, and a step of performing a preset type of processing using the image data obtained by the imaging to inspect the inspection target. In the above, one type of processing result is referred to another type of processing, and when there is a plurality of the one type of processing result, the plurality of processing results are collectively included in the other type of processing. Image processing inspection method individually cited. 7. The method according to claim 1, further comprising a step of imaging the inspection target, and a step of performing a predetermined type of processing using the image data obtained by the imaging to inspect the inspection target. In the above, one type of processing result is referred to another type of processing, and when there is a plurality of the one type of processing result, the plurality of processing results are collectively included in the other type of processing. An image processing inspection method which is individually cited, and wherein collective individual citation of the plurality of processing results for the other type of processing can be set at one time. 8. An imaging method for an inspection object, comprising: performing a predetermined type of processing using the image data obtained by the imaging to inspect the inspection object; All or a part of the processing results in are quoted in a worksheet, and when there is a plurality of one type of processing result cited in the worksheet, these plurality of processing results are collectively written in the worksheet. Image processing inspection method individually cited. 9. The method according to claim 1, further comprising the steps of: imaging the inspection target; and performing a predetermined type of processing using the image data obtained by the imaging to inspect the inspection target. All or a part of the processing results in are quoted in a worksheet, and when there is a plurality of one type of processing result cited in the worksheet, these plurality of processing results are collectively written in the worksheet. An image processing / inspection method which is individually cited and outputs a calculation result obtained by the worksheet as an inspection result.