JP3018878B2 - Picture inspection equipment - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a picture inspecting apparatus suitable for automatically detecting a tail defect occurring in a direction perpendicular to a picture contour of a printed matter and reducing printing defects as much as possible.

[0002]

2. Description of the Related Art As defective contents of a printed matter, there are a tail defect occurring at a picture outline portion and a printing defect defect occurring inside a picture. The tail is generated in the printing direction, is formed of a linear, pointed tip that protrudes into the picture of the printed matter, and has a characteristic that it is generated continuously once generated. The frequency of occurrence is relatively high in gravure soft packaging printing and the like, and is also called doctor waste. If the tail becomes longer than a certain length, the printed matter becomes defective. The pattern inspection method which has been conventionally implemented covers a pattern outline of a printed matter with a mask and detects a defect generated inside the pattern by image processing, and only the above-described print defect defect is detected. On the other hand, the detection of a tail defect was performed exclusively by visual observation.

[0003]

As described above, since the detection of a tail defect relies on visual observation, a detection error is likely to occur, and there is a problem that many defective prints are generated. In addition, visual detection requires a high degree of skill, requires special skilled workers, is extremely inconvenient, cannot perform unattended work, and has a problem in that work efficiency and reliability cannot be improved.

The present invention has been made to solve the above-mentioned problems, and a tail defect is automatically and accurately detected, and a printed matter is reduced, and work efficiency and reliability can be improved. An object of the present invention is to provide a picture inspection apparatus that enables unattended work.

[0005]

SUMMARY OF THE INVENTION In order to achieve the above object, the present invention provides a picture inspection apparatus for image processing a printed matter and detecting a tail defect generated vertically from a picture edge, Contour extraction means for extracting the contours of a reference image serving as an inspection reference and a target image serving as an inspection target to generate a reference contour image and a target contour image, respectively; and using a predetermined logical filter, the reference contour image and the target contour respectively. Vertical enhancement means for processing the image and enhancing its vertical vector component;
Mask creating means for creating and storing a mask image by expanding a reference contour image in which a vertical vector component is emphasized, and masking a target contour image in which a vertical vector component is emphasized using the mask image to produce a tail defect A pattern inspection apparatus having a mask processing unit for detecting a horizontal edge and a vertical edge by using a Sobel filter to extract a horizontal edge and a vertical edge. The present invention is characterized by a picture inspecting apparatus that generates a horizontal component image and a vertical component image by performing image processing to generate a reference contour image and a target contour image by combining the two component images.

[0006]

According to the present invention, a tail image is determined by superimposing a reference image serving as an inspection reference and a target image to be inspected. Specifically, using a differential operator such as a Sobel filter, the horizontal and vertical edges of the reference image and the target image are extracted and binarized, and horizontal and vertical component images are created and then combined. A reference contour image and a target contour image are generated. Next, after emphasizing only the vertical vector components of the reference contour image and the target contour image by using a predetermined logical filter, a mask image is created and stored by expanding the emphasized reference contour image. When this mask image and the emphasized target contour image are overlapped, only the tail is exposed, and the tail that should be defective is detected. With the above processing method, the tail failure is automatically and reliably detected.

[0007]

An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing the overall configuration of this embodiment, FIG. 2 is a flowchart for explaining a tail detection method of this embodiment, and FIG. 3 is a partial plane of a reference image and a target image taken from a printed matter. FIG. 4 is a schematic diagram showing weight coefficients of a Sobel filter for extracting horizontal edges, FIG. 5 is a plan view of horizontal edge extracted images of both reference and target images, and FIG. 6 is a diagram of a Sobel filter for extracting vertical edges. FIG. 7 is a schematic diagram showing weighting coefficients, FIG. 7 is a plan view of vertical edge extracted images of both reference and target images, FIGS. 8 and 9 are plan views showing binarized horizontal and vertical edge extracted images, and FIG. 8 and 9
Plan view showing a reference contour image and a target contour image obtained by synthesizing the horizontal edge and vertical edge extracted images shown in FIG.
11 to 16 are schematic diagrams of a logical filter used in the present embodiment, FIG. 17 is a plan view showing a reference contour image and a target contour image in which only vertical vector components are emphasized, and FIG. Plan view of the mask image, FIG.
9 is a plan view showing a tail detected by covering the emphasized target contour image with a mask image.

First, the overall configuration of the embodiment will be described with reference to FIG. The picture inspection apparatus 1 of the present embodiment is roughly composed of a contour extracting means 2, a vertical emphasizing means 3, a mask creating means 4, a mask processing means 5, and the like.

The processing contents of the contour extracting means 2 include:
As shown in FIG. 1, an image capturing unit that captures a reference image serving as an inspection standard and a target image to be inspected from a printed material by an image scanner or the like, and a Sobel shown in FIG. 4 and FIG. Edge extraction for performing horizontal edge and vertical edge extraction by filters 6 and 7, its binarization processing unit, and synthesizing the binarized horizontal component image and vertical component image to obtain a reference contour image and a target contour image , Etc., that generate the Hereinafter, the contents of each processing unit will be described in more detail.

As shown in the flowchart of FIG. 2, a reference image and a target image are fetched from a printed material in steps A-1 and B-1. As the reference image, either an absolute reference based on the first printed matter or a relative reference based on the immediately preceding printed matter is selected. A-1 in FIG. 3 indicates a reference image, and B-1 indicates a target image. Hereinafter, the step reference symbols in the flowchart correspond to the image reference symbols. “A” in the reference code corresponds to the reference image,
B ″ corresponds to the target image. The Sobel filter 6 for performing horizontal edge extraction is composed of 3 × 3 pixels, and is composed of −1, 0, 1 as shown in FIG. A pixel value at a position corresponding to a 3 × 3 pixel is obtained by mounting the Sobel filter 6, and the sum of all pixel values calculated by multiplying the value by −1, 0, and 1 is the central point 6.
The pixel value at a. The values of −1, 0, and 1 are set in order to simultaneously perform differentiation in the vertical direction and smoothing in the horizontal direction to mainly extract horizontal edges. By performing the above processing on the reference image and the target image of A-1 and B-1 in FIG. 3, horizontal edge extraction in steps A-2 and B-2 of the flowchart is performed. The horizontal edge extracted images are shown in A-2 and B-2 in FIG. Similarly, the 3 × 3 Sobel filter 7 shown in FIG.
Vertical edges of -3 and B-3 are extracted, and the vertical edge extracted images are shown in A-3 and B-3 of FIG. In addition,
In the case of the Sobel filter 7, the pixel value of the calculated sum is displayed at the center point 7a. The reason why the Sobel filter 7 employs an array of -1, 0, 1 as shown in the drawing is to perform vertical differentiation and smoothing in the vertical direction at the same time to mainly extract vertical edges. is there. Next, a binarization process is performed as shown in steps A-4, B-4 and A-5, B-5 of the flowchart. For example, a threshold value is obtained from the pixel values of the horizontal edge extracted images A-2 and B-2 shown in FIG. 5 and binarized based on the threshold value. The binarized horizontal edge extracted image (horizontal component image) is shown in FIG.
4, B-4. Similarly, binarized vertical edge extracted images (vertical component images) are shown in A-5 and B-5 in FIG. Next, steps A-6, B-
As shown in FIG. 6, the horizontal component images A-4 and B-4 and the vertical component images A-5 and B-5 are respectively subjected to logical sum (OR) processing. As a result, reference contour images and target contour images shown in A-6 and B-6 in FIG. 10 are obtained.

As shown in FIG. 1, the vertical enhancement means 3 enhances the reference contour image A-6 and the target contour image B-6, and as shown in A-7 and B-7 of the flowchart, Only the vertical vector component is emphasized, and a reference contour image A-7 and a target contour image B-7 with vertical component enhancement as shown in FIG. 17 are obtained. To determine this image, certain logical filters are used, which are shown in FIGS. Each of the logical filters 8, 9, 10, 11, 12, 13 is a logical filter having a combination of ×, 0, 1 and having a number of 3 × 6 pixels in some cases consisting of 5 × 4 pixels. May be used. More specifically, for example, when the logical filter 8 of FIG. 11 is used and this is matched with the reference contour image A-6 or the target contour image B-6 shown in FIG.
If the pixel array pattern in the vicinity of × 4 matches the pattern of the logical filter 8, the pixel at the position 8a in FIG. In the filter, the pixel of X is excluded from the matching judgment. During the above processing, three 1s continue in the center row. Such processing is further performed by the logical filters 9-1 having the patterns shown in FIGS.
3 to obtain a reference contour image A-7 and a target contour image B-7 for vertical component emphasis.
Each of the six types of logical filters is obtained by patterning a typical tail shape.

Next, the mask creating means 4 will be described. This means comprises a process of expanding the reference contour image in which the vertical component is emphasized to create a mask image A-8 as shown in step A-8, and a process A-9 of storing the mask image. FIG. 18 shows an expanded reference contour image, that is, a mask image A-8. The expansion process is performed by inverting the reference contour image A-7 by one pixel along the contour.

Next, the mask processing means 5 will be described. This means superimposes the mask image A-9 and the target contour image B-7 on which the vertical component is emphasized, as shown in FIG. 1 and the judgment of step B-8 in the flowchart.
(FIG. 19). Since the mask image A-9 has been subjected to the dilation processing, the portion other than the tail 14 of the target contour image B-7 is entirely covered by the mask image A-9. Therefore, only the tail 14 is clearly detected as shown in FIG.

As can be understood from the above description, the tail detection algorithm according to the present invention is created in conformity with the characteristics of the tail. The tail has features such as protruding from the contour portion to the non-contour portion, always flowing in the printing direction (vertical direction), often being sharp at the tip, and continuously occurring. The present invention positively utilizes these features. In other words, the tail in the printing direction, which is a feature of the tail, is emphasized, so that the tail is stretched more than the variation (corresponding to the mask width due to positional deviation or the like). The judgment is bad if the stretched tail protrudes from the mask.

In the above embodiment, 5 × 4 logical filters 8 to 13 are used, but 3 × 6 filters may be used. This is the RA used for the conversion table of the filter.
It is limited by the size of M and is not necessarily limited to the above. Further, in the above-described embodiment, the number of times of expansion of the reference contour image A-7 for vertical component enhancement is set to one, but the present invention is not limited to this. The number of times of expansion is k, tail 1
Assuming that the length of 4 is g and the number of emphasis is m, ideally, the number of emphasis is determined so as to satisfy m> 2kg. For example, when k = 1 and g = 1 (one pixel), m> 1, that is, the number of emphasis is two. 1 by one filter
Since the pixels are emphasized, the tail 14 is expanded to three pixels as a whole and detected. However, since there is a quantization error (error due to binarization) and 1 may be set to 0, the unit of the tail to be emphasized may be at least two pixels. Also,
If one pixel is about 0.2 mm, three pixels will be used during operation.
Normally, it is preferable that the tail 14 of two pixels, at most, one pixel can be detected. However, a tail with a long width and a rounded tip, a tail buried in a quantization error, or a tail in a complicated character area may be difficult to detect depending on the mask size.

[0016]

According to the present invention, the following remarkable effects are obtained. 1) The tail, which previously could not be automatically detected, automatically
And it is reliably detected. 2) Since a tail defect is detected without relying on visual observation, automatic printing becomes possible, thereby improving work efficiency and improving reliability. 3) An accurate tail detection can be performed without requiring a special expert. 4) By appropriately setting the reference image, it is possible to significantly reduce the printed matter defect.

[Brief description of the drawings]

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

FIG. 2 is a flowchart illustrating a processing method according to the embodiment.

FIG. 3 is a plan view showing a reference image and a target image captured from a printed material.

FIG. 4 is a schematic diagram showing a Sobel filter for extracting a horizontal edge.

FIG. 5 is a plan view showing an edge-extracted reference image and a horizontal edge-extracted image of a target image.

FIG. 6 is a schematic diagram showing a Sobel filter for vertical edge extraction.

FIG. 7 is a plan view showing a reference image from which edges are extracted and a vertical edge extracted image of a target image.

FIG. 8 is a plan view showing the binarized horizontal edge extracted image (horizontal component image) of FIG. 5;

FIG. 9 is a plan view showing the binarized vertical edge extraction image (vertical component image) of FIG. 7;

FIG. 10 is a plan view showing a reference contour image and a target contour image obtained by combining the extracted images of FIGS. 8 and 9;

FIG. 11 is a schematic diagram of a logical filter for enhancing an image.

FIG. 12 is a schematic diagram of a logical filter for enhancing an image.

FIG. 13 is a schematic diagram of a logical filter for enhancing an image.

FIG. 14 is a schematic diagram of a logical filter for enhancing an image.

FIG. 15 is a schematic diagram of a logical filter for enhancing an image.

FIG. 16 is a schematic diagram of a logical filter for enhancing an image.

FIG. 17 is a plan view showing a reference contour image and a target contour image for vertical component emphasis.

FIG. 18 is a plan view showing a mask image formed by expanding the reference contour image of FIG. 17;

FIG. 19 is a plan view showing a detected tail.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Picture detection apparatus 2 Outline extraction means 3 Vertical emphasis means 4 Mask creation means 5 Mask processing means 6 Sobel filter 7 Sobel filter 8 Logic filter 9 Logic filter 10 Logic filter 11 Logic filter 12 Logic filter 13 Logic filter 14 Tail

────────────────────────────────────────────────── ─── Continued on the front page (58) Fields investigated (Int.Cl. ⁷ , DB name) G06T 1/00 G06T 5/20 G06T ⁷ /00-7/60 B41F 33/14 G01N 21/88 H04N 1 / 00

Claims (2)

(57) [Claims] 1. A picture inspection apparatus for processing a printed matter to detect a tail defect generated in a vertical direction from a picture edge, wherein a contour of a reference image as an inspection reference and a contour of a target image to be inspected are extracted. Contour extraction means for generating a reference contour image and a target contour image, and processing the reference contour image and the target contour image using a predetermined logical filter,
Vertical emphasis means for emphasizing the vertical vector component, mask generation means for generating and storing a mask image by expanding a reference contour image emphasizing the vertical vector component, and emphasizing the vertical vector component using the mask image A picture inspection apparatus comprising mask processing means for masking a target contour image and detecting a tail failure. 2. The method according to claim 1, wherein the contour extracting means performs image processing for extracting a horizontal edge and a vertical edge using a Sobel filter and binarizing the image to generate a horizontal component image and a vertical component image. The picture inspection apparatus according to claim 1, wherein the reference contour image and the target contour image are generated by combining the reference contour image and the target contour image.