JPH01200357A - Automatic cutting system - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention relates to an apparatus for creating a printing plate film by extracting a background part from an input image, and in particular detects sewing points from a color image and detects the features. The present invention relates to a device for creating a printing plate film with a background portion cut out.

(Prior Art) There are many plain mesh portions in a color printed matter, and the plate-making process for these plain mesh portions is carried out in a special process different from the plate-making process for general color portions, so-called toned materials.

Conventionally, this type of device was disclosed in Japanese Patent Application Laid-Open No. 62-13005.
An apparatus for producing a plain mesh film original plate has been proposed as shown in Publication No. 9 and the like.

FIG. 9 is a block diagram illustrating an example of the configuration of a conventional plain mesh film master production device. Reference numeral 51 denotes a scanner that reads a line drawing image and sends it via an interface 52 to 1. The binary image data is input to the computer 53 using the steps shown in FIG. 54 is an external storage device that stores line drawing image data input from the scanner 51.

55 is an interface that outputs image data processed by the computer 53 to an output scanner 56; The output scanner 56 outputs the film original plate for each printing plate color based on the image data processed by the computer 53. A floppy disk device 57 mainly stores line drawing image data taken in from the scanner 51. 6
0 is a color separation device, computer 61 and computer 61
A tablet 63. is connected to the tablet 14621 for inputting position data. It is composed of a floppy disk device 64 and the like.

Next, processing of line drawing image data taken in from the scanner 51 will be explained.

The input line drawing image is converted into a binary image by the scanner 51, and then imported into the internal memory of the computer 53, read out line by line, and subjected to image processing such as removing dust data included in the binary image data. is executed and stored in the external storage device 54.

Next, according to instructions from the computer 53, the external storage device 5
The image data stored in 4 is output to the color separation device 60,
A predetermined color separation process (coloring process for the inside and outside of the picture drawn as a line drawing) according to the color instruction sheet is executed.

Then, the color separation data separated for the line drawing image is transferred to the computer 53. This allows computer 5
3 outputs the plain mesh film original data for each plate color to the output scanner 56 while referring to the color separation data.

(Problem to be solved by the invention) However, there are cases where only necessary parts are cut out from a photographic manuscript and used.For example, a square photographic manuscript is trimmed into a heart shape, or an object in a photographic manuscript is cut out and used. There are cases where only objects are extracted and used by combining them with other photographic originals.In this case, a clipping process is generally performed.

In other words, you can specify ``Kirinuki'' by tracing the outline of the required pattern on layout paper with a tracing machine, or apply tracing vapor to a photo manuscript, draw the outline of the necessary part, and then add diagonal lines to the unnecessary part. Smash it, specify "Kirinuki", create a cutout mask etc. according to the cutout specification, and perform compositing.

However, printed matter does not only consist of a single color area as mentioned above, but also includes gradual color changes, negative and positive films for color photographs, etc. When creating a film version by extracting only a specific object, such as a person or furniture,
Since the area to be cut out overlaps with areas of different brightness, saturation, and hue, it is not possible to automatically create a faithful film version using the above method. By creating a mask corresponding to the area to be cut out and overlapping that mask with the film original, the film version of the desired color original (
However, due to the complexity of the image of the film original, the efficiency of film plate creation is significantly reduced, which greatly increases the number of days required for the printing process. There are some problems such as the problem of

The present invention has been made to solve the above-mentioned problems, and the present invention calculates density distance data from the density average value and covariance value of the background portion specified for the read color original. The purpose of this invention is to obtain an automatic cropping system that can automatically extract cropped images of color images.

[Means to solve the problem]

The automatic cutting system according to the present invention includes a document reading device for reading a color photo document, an image memory for storing the color image data read by the document reading device for each plate color, and the color image stored in the image memory. A display means for reading and displaying data, an area specifying means for specifying a predetermined background image area displayed on the display means, and a color image data for the background image area specified by the area specifying means for reading out each plate color. density average/covariance calculation means for calculating the density average value and covariance value between plate colors, and a density average/covariance calculation means for reading the color image data stored in the image memory for each pixel and for each plate color and calculating the density average/covariance value. Discrimination function calculation means for calculating density distance data using a discriminant function while referring to the density average value for each plate color and the covariance value between plate colors calculated by the dispersion calculation means, and the density calculated by the discriminant function calculation means. It consists of a background part extracting means for extracting background part image data while referring to distance data and pre-stored judgment distance data.

(Operation) In the present invention, the color photographic original read by the original reading means is stored in the image memory for each plate color, and is displayed on the display means.

Here, when the area specifying means specifies a background image area for the color photo original displayed on the display device, the density average/covariance calculation device reads color image data for the specified background image area from the image memory; The density average value for each plate color and the covariance value between plate colors are calculated. Next, the discriminant function calculating means reads out the color image data stored in the image memory pixel by pixel and for each plate color, and calculates the calculated density average value for each plate and covariance value between the plate colors using a discriminant function. The concentration distance data is calculated by substituting it into a certain, for example, normal distribution function. Then, the background portion extraction means extracts background portion surface image data while referring to the calculated density distance data and pre-stored judgment distance data.

〔Example〕

FIG. 1 is a block diagram illustrating the configuration of an automatic cutting system showing an embodiment of the present invention.

In this figure, reference numeral 1 denotes a layout table, on which a color original 2 (with a uniform background) such as a color film, for example, is placed. Reference numeral 3 denotes a color scanner which optically reads the image of the color original 2 and stores it in the image memory 4 while converting the RGB number into the Y-M-C-BK number. 5 is an image processing controller section composed of a computer, etc.;
Concentration average/covariance calculation means 5a, discriminant function calculation means 5b
.

Background portion extraction means 5c, smoothing processing means 5d.

Vector conversion means 5e, vector data correction means 5f.

It is composed of a noise removing means 5g and the like, and is activated based on a clipping processing program stored in the program memory 10. The density average/covariance calculation means 5a reads out color image data corresponding to the background area designated by the pointing device 7b, which is an area designation means, from the image memory 4, which is an image memory, and converts the color image data into Y, M, C, and BK color spaces. The density average value and the covariance value between plate colors are calculated for each data.

The discriminant function calculating means 5b reads out the color image data stored in the image memory 4 for each pixel and for each plate color, and calculates the density average value and the value for each plate color calculated by the density average/covariance calculating means 5a. Density distance data is calculated using a discriminant function while referring to covariance values between plate colors.

The background part extraction means 5C extracts a background part image from the color image data stored in the image memory 4 while referring to the density distance data calculated by the discriminant function calculation means 5b and the judgment distance data (Mahalanobis distance data) stored in advance. Extract the data.

The smoothing processing means 5d smoothes the background image data extracted by the background extraction means 5c, as will be described later.

The vector converter 5e converts the background image data smoothed by the smoothing processor 5d into background vector data.

The vector data correction means 5f thins out and corrects the background vector data vectorized by the vector conversion means 5e.

Next, the noise removal means 5g performs the vector data correction means 5.
Noise in the background part vector data that has been thinned out and corrected to f is removed according to the knowledge information.

Reference numeral 7 denotes a human power section, which is composed of a keyboard 7a and a pointing device 7b, and inputs commands, position data, etc. necessary for the clipping process to the image processing controller section 5.

Reference numeral 8 denotes a layout scanner serving as a film output means, which separates color image data other than the background from the color image data stored in the image memory 4 by plate color while referring to the background vector data output from the noise removal means 5g. It is read out, cut out and output on a printing film plate 9.

FIG. 2 is a state transition diagram illustrating the automatic clipping process according to the present invention, and the same parts as in FIG. 1 are given the same reference numerals.

In this figure, 11 indicates background extracted image data,
This corresponds to the background extracted image data extracted by the background extracting means 5C shown in FIG. Nl.

N2 is a noise component, which corresponds to data extracted as an uneven density region generated by image processing calculations.

12 is smoothing data, smoothing processing means 5
d corresponds to the noise component N1*N2, for example, obtained by removing adjacent pixel data using predetermined matrix data. As a result, background contour data 12a is generated.

13 is background vector data; background contour data 12
This corresponds to the vector data of a.

Reference numeral 14 indicates background vector data that has been thinned out and corrected, and background vector data 13 is processed by the vector data correction means 5f.
Obtained by thinning correction. 14a and 14b are noise vector data, which are automatically erased by the noise removing means 5g using knowledge information.

15 is background vector data, and this background vector data 15 is output to the layout scanner 8.

16 is a cutout image of the printing film plate 9 shown in FIG.
exposed to light.

When the manual input for the color original yJ2 is instructed from the pointing device 7b, the color scanner 3 starts reading the color original fA2, and converts the read color image data into plate colors (yellow, magenta, cyan, black).
Each time, data is sequentially written to the image memory 4. When this writing is completed, the color image data read from the image memory 4 is displayed on the display 6.

Here, when the background area or background point P is specified by the pointing device 7b, the density average/covariance calculation means 5a reads out the color image data for the specified background image area from the image memory 4, and reads out the color image data for the specified background image area for each plate color. density average values AVM, AVC, AVY, AVK and covariance values between plate colors CVMM, -CVCM, CVYM, CVKM,
・、CVMK、CVCK、CVYK、、CVKK (
A total of 16 variables) are calculated. Next, the discrimination function calculating means 5b reads out the color image data stored in the image memory 4 pixel by pixel and for each plate color, and calculates the calculated density average values AVM, AVC, AVY, AVK and plate colors for each plate. The covariance value between CVMM.

CVCM, CVYM, CVKM, -, CVMK.

Concentration distance data is calculated by substituting CVYK and CVKK into a normal distribution function which is a discrimination function in CVC.

Then, the background portion extracting means 5C extracts the background portion extracted image data 11 by determining whether the calculated density distance data is smaller than pre-stored determination distance data.

The extracted background image data is processed by smoothing processing means 5.
The background contour portion is smoothed by d, and smoothing data 12 is generated.

Next, the vector converting means 5e transforms the background contour data 12a, which is the background image data, into the background vector data 1.
3, the vector data correction means 5f performs a thinning process to reduce the number of change points in the background vector data 13 to correct the vector shape. Then, the noise removing means 5g erases the noise vector data 14a and 14b using the knowledge information, and the noise removed background part vector data 1
5 is output to the layout scanner 8.

In accordance with this, the layout scanner 8 reads the color image data (cutout image 16) corresponding to the outside of the background part in the color image data stored in the image memory 4 while referring to the background part vector data 15, and reads the color image data (cutout image 16) corresponding to the outside of the background part in the color image data stored in the image memory 4.
Cut out each plate and output the exposure.

Next, with reference to FIGS. 3 to 6, smoothing processing based on expansion and contraction by the smoothing processing means 5d shown in FIG. 1 will be explained.

FIG. 3 is a schematic diagram illustrating expansion of contour pixels by the smoothing processing means 5d shown in FIG.
Neighboring pixels are searched to determine "1" (black pixel) and "rO" (white pixel) of the target pixel 21a. Reference numeral 22 denotes an expansion processing pattern, which corresponds to a state in which the target pixel 21a is formed to be “1” (indicated by diagonal lines) and expanded when even one of the eight neighboring pixels of the determination pixel pattern 21 is “1”.

FIG. 4 is a schematic diagram illustrating the contraction of contour pixels by the smoothing processing means 5d shown in FIG.
The rib and rQJ of the target pixel 31a are determined by searching for neighboring pixels. Reference numeral 32 denotes a contraction processing pattern, which corresponds to a state in which the target pixel 31a is formed to "0" and contracted when even one of the eight neighboring pixels of the determination pixel pattern 31 is "0".

For example, when the TRS image image data 41a in which a convex notch is included in the outline of a line drawing as shown in FIG.
A contraction scan is performed using the determination pixel pattern 31 shown in the figure to generate contraction image data 41b, and in order to perform expansion processing on this contraction image data 41b, the smoothing processing means 5d is operated by the third smoothing processing means 5d based on the smoothing processing program. Dilation scanning is performed using the judgment pixel pattern 21 shown in the figure to generate a notch-removed image 41c.

On the other hand, when line drawing image data 42a in which the outline of the line drawing includes a concave notch as shown in FIG. 6 is retrieved, the 72 judgment pixel pattern 21 shown in FIG. In order to perform dilation scanning to generate dilated image data 42b, and perform a dilation process on this dilated image data 42b, the smoothing processing means 5dh is executed based on a smoothing processing program.
<Contraction scanning is performed using the determination pixel pattern 31 shown in FIG. 4 to generate notch-removed image data 42c. In this embodiment, this process is performed on the entire image in the order of expansion, expansion, and contraction.

FIG. 7 is a schematic diagram illustrating vector data correction processing by the vector data correction means 5f shown in FIG.
Reference numeral 5 indicates original vector data, which corresponds to vector data generated by the vector conversion means 5e. Reference numeral 46 denotes corrected vector data, which corresponds to data obtained by reducing the number of vector points at a predetermined pitch so as not to generate a level difference between the respective original vector data 45.

As can be seen from this figure, original vector data 45 is automatically corrected to corrected vector data 46 by searching for key points of change on the binary thin line using direction codes. This reduces the roughness of the contour edges.

Next, the noise removing means 5g extracts the corrected vector data 4.
6, noise vector data is removed in loop units.

The knowledge information ■～■ for noise removal is stored in an internal memory (not shown), and the following noise removal rules (1) are stored in the internal memory (not shown).
) to (4) can be removed by searching the vector data according to the following.

■Loop length ■Loop inclusion relationship ■Loop complexity (number of critical points/vector loop length) (1) A vector loop whose vector loop length is less than a certain value and whose complexity is more than a certain value is Remove.

(2) Vector loops whose vector loop length is a certain value or more, whose inclusion relationship is the outermost one, and whose complexity is less than a certain certain value remain.

(3) Vector loops that are inside due to inclusion relationships and whose complexity exceeds a certain value are removed.

(4) A vector loop that is inside due to an inclusion relationship, has a vector loop length of a certain value or more, and has a complexity of a certain certain value or less is left as a cutout line.

Using such knowledge information and noise removal rules, highly accurate background vector data for the cropped image is generated, and the layout scanner 8 accesses the image memory 4 while referring to this background vector data, and removes the parts other than the background. A color image data sheet is extracted, and a printing plate of the cutout image is automatically exposed and outputted onto a printing film plate 9.

Next, automatic clipping processing according to the present invention will be explained with reference to FIG.

FIG. 8 is a flowchart illustrating the automatic clipping processing procedure according to the present invention. Note that (1) to (17) indicate each step.

The pointing device 7b instructs the color document 2 to read the image, and waits for the color scanner 3 to finish reading the color document 2.
), when reading for each plate color is completed, the read color image data is registered in the image memory 4 for each plate color (2
).

Next, it waits for a drawing command for the registered color image to be input from the pointing device 7b (3), and when the drawing command is input, the color image data read from the image memory 4 is drawn on the display 6 (3). 4
). At this point, the operator waits for the operator's input from the pointing device 7b to indicate the background part 5).
When the background part is specified, the density average/covariance calculation means 5a
reads the color image data for the background area indicated by the pointing device 7b from the image memory 4, calculates the density average value for each plate color and the covariance value between the plate colors, and calculates the color image data for each pixel read from the image memory 4. The color image data, the density average value, and the covariance value are substituted into a normal distribution function serving as a discrimination function to calculate density distance data (6).

Then, refer to the pre-stored judgment distance data 7) and judge whether the density distance data becomes the background part 8). If No, return to step (6); if YES, the color becomes the background part. Register image data (9)
.

Next, the smoothing processing means 5d expands and contracts the contour shape of the color image data (10).

(11), smoothing correction.

Next, the vector conversion means 5e converts the smoothed background image data (raster data) into vector data (32).

Subsequently, the vector data correction means 5f performs thinning correction on the vector data, and the noise removal means 5g performs noise removal on the vector data (13), (14).

Next, the layout scanner 8 waits for the color image data for each plate color stored in the image memory 4 to be read out while referring to the corrected vector data (15).
), read out color image outside the background (cropped image)
is exposed to the printing film plate 9 for each plate color (1
6).

Next, determine whether all the films have been output]7) If no, return to step (15) and select YES.
If so, the process ends.

In the above embodiment, the color original 2 is transferred to the color scanner 3.
Although the case where input is made is described in No. 1, the same processing can be executed by inputting from an input drum (not shown) of the layout scanner 8.

〔Effect of the invention〕

As explained above, the present invention includes an original reading means for reading a color photo original, an image memory for storing color image data read by the original reading means for each plate color, and the color image stored in the image memory. a display means for reading and displaying data; an area specifying means for specifying a predetermined background image area displayed on the display means;
A density average/covariance calculating means reads the color image data to be engraved in the background image area specified by the area specifying means and calculates the density average value for each plate color and the covariance value between the plate colors, and the image memory. The stored color image data is read out for each pixel and for each plate color, and identified by referring to the density average value for each plate color and the covariance value between plate colors calculated by the density average/covariance calculation means. Discrimination function calculation means for calculating density distance data using a function, and background part extraction means for extracting background part image data while referring to the density distance data calculated by the discrimination function calculation means and judgment distance data stored in advance. With this configuration, a cutout image of a read color image can be automatically extracted for each plate color by a simple operation such as specifying an arbitrary point where the background of the read color image is negative.

Therefore, compared to the conventional cutout image film creation process using mask processing, excellent effects such as being able to extract a cutout image print film with high accuracy in a shorter time can be achieved.

[Brief explanation of the drawing]

FIG. 1 is a block diagram explaining the configuration of an automatic clipping system showing an embodiment of the present invention, FIG. 2 is a state transition diagram explaining automatic clipping processing according to the present invention, and FIG. FIG. 4 is a schematic diagram illustrating the expansion of contour pixels by the smoothing processing means shown in FIG. 1, and FIG. 5 and FIG. FIG. 7 is a schematic diagram explaining the vector data correction process by the vector data correction means shown in FIG. 1, and FIG. 8 is a schematic diagram explaining the automatic clipping processing procedure according to the present invention. The flowchart and FIG. 9 are block diagrams illustrating an example of the configuration of a conventional plain screen film master production apparatus. In the figure, 1 is a layout table, 2 is a color original, 3 is a color scanner, 4 is an image memory, 5 is an image processing controller section, 5a is a density average/covariance calculation means, 5b
5C is a discriminant function calculation means, 5C is a background extraction means, 5d is a smoothing processing means, 5e is a vector conversion means, 5f is a vector data correction means, 5g is a noise removal means, 6 is a display, 7 is a human power section, and 7a is a keyboard. , 7b is a pointing device, 8 is a layout scanner, and 9 is a printing film plate. Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7

Claims (1)

[Claims] an original reading means for reading a color photographic original; an image memory for storing color image data read by the original reading means for each plate color; and a display means for reading and displaying the color image data stored in the image memory; an area specifying means for specifying a predetermined background image area displayed on the display means; and an area specifying means for reading out the color image data for the background image area specified by the area specifying means, and an average density value and a plate color for each plate color. density average/covariance calculation means for calculating a covariance value between; and density average/covariance calculation means for reading out the color image data stored in the image memory for each pixel and for each printing color Discrimination function calculation means for calculating density distance data using a discriminant function while referring to the calculated density average value for each plate color and covariance value between plate colors; An automatic clipping system comprising a background part extracting means for extracting background part image data while referring to stored determination distance data.