JPH06148094A - Method for inspecting mixture of foreign matter of sheetlike product - Google Patents

Abstract

PURPOSE:To effectively detect mixture of a foreign matter by imaging a surface of a sheetlike product by a CCD camera by irradiating the product from its rear surface, and detecting a part having different density difference from that of its periphery from the image. CONSTITUTION:A sheetlike product 11 to be detected for mixture of a foreign matter is disposed on a light projecting unit 10, the product 11 is imaged together with a light transmitted through the product 11 by an upper monochromatic CCD camera 12, its image signal is input to an image processor 13, and mixture of the foreign matter is inspected by a computer 14. That is, the input image is processed by a density morphology and an image statistical quantity, and images obtained by the respective processes are combined to obtain the image of the matter. Number of parts recognized as the matters and its area are obtained, and the product 11 is decided whether acceptable or rejectable.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for inspecting a sheet-shaped product for foreign matter, for inspecting the sheet-shaped product for foreign matter.

[0002]

2. Description of the Related Art If a sheet-shaped product such as paper is contaminated with foreign matter, its value as a product is reduced, and it is necessary to inspect it.

[0003]

In this method for inspecting a foreign substance, visual inspection is inaccurate due to individual differences.
Further, if the foreign matter is merely optically detected and the foreign matter is buried in the sheet, there is a problem that the foreign matter cannot be detected simply by looking at the surface.

Therefore, an object of the present invention is to solve the above problems and to provide a method of inspecting a sheet-like product for foreign matter, which can optically and reliably detect the presence of foreign matter.

[0005]

In order to achieve the above object, the present invention is directed to illuminating the back surface of a sheet-like product with a CCD camera, and capturing the front surface with a CCD camera. Is detected as a foreign matter.

[0006]

According to the above construction, by shining light on the sheet-like product and picking up an image of the transmitted light with the CCD camera, a light and shade difference between a portion having a foreign substance and a portion having no foreign substance becomes remarkable.
Foreign matters can be easily inspected by finding a portion having a large contrast in the image of the CCD camera.

[0007]

An embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

In FIG. 1A, a sheet 11 for detecting foreign matter is placed on a light projecting device 10, and a monochrome CCD camera 12 for picking up the sheet 11 together with the light transmitted through the sheet 11 is placed above the sheet 11. To be done. The signal from the monochrome CCD camera 12 is input to the image processing device 13, and the computer 14 inspects the foreign matter.

This foreign matter detection algorithm is shown in FIG. 1 (b).
First, the inspection is started, and when an image is input, the foreign matter is extracted from the image based on the density morphology and the image statistics, the area and number of the foreign matter are measured, and the quality of the product is judged. Finish the inspection. The aperture of the lens attached to the monochrome CCD camera is adjusted in advance so that an appropriate inspection can be performed.

The foreign matter mixture inspection based on the density morphology and the image statistics will be described in detail with reference to FIG.

First, an image 20 of one screen picked up by a monochrome CCD camera is composed of 512 horizontal pixels and 512 vertical pixels as shown in FIG. The signal of this pixel can be changed to a level of 0 for black (no transmitted light) and a level of 255 for white (100% transmission) when the gray value is expressed by 8-bit gradation. The portions 21a, 21b, 22c to 21e appearing blacker than the set level on the image 20 are indicated by diagonal lines.

Each of the parts 21a, 21b, 22c to 21c
The foreign matter of e is extracted by the density morphology if each area is equal to or smaller than the area threshold S1, and is extracted by using the image statistic if it is equal to or larger than the area threshold S2.

Next, the foreign matter detection based on the light and shade morphology will be described. If the size of the filter is determined in accordance with the area threshold value S1 and the maximum value filter is applied to the image 20 in accordance with the filter size, then the minimum value filter is applied. Two
An image 24 in which only 1a and 22d are left is obtained. As a result, the level of each pixel at the position of the AA line of the image 20 is represented by the curve 26 of (d), but in the image 24, the level of each pixel at the position of the AA line is (d). ) Curve 25
It is represented by. The curve 26 is subtracted from the curve 25 in (d) to obtain the shade difference as shown in (e). Similarly, the gray level difference is calculated for all the vertical directions as described above, that is, the image 20 is subtracted from the image 24 to obtain the gray level difference of each pixel,
By comparing with the set threshold value T1, only the part exceeding the threshold value T1 is left as the pixel value level 255, and the other parts are left as the pixel value level 0. If S1 or less and the difference in shade from the surroundings is the threshold value T
Image 2 with binarized parts 22c and 22e larger than 1.
7 is obtained.

Next, the foreign matter detection based on the image statistics will be described. Before inspection, a good image is input in advance, the average gray value m and standard deviation σ of the image are calculated, and then the average gray value m
And the standard deviation σ, the binarization threshold value T2 (= m + k * σ
+ B k: arbitrary coefficient, b: bias value) are determined. When the image 20 is binarized with a threshold value T2 and a portion having an area threshold value S2 or more is left, as shown in (b), the image level is particularly low and the area is the area threshold value. An image 23 including the portion 21a of S2 or more is obtained.

Image 27 obtained by the light and shade morphology processing
And the image 23 obtained by the image statistic processing are combined to obtain a foreign substance image 28 as shown in (g). Then, the number of the portions 21a, 22c, 22e recognized as the foreign matter is obtained and the area thereof is also obtained, and the quality of the product is judged from these.

In this embodiment, a monochrome CCD camera is used, but an inspection can be carried out by using a color CCD camera and performing the same processing on each of the R, G and B components.

Further, here, the image size is 512 × 51.
2 pixels, the gradation of the image gray value is 8 bits 256 gradations,
Although the gradation value level 0 is described in detail as black and 255 as white, foreign matter can be inspected even if the image size and the gradation level are selected.

As the foreign matter extraction processing, an example using both the light and shade morphology and the image statistic is given, but the foreign matter extraction and inspection can be carried out individually according to the foreign matter to be extracted.

[0019]

In summary, according to the present invention, light is applied to a sheet-like product and the transmitted light is imaged by a CCD camera, so that a light and shade difference between a portion having a foreign substance and a portion having no foreign substance appears remarkably. It is possible to easily inspect for foreign matter by searching for a portion having a large difference in shade from the image of the CCD camera.

[Brief description of drawings]

FIG. 1 is a diagram showing an embodiment of the present invention.

FIG. 2 is an explanatory diagram for inspecting a foreign substance in the present invention.

[Explanation of symbols]

 10 Projector 11 Sheet-like product 12 CCD camera

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Masahiro Yagabe 2-1-1 Toyosu, Koto-ku, Tokyo Ishikawajima Harima Heavy Industries Ltd. Tokyo No. 1 factory (72) Inventor Junichi Ito Toyosu, Koto-ku, Tokyo 1-1-1 Ishikawajima Harima Heavy Industries Ltd. Tokyo No. 1 factory

Claims (1)

[Claims] 1. A sheet-like product characterized in that light is applied from the back side of a sheet-like product, the surface is imaged by a CCD camera, and a portion having a different shade from the surroundings is detected as a foreign matter from the image taken by the CCD camera. Foreign matter contamination inspection method for products.