JPH10148515A - Apparatus and method for inspection of image - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain an apparatus and a method n which the kind, the generation place and the like of a defect can be investigated easily by a method wherein inspection results, about a plurality of objects to be inspected, which are acquired by an image processing means, are totalized and the necessary part of their statistical result is displayed in a definite form. SOLUTION: Caps 10 as objects to be inspected are conveyed automatically to an imaging region by a CCD camera 11, and they are detected by a sensor so as to be imaged automatically. Image signals on surfaces of the imaged caps 10 are sent sequentially to an image processor 12. Every image signal of every cap 10 is A/D-converted, a noise is removed by an image filter, it is then binarized by a prescribed threshold value, a particle size is measured on the basis of it, and the existence of a defect and its kind are judged on the basis of its result. When the defect is detected, the image signal in the imaging operation of every cap 10 is recorded in an MO disk inside the image processor 12 together with position information. After its processing operation has been finished, an inspection result is displayed on a CRT screen at a computer. In this manner, inspection results of the caps 10 in a plurality are totalized so as to be displayed, and a statistical result can be investigated.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image inspection apparatus and an image inspection method for inspecting the surface of an inspection object for defects by imaging the surface of the inspection object and performing image processing on the image. .

[0002]

2. Description of the Related Art An image inspection apparatus using an image processing method is applied to quality inspection of caps of food and beverage containers. With such an apparatus, a large number of products can be automatically inspected, and the inspection process can be made more efficient. An image inspection apparatus based on this method captures an image of the upper surface of the cap, which is an inspection target, using a CCD camera or the like, digitizes this image signal, and binarizes the image with an appropriate threshold. If there is a defect such as dirt or a flaw on the upper surface of the cap, the defect is displayed as a connected area (hereinafter, also referred to as an “island”) in the binary image. By finding this connection area, the existence of defects is inspected,
The size and shape of the defect can be known from the area (the number of pixels) and the shape of the connection region.

[0003]

By the way, the conventional image inspection apparatus automatically inspects whether there is a defect in the product and what kind of defect the defect is, but the defect is found. In some cases, the product was simply removed from the line. However, if detailed information on the found defects is accumulated, the information can be used as a means for knowing a problem in the manufacturing process.

The present invention has been made based on the above circumstances, and provides an image inspection apparatus which can be used to find a problem in a manufacturing process by using information on a defect found by inspecting a product. The purpose is to do.

[0005]

According to a first aspect of the present invention, there is provided an image inspection apparatus for capturing an image of an object to be inspected, and an image output from the image capturing unit. An image processing unit that performs predetermined image processing on the image signal to inspect for the presence or absence and the type of a defect in the inspection object, and a plurality of inspection objects based on an inspection result obtained by the image processing unit. It is characterized by comprising: an inspection result totalizing means for totalizing inspection results to obtain a statistical result; and an image display means for displaying a required part of the statistical results obtained by the inspection result totaling means in a predetermined format. I do.

According to a fifth aspect of the present invention, there is provided an image inspection method, wherein a predetermined image processing is performed on an image of an inspection object captured by an imaging means to inspect the presence or absence of a defect and the type of the defect in the inspection object. Then, based on the inspection results, the inspection results of the plurality of inspection objects are totaled, and a required part of the statistical results obtained by the totaling is displayed in a predetermined format.

According to the present invention, based on the inspection results obtained by the image processing, the inspection results of a plurality of inspection objects are totaled to obtain a statistical result, and a necessary part of the statistical result is determined by a predetermined part. By displaying in the format, it is possible to easily examine the statistical results, as a result of this review,
Information such as the type of a defect that frequently occurs and where a large number of defects occur in an inspection object can be obtained.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a schematic configuration diagram of the image inspection apparatus of the present embodiment, and FIG. 2 is a flowchart showing a procedure for determining the presence or absence of a defect and its type in the image processing apparatus. The image inspection apparatus according to the present embodiment has an upper surface of a cap of a plastic bottle used as a beverage container,
The inspection is performed for defects such as dirt, flaws, shape defects, and protrusions that may occur in the manufacturing process. As shown in FIG. 1, an image inspection apparatus according to the present embodiment includes a CCD camera 11 for capturing an image of
An image processing device 12 that performs predetermined image processing on an image signal obtained by the camera 11 to determine whether or not there is a defect and its type, and a monitor 1 that displays an image of the upper surface of the cap.
3. The operation of the image processing apparatus 12 is controlled to manage the entire inspection, and the results of the inspections performed in the image processing apparatus 12 are totaled to obtain a statistical result. It comprises a computer 14 capable of referring to detailed contents. The image processing device 12
Has a magneto-optical (MO) disk inside,
Here, the image data of the cap is stored, and the image can be displayed on the monitor 13 as needed.

In FIG. 1, when a cap 10 to be inspected is automatically conveyed to an imaging area of a CCD camera 11, a sensor (not shown) detects this. CCD
The camera 11 starts the imaging operation at the same time as receiving the signal to that effect. In the present embodiment, the caps are transported at a speed of about 1700 caps per minute, and the imaging operation is a high-speed operation corresponding thereto. The CC of the present embodiment
The D camera 11 has an imaging field of view of φ34 mm and a resolution of 0.07.
mm / pic.

Image signals of the upper surface of the cap captured by the CCD camera 11 are sequentially sent to an image processing device 12. The image signal sent to the image processing device 12 is subjected to the following processing for each image signal of each cap. First, an image signal is converted from an analog signal to a digital signal by A / A.
It is D-converted into a digital image signal of, for example, 256 gradations. Then, after noise is removed by the image filter, binarization is performed using a predetermined threshold. Image processing device 1
2 further performs a particle size measurement based on the binarized image signal. Specifically, labeling of the connected region (or “island”), calculation of the number of labeled islands, and calculation of the area value of each island are performed. Here, the area of the island is obtained as the number of pixels constituting the island.

The image processing apparatus 12 determines the presence or absence of a defect and the type of the defect according to the procedure shown in FIG. 2 based on the result of the particle size measurement. In FIG. 2, “calculation of image processing result” in step 1 corresponds to the above-described particle size measurement. When the image processing result is calculated, first, whether the cap is free from dirt (step 2), whether there is any flaw (step 4), whether the cap is not defective (step 6), and whether there is no protrusion (step 8), The determination is made sequentially in this order. If it is determined that there is a defect, the defect is counted according to the type (step 3, step 5, step 7, step 9). If any of these defects is found, the original image of the cap, that is, the image captured by the CCD camera 11 is recorded on the MO disk in the image processing device 12. At this time, information indicating where each defect is found in the cap is also recorded.

On the other hand, if none of "dirt", "flaw", "defective shape", and "projection" is counted (step 10), it is counted as a normal product (step 1).
1). When the above processing is completed, the inspection result is displayed on the CRT screen of the computer 14 (step 12). 3 to 8 are diagrams showing screen configurations for displaying the above inspection results. The above inspection is performed in units of 50 caps per lot. FIG. 3 shows an outline of inspection results of 50 caps of a certain lot, and each number from 1 to 50 corresponds to each cap included in one lot. A hatched number means that a defect was found in the cap corresponding to the number, and on the actual CRT screen, a color (for example, red, blue, yellow, or green) corresponding to each defect was found. 4 colors). If a plurality of types of defects are found for one cap, the color corresponding to the name of the first detected defect is displayed.

In FIG. 3, Nos. 6, 23, 24, 26
Numbers 49 and 49 are shaded to indicate that caps with these numbers have defects. FIG.
In the screen of "TOTAL", the cap is 50
The column of “normal products” indicates that 45 of the 50 caps have no defect and are normal. In addition, "dirt", "flaw", "shape"
Each column of “protrusion” and “projection” indicates that the number of defects of each type found was “dirty” and two other defects, respectively. . To display the inspection results of the lots before and after this lot, the user presses the “F1” key or the “F2” key on the keyboard of the computer 14.

When the number of a cap where a defect is found is selected on the screen shown in FIG. 3, details of the defect found for the cap can be displayed. The number can be selected with a mouse or a cursor. Alternatively, a transparent touch panel may be provided on the surface of the CRT, and the details of the defect may be displayed by simply touching a desired number with a finger.

FIG. 4 shows a screen on which details of the defect of the sixth cap among the 50 inspected caps are displayed. In the screen of FIG. 4, first, the inspection time is displayed in the uppermost column, and the defect name of the defect found for the cap is displayed below the inspection time. On the right side of each defect name, information related to the defect is displayed. That is,
As for “dirt”, the set binarization threshold is 256.
20 of the gradations, and two stains were found. As for “flaw”, the set threshold is 20 gradations, the length of the flaw is two pixels, and the number of flaws is 1
Individual. As for “shape failure”, the set threshold value is 20 gradations, and the degree of deformation is 2%. For the “projections”, the set threshold value is 20 gradations, the angle is 2 °, and the number is “2”. If necessary, an actual image of the sixth cap recorded on the MO disk inside the image processing device 12 is displayed on the monitor 13.
It can also be displayed above.

If more detailed inspection data is required than in FIG. 4, a defect name is selected on the screen of FIG. 4 in the same manner as described above. FIG. 5 shows a screen when "dirt" is selected on the screen of FIG. The screen of FIG. 5 shows, for each of the two found “dirts”, the respective “upper left coordinates”,
Specific numerical values indicating “lower right coordinate”, “center coordinate”, and “area” are displayed. Thus, the position, size, and approximate shape of the dirt can be known. Similar screens can be displayed for other defects by selecting a desired defect type on the screen of FIG.
In the screen of FIG. 5, "upper left coordinate", "lower right coordinate", "center coordinate", and "area" are displayed as an example, but "lower left coordinate" and "upper right coordinate" are also displayed. You may do so.

FIG. 6A is a screen that graphically displays the display contents of FIG. That is, the two dirts shown in FIG. 5 are displayed in such a manner that it is possible to know where and what size and shape the two dirts actually exist on the upper surface of the cap. Then, when No. 1 or No. 2 of “No.” in FIG. 5 is selected, a position display cursor (in FIG. 6B, represented by a “×” mark) on the image of the corresponding defect as shown in FIG. .) Moves. Alternatively, the color of the defective portion may be changed by selecting a number.
When the type of defect is a shape defect, to understand which part is deformed and how much from the original shape,
A portion where a shape defect has occurred may be exaggerated and displayed by superimposing the image on a standard product.

FIG. 7 shows a screen for displaying a statistical result in which the inspection results of a certain number of caps are totaled and summarized. The screen of FIG. 7 shows that there is one defect each of “dirt”, “flaw”, “defective shape”, and “projection”. By looking at this, it is possible to obtain information on what kind of defects are frequently present in the production line. FIG. 8 is an image in which all the found defects (indicated by “x” in FIG. 7) are displayed on the cap by type, based on the statistical results of FIG. With such a display, it is possible to know at which position of the cap the defect has occurred. By this, for example, if it is found that the same type of defect occurs at a specific position of the cap,
It is possible to make predictions that there may be a problem at a specific location in the manufacturing process, which can be used to improve the manufacturing process.

The present invention is not limited to the above embodiment, and various changes can be made within the scope of the invention. In the above embodiment, the present invention is applied to the defect inspection of the upper surface of the cap of the PET bottle, but the inspection object of the present invention is not limited to the cap of the PET bottle, and can be applied to various inspection objects. As an example, if the present invention is applied to a defect inspection of a semiconductor wafer immediately before final shipment after polishing, physical / chemical inspection, etc., a problem in a semiconductor wafer manufacturing process is found and the problem is improved. Can help.

[0020]

As described above, according to the present invention, the inspection results for a plurality of inspection objects are totaled based on the inspection results obtained by the image processing, and the statistical results are obtained. By displaying the necessary parts in a predetermined format, it is possible to easily examine the statistical results, and as a result of this examination, the types of frequently occurring defects and where many defects occur in the inspection object Information such as the time at which the defect occurred, etc., and provide a clue to knowing if there is no problem in the manufacturing process of the inspection target based on this information, and if so, where it is. Thus, it is possible to provide an image inspection apparatus and an image inspection method that are useful for improving a manufacturing process.

[Brief description of the drawings]

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

FIG. 2 is a flowchart showing a procedure for determining the presence or absence of a defect and its type in the image processing apparatus.

FIG. 3 is a diagram showing a screen configuration for displaying inspection results of one lot of caps in the image processing apparatus.

FIG. 4 is a diagram showing a screen configuration for displaying the content of a defect found for a certain cap.

FIG. 5 is a diagram showing a screen configuration for displaying the position and area of a specific type of defect found for a certain cap.

6 is a diagram of a screen in which a specific position of a defect displayed in FIG. 5 is graphically displayed by superimposing a cap image.

FIG. 7 is a diagram showing a screen configuration for displaying statistical results of defects found for a certain number of caps.

FIG. 8 is a diagram of a screen in which a defect occurrence position found by performing on a certain number of caps is superimposed on a cap image and is graphically displayed.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 10 Inspection object (cap) 11 CCD camera 12 Image processing device 13 Monitor 14 Computer

Claims (8)

[Claims] 1. An image pickup means for capturing an image of an inspection object, and an image processing means for performing predetermined image processing on an image signal output from the image pickup means to inspect the presence or absence of a defect in the inspection object and its type. Based on the inspection result obtained by the image processing unit, an inspection result aggregation unit that aggregates the inspection results of the plurality of inspection objects to obtain a statistical result, and a statistical result obtained by the inspection result aggregation unit. An image display means for displaying a necessary part of the image in a predetermined format. 2. The method according to claim 1, wherein the image display unit displays one or a plurality of detected defects as an image of the inspection object based on a statistical result of the inspection objects obtained by the inspection result totaling unit. 2. The image inspection apparatus according to claim 1, wherein the image inspection apparatus has a function of superimposed graphic display. 3. The image inspection apparatus according to claim 1, wherein the inspection target is a cap of a food or beverage container. 4. The image inspection apparatus according to claim 1, wherein the inspection object is a semiconductor wafer. 5. An image of the inspection object captured by the imaging means is subjected to predetermined image processing to inspect the inspection object for the presence or absence of a defect and its type, and based on the inspection result, a plurality of the plurality of the plurality of inspections are performed. An image inspection method, wherein inspection results of inspection objects are totaled, and a necessary part of the statistical results obtained by the aggregation is displayed in a predetermined format. 6. The display of a required portion of the statistical result is a graphic display of one or more found defects superimposed on an image of the inspection object.
Image inspection method as described. 7. The image inspection apparatus according to claim 5, wherein the inspection object is a cap of a food or beverage container. 8. The image inspection apparatus according to claim 5, wherein the inspection object is a semiconductor wafer.