JP2875446B2 - Contour inspection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a contour inspection apparatus for inspecting the contour of an image formed based on a binary image obtained by converting an image document into a binary image.

[0002]

2. Description of the Related Art When an image such as a font for printing is processed by a computer, an outline of the image is sometimes extracted. For example, when an outline font is created from a character document, a method of converting the character image into a binary image using a scanner input device or the like, and converting the binary image into an outline font using an automatic contour extraction device that automatically tracks the boundaries of characters is known. Has been taken. Although the outline font created by this method depends on the extraction accuracy of the automatic contour extraction device, the image quality is usually poor. Therefore, it is necessary to perform an artificial visual inspection to correct the image quality.
Specifically, the extracted outline font is displayed on a display of a computer, and the image quality is corrected by correcting the outline on the screen using a pointing device such as a mouse.

When the image quality correction operation is completed, the outline font is output to a proof output such as paper, and a visual inspection is performed to determine whether the outline font is correct. By this inspection work, it is possible to find an erroneous correction portion at the time of image quality correction and a portion of poor image quality that has not been corrected, and the process is shifted to the image quality correction operation again as necessary.

[0004]

However, in the above-mentioned conventional technology, since the outline font is inspected by the naked eye, the erroneous correction at the time of the image quality correction may be overlooked. In particular, when visually inspecting a large number of outline fonts, the occurrence rate of the above-mentioned oversight becomes extremely large due to the fatigue of the worker and the like, and further, there is a problem that the working efficiency is reduced.

[0005] The contour inspection apparatus of the present invention has been made in view of such a problem, and can automatically determine an erroneously corrected contour instead of a manual visual inspection operation. An object of the present invention is to improve work efficiency and inspection accuracy.

[0006]

Means for Solving the Problems In order to achieve such an object, the following structure is adopted as means for solving the above-mentioned problems. That is, the contour inspection apparatus of the present invention is a contour inspection apparatus for inspecting the quality of an outline of an image created based on a binary image obtained by converting an image document into a binary image. Binary image data storage means for storing image data; first occupancy ratio calculation means for calculating an occupancy ratio of an area represented by one of binary numbers in the binary image data to an entire area; Contour data generating means for generating contour data indicating the contour of the image based on the binary image data; modified contour data generating means for modifying the contour data to generate modified contour data; Second occupancy ratio calculation means for calculating the occupancy ratio of the region corresponding to one value to the entire region, and occupancy ratio in the binary image data calculated by the first occupancy ratio calculation means Comparing / determining means for comparing the occupancy ratio in the corrected contour data calculated by the second occupancy ratio calculating means, and judging the quality of the contour indicated by the contour data in accordance with the comparison result. That is the gist.

[0007]

In the contour inspection apparatus according to the present invention, the binary image data representing the binary image obtained by converting the image document into a binary image is stored in the binary image data storage means.
The occupation ratio of the region represented by one of the binary numbers in the value image data to the entire region is calculated by the first occupation ratio calculation means. Next, contour data indicating the contour of the image created based on the binary image is generated by the contour data generating means, and the contour data is corrected, whereby the corrected contour data is generated by the corrected contour data generating means. The occupation ratio of the region corresponding to the one value to the entire region in the corrected contour data is calculated by the second occupation ratio calculation means. Then, the occupation ratio in the binary image data is compared with the occupation ratio in the corrected contour data by a comparing / determining means, and the quality of the contour indicated by the contour data is determined according to the comparison result.

For this reason, if the corrected contour data of the image created based on the binary image data obtained by converting the image document into a binary image has a shape far apart from the binary image data as the original image, the comparison / determination is performed. The result of the comparison between the two occupation ratios in the binary image data and the corrected contour data by the means is significantly different, and the contour indicated by the corrected contour data is determined to be defective. That is, if the contour data of the image created from the original image is deformed due to a correction mistake at the time of the correction (for example, an erroneous correction in a manual image quality correction operation described in the related art), the contour data Has a shape far apart from the binary image, and its outline is determined to be defective by the comparing / determining means.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS In order to further clarify the structure and operation of the present invention described above, preferred embodiments of the present invention will be described below.

FIG. 1 is a block diagram showing a schematic configuration of an image processing apparatus having a contour inspection apparatus as one embodiment of the present invention. As shown in FIG.
Processing unit 10 provided with PU1, ROM3, RAM5
And an image scanner 12 for reading an image on the document OR as raster data, an interactive terminal 14 for instructing contour line extraction and displaying the raster data on a screen, and a magnetic disk device 16 as an external storage device for storing various data. It is composed of

The CPU 1 that performs processing according to the program stored in the ROM 3 includes a raster / vector conversion unit 1a, a vector / raster conversion unit 1b, and a black ratio calculation unit 1c realized by the processing. The CPU 1 is connected via a common bus 17 to an image input port 20 directly connected to the image scanner 12, a terminal control unit 22 directly connected to the interactive terminal 14, and a disk control unit 24 directly connected to the magnetic disk device 16. ing.

The image scanner 12 optically scans an image on a document OR, reads image data as black and white binary information, and outputs the binary information in a raster format. The document OR is a so-called character document on which characters (fonts) are written. The interactive terminal 14 includes a keyboard 14a and a mouse 14b for instructing various processes, and a CRT display 14c for displaying the results of the processes.

Next, the outline font creation processing routine performed by the processing unit 10 will be described in detail with reference to the flowchart of FIG. According to this processing routine, an outline font indicating the outline of the font written in the document OR is created, and the quality of the outline font is checked.

As shown in FIG. 2, C of the processing unit 10
When the process is started, the PU 1 first performs a process of inputting an image to be written on the document OR (step S100).
This image input is performed by fetching raster data of a binary image read from the image scanner 12 through the image input port 20 and developing the raster data in a predetermined area of the RAM 5. Next, this image data (original image data)
A process of storing D0 in a predetermined area of the magnetic disk device 16 is performed (step S110).

Subsequently, the original image data D0 stored in step 110 is fetched, and the black portion ratio Ra of the original image data D0, that is, the ratio of the black portion to the entire region of the original image data D0 is calculated by the black portion ratio calculating section 1c. Is calculated (step S120). In this case, the black portion ratio Ra is obtained from the number of bits (pixels) represented by the value 1 (black) and the total number of bits since the original image data D0 is expressed in a raster format.

Thereafter, the original image data D0 stored in step 110 is converted from raster format data to vector format data by the raster / vector converter 1a (step S130). This raster / vector converter 1a
Outputs the outline (outline) of the font as vector data by automatically tracking the boundary of the font on the image expressed as raster data, and the outline data D1 is created. Next, a process of storing the contour data D1 in a predetermined area of the magnetic disk device 16 is performed (step S140).

Subsequently, in step S140, an outline correction operation for correcting the image quality of the outline data D1 stored in the magnetic disk device 16 is performed (step S150). This contour correction work is performed by displaying the contour data D1 on the CRT display 14c and
The contour is artificially corrected on the screen using b. The corrected contour data D2 thus corrected is created. Next, a process of storing the corrected contour data D2 in a predetermined area of the magnetic disk device 16 is performed (step S160).

Subsequently, the corrected contour data D2 stored in step 160 for detecting the black portion ratio Rb in the corrected contour data D2 is converted from vector format data to raster format data by the vector / raster converter 1b. (Step S170). The vector / raster conversion unit 1b expresses, as raster data, a font having the outline indicated by the modified outline data D2 as a boundary.
New image data D in binary raster format indicating the font
3 is created.

Subsequently, the new image data D3 is fetched, and the black portion ratio calculation section 1c calculates the black portion ratio Rb of the new image data D3, that is, the ratio of the black region to the entire region of the new image data D3 (step). S18
0). In this case, as in step S120, the black portion ratio Rb is obtained from the number of bits represented by the value 1 (black) and the total number of bits in the new image data D3.

Thereafter, the absolute value of the value obtained by subtracting the black portion ratio Rb of the new image data D3 calculated in step S180 from the black portion ratio Ra of the original image data D0 calculated in step S120 is a predetermined value R0 (this embodiment). Then, 0.5
[%]) Is determined (step S19).
0). Here, when it is determined that | Ra−Rb | ≦ R0,
Assuming that the deviation of the black portion ratio Rb of the new image data D3 from the black portion ratio Ra of the original image data D0 is within the allowable range,
The process proceeds to step S200.

In step S200, "test result = good" is displayed on the CRT display 14c. Thereafter, a process of outputting the modified contour data D2 stored in the magnetic disk device 16 to the outside as outline font data in step S160 is performed (step S210). Here, the corrected contour data D2 may be stored in the magnetic disk device 16 with a new file name as an outline font, or may be printed on a printer device (not shown). Then "End"
To end the processing of this routine.

On the other hand, in step S190, | Ra-Rb
If it is determined that |> R0, it is determined that the deviation of the black portion ratio Rb of the new image data D3 from the black portion ratio Ra of the original image data D0 is out of the allowable range, and "Inspection result = bad" is displayed on the CRT display 14c ( (Step S220) Then, the process returns to step S150, and the contour correction work is performed again. In the contour correction work at this time, the correction may be performed again on the corrected contour data D2 after the correction, and the correction after the raster / vector conversion in the step S130 is still performed. May be corrected for the contour data D1 that has not been subjected to the correction.

Next, how an outline font is created based on the font written on the original OR by the processing according to the outline font creation processing routine configured as described above will be described with reference to a specific example. .

It is assumed that the font shown in FIG. 3A is entered in the original OR. First, step S
By image input by 100 image scanners 12,
The raster-format original image data D0 shown in FIG. 3B is created. Here, for simplicity of description, the original image data D0 is represented by a low number of pixels, but the actual original image data D0 has a higher resolution. Then, step S
By calculating the black portion ratio of 120, the ratio Ra of the number of bits represented by the value 1 in the original image data D0 to all the bits is Ra
Is calculated. In the original image data D0, as shown in FIG.
Therefore, the black portion ratio Ra is 34 [%] when 22 ÷ 64.

Subsequently, the outline data D1 shown in FIG. 3C is automatically generated by the raster / vector conversion in step S130. Subsequently, the contour is corrected artificially by the contour correcting operation of step S150. As a result, corrected contour data D2 shown in FIG. 3D is created. In this contour correction work, the inner contour L1 as shown in FIG.
Has been deleted.

Thereafter, the modified contour data D2 shown in FIG.
To new raster image data D3 shown in FIG.
Is automatically generated. Subsequently, the ratio Rb of the number of bits represented by the value 1 in the new image data D3 to all bits is calculated by the black portion ratio calculation in step S180.
In the new image data D3, as shown in FIG. 3 (e), the total area is 64 and the number of black spots is 32, so the black portion ratio Rb is 32 ÷ 64 and 50%.

Subsequently, by the comparison processing in step S190, the difference between the two black portion ratios Ra and Rb is 16 [%] of 50-34, and it is determined whether or not this value is equal to or less than a predetermined value R0. The value of the predetermined value R0 is actually 0.5 [%] as described above. However, in this description, the original image data D0 is represented by a small number of pixels for simplification of the description. Therefore, for example, 5% is taken. The difference between the black portions Ra and Rb is 16 [%],
Since the difference is not less than [%], it is determined that the difference is out of the allowable range, and then, in step S220, “inspection result = defective” is displayed on the CRT display 14c. In this way, the operator is notified that the corrected contour data D2 shown in FIG. 3D is defective, and also prompts that re-correction is necessary.

On the other hand, when the difference between the two black portion ratios Ra and Rb becomes equal to or less than the predetermined value R0, "Inspection result = good" is displayed on the CRT display 14c in step S200, and in the subsequent step S210, FIG. Is output to a printer or the like as an outline font.

As described in detail above, in the image processing apparatus provided with the contour inspection apparatus of this embodiment, the outline font (corrected contour data D
The defect due to the erroneous correction of 2) can be automatically determined instead of the manual inspection work. As a result,
It is possible to improve the inspection work efficiency and the inspection accuracy.

In this embodiment, as the first occupation ratio calculation means and the second occupation ratio calculation means, the occupation ratio of the bit having the value 1 is calculated by using the black portion calculation unit 1c. In place of the above, a configuration using a white portion ratio calculation unit that calculates the occupation ratio of the bit having the value 0 may be used.

In this embodiment, the vector data (corrected contour data) is converted into raster data (new image data) for detecting the black portion ratio in the corrected contour data. However, the black portion ratio Rb is directly obtained from the vector data. Is also good.

Although one embodiment of the present invention has been described above, the present invention is not limited to such an embodiment, and the gist of the present invention is, for example, a configuration for inspecting the outline of a figure instead of an outline font. Of course, the present invention can be implemented in various modes without departing from the scope of the present invention.

[0033]

As described above, in the contour inspection apparatus of the present invention, the defect that the contour data of the image created on the basis of the binary image obtained by converting the image document into a binary image is erroneously corrected is manually corrected. Instead of the visual inspection operation, the determination can be made automatically, so that the working efficiency can be improved and the inspection accuracy can be improved.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a schematic configuration of an image processing apparatus including a contour inspection apparatus as one embodiment of the present invention.

FIG. 2 is a flowchart showing an outline font creation processing routine performed by a processing unit 10;

FIG. 3 is an explanatory diagram showing a specific example of a change in image data due to processing according to an outline font creation processing routine.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... CPU 1a ... Raster / vector conversion part 1b ... Vector / raster conversion part 1c ... Black ratio calculation part 3 ... ROM 5 ... RAM 10 ... Processing unit 12 ... Image scanner 14 ... Interactive terminal 14a ... Keyboard 14b ... Mouse 14c ... CRT display 16: Magnetic disk drive D0: Original image data D1: Outline data D2: Corrected outline data (outline font) D3: New image data OR: Original Ra, Rb: Black portion ratio

──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Hiromi Chatani 4-chome Ten-chome, Horikawa-dori-Terauchi, Kamigyo-ku, Kyoto 1 Dainippon Screen Mfg. Co., Ltd. (72) Inventor Masayuki Toyoizumi Kyoto 1 Dainippon screen Manufacturing Co., Ltd. in the 4-chome heaven Kamikita-cho, one address to climb inside Noriyuki Kamigyo-ku Horikawa temple (58) investigated the field (Int.Cl. ^6, DB name) G06T 7/00 G06T 1/00 G09G 5/24

Claims (1)

(57) [Claims] 1. An outline inspection apparatus for inspecting the quality of an outline of an image created based on a binary image obtained by converting an image document into a binary image, and storing binary image data indicating the binary image. Binary image data storage means; first occupancy ratio calculation means for calculating the occupancy ratio of the region represented by one of the binary digits in the binary image data to the entire region; Contour data generating means for generating contour data indicating the contour of the image based on the corrected contour data; and correcting the contour data to generate corrected contour data. A second occupancy ratio calculating unit for calculating an occupancy ratio of the region to be occupied in the entire region; A contour inspection device comprising: a comparison / judgment means for comparing the occupation ratio in the corrected contour data calculated by the occupancy calculating means and judging the quality of the contour indicated by the contour data according to the comparison result.