JPH1115955A - Mask creation device and recording medium recording mask creation program - Google Patents

Abstract

(57) Abstract: An object of the present invention is to provide an apparatus and a program for creating a mask used when extracting an image in a layout scanner or the like. An image data input unit, an edge image creating unit for creating edge image data, a binarized image creating unit for creating binary image data, and a thin line for creating thinned image data. A mask creating apparatus comprising: a segmented image creating unit 4, an image merging unit 5 for merging thin line image data, a mask creating unit 6 for creating a mask, and a storage unit 7 for storing the data. And a recording medium on which a program is recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

TECHNICAL FIELD The present invention relates to a method for converting image data
The present invention relates to a mask creating apparatus for extracting only a required image area.

[0002]

2. Description of the Related Art Conventionally, in an image processing apparatus such as a layout scanner, as a mask creating apparatus for cutting out a required image area from image data, an operator refers to an image displayed on a display, There has been an apparatus for creating a mask by tracing the outline of an area where a mask is to be created using a digitizer or a pointing device such as a mouse. Also,
There has been an apparatus that detects a color difference or a density difference between a mask creation area and a background area and sets a threshold value of a color signal or a density signal so as to divide the two areas to create a mask.

[0003]

However, in an apparatus for creating a mask by tracing a contour portion of an area where a mask is to be created, if a region having a complicated shape is to be cut out, the tracing operation becomes complicated. The burden on the operator increased, and the work time had to be very long. Further, when connecting the point information read by the trace to form line information, it is necessary to perform a smoothing process or a vectorization process, so that a complicated processing mechanism must be incorporated in the apparatus.

On the other hand, in an apparatus for creating a mask from a color signal or a density signal, it is necessary for an operator to set an appropriate threshold each time while checking an image. Another difference is that when creating a mask from a specific area in a photographic image taken in a natural environment such as outdoors, the same color as that in that area exists in the background area. In such a case, there is a problem that the two regions cannot be divided.

Further, in an apparatus for dividing a mask area and another area from color quantization of image data and edge information, an area (for example, a complicated grid) composed of a combination of various colors and pictures is used. When it is attempted to cut out a pattern or a floral sweater, clothes, etc. at once, there is a problem in that the edges cannot be extracted too finely so that the region cannot be collectively divided.

[0006]

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and the invention described in claim 1 of the present invention comprises an image data image input means 101,
An edge image creating unit 103 for creating edge image data from the image data;
Binarized image creating means 104 for creating binarized image data
Thinning image creating means 105 for creating thinning image data from the binary image data and the edge image data;
A combined image creating unit 107 that combines thinned image data to create combined image data, a mask creating unit 108 that creates a mask from the combined image data, and a storage unit 102 that stores the data. Is a mask making apparatus.

According to a second aspect of the present invention, there is provided the above-mentioned mask creating apparatus, further comprising an image deleting means 106 for deleting a portion such as a branch portion of the thinned image data. It is. In addition, the display device 109 for displaying each image data can be added to the above means to display each image data.

According to a third aspect of the present invention, the image data is input, edge image data is created from the image data, and the image data is binarized.
Making thinned image data from edge image data and binary image data, merging the thinned image data to make merged image data, and making a mask from the merged image data And a storage medium storing a program for storing the data.

Further, the invention described in claim 4 of the present invention is a recording medium recording the above-mentioned program, wherein a branch portion of the thinned image data is deleted.

[0010] When the cut-out image data is created using the mask, an image output means 110 for outputting the mask and the image data to another device may be provided.

[0011]

Embodiments of the present invention will be described below in detail with reference to the drawings. FIG. 1 is a functional block diagram showing the configuration of the mask producing apparatus of the present invention. FIG. 2 is a block diagram showing a schematic configuration of the mask producing apparatus of the present invention. The mask creation device according to the present embodiment includes an image input device 201 that inputs image data from an external system,
Input device 2 having a pointing device such as a mouse
02, a storage device 203 composed of a semiconductor memory, a magnetic disk, etc., and an arithmetic processing unit 20 composed of a computer, etc.
4, an output device 205 such as a data transmission device for transmitting data to another system, a display device 206 such as a color display, and a storage device such as a CD-ROM 207 for storing a program to be supplied to the arithmetic processing device 204. And a medium.

An image input device 201 converts image data into RG
B, YMCK, or digital data such as a monotone signal. Data communication for capturing image data from an external system using the Internet or the like, or a color scanner for capturing image data of a color or monochrome document. Device.

The input device 202 is for giving instructions and setting to each image data displayed on the display device 206. The storage device 203 stores the image data from the image input device 201, and processes processed edge image data, binary image data, thin line image data,
It stores various image data such as merged image data and mask data and a program to be supplied to the arithmetic processing unit 204. The output device 205 is for outputting the mask data to another device or the like. The operation of the display device 206 is controlled by the arithmetic processing device 204 and displays various image data from the storage unit 203.

The program supplied to the arithmetic processing unit 204 is stored in a CD-ROM 207, FD, MO, HD, or the like, and is set in a drive (not shown) when the computer is used to be read and used. And The method for supplying the program is not limited to the above method, and the program can be supplied using a network such as the Internet.

The arithmetic processing unit 204 is supplied from a CPU 211 for controlling the entire apparatus, a ROM 212 (read only memory) storing a program for controlling the apparatus, and a work memory and a CD-ROM 207 necessary for the operation of the program. And a RAM (random access memory) that functions by storing a program to be executed.

Next, the flow of processing will be described in detail with reference to a flowchart as shown in FIG. Step 301 (S301) First, image data is input as digital gradation data by the image input device 201 and stored in the storage device 203. At this time, if the image data is a monochrome image, the gradation data thereof is used as it is, and if the image data is a color image, only the luminance signal may be targeted. Therefore, when a color signal is input as a luminance / color difference signal, only the luminance signal may be adopted. However, when the color signal is input as three primary colors of RGB or YMC, coordinate conversion of data is performed in advance to obtain a luminance signal. Need to be kept.

Step 302 (S302) Next, the stored image data is displayed on the display device 206, and the image data can be confirmed on the display of the display device 206.

Step 303 (S303) Next, the image data is confirmed on the display device 206, and if there is no defect in the image data, edge image data which is an edge of the image data is created. Hereinafter, the process of creating the edge image data will be described in detail. The pixel value of the image data is measured, and the difference from the adjacent pixel is calculated using Equation 1.

[0019]

(Equation 1)

△ f (x, y) described in Expression 1 is a pixel value of the image data on the xy plane, and the function △ f (x, y) is the image data itself. And
This is an expression indicating that the difference between the value of the adjacent pixel and the value of the pixel can be obtained by differentiating as in Expression 1. That is, the function △ f (x, y) obtained here becomes an image representing the amount of change in the pixel value, and edge data representing the shape of a similar color as an object in the image can be obtained. .

Step 304 (S304) Next, binarized image data is created. This is because, when an area of image data is detected, only an outline is required, so that processing can be performed using a binarized image. Therefore, image data is processed into binary image data. Hereinafter, a process of creating binarized image data will be described in detail. In this example, the threshold value for binarizing the image data can be set by regarding the ratio of the number of pixels of the line drawing part and the non-line drawing part of the elements constituting the edge of the image to 1: 9 (see FIG. 4). .

In the present embodiment, the ratio of the number of images between the line drawing portion and the line drawing portion is 1: 9, but this ratio is determined by the p-tile method. The ratio changes depending on the content of the image data, and the ratio of the number of images between the line drawing portion and the line drawing portion changes depending on the content of the image data.

Step 305 (S305) Next, thin line image data is created using the edge image data and the binary image data. In other words, the outline portion 501 of the image data is set by the edge image data, and the image data is 2 by the binarized image data.
Is divided into two pieces of image data 502 and 503,
Thin line image data can be created by using these two data (see FIG. 5). The edge portion of the thinned image data often has a thickness of 2 pixels or more. However, it is assumed that the edge portion has a thickness of 1 pixel without changing the skeleton of the edge.

Step 306 (S 306) Next, unnecessary branch pixels are deleted so that the edge portion of the thinned image data always becomes a contour line forming a closed region. Pixels are deleted until there are no more points that can be deleted. That is, the number of links is 1 or 0
Is deleted. Here, the number of links indicates the number of pixels that are line drawing portions among eight pixels adjacent to a certain pixel. Then, first, four adjacent pixels (vertical and horizontal)
If there is at least one non-image portion, the pixel is a deletion candidate, and the number of pixels to be deleted is adjacent (vertically, horizontally, obliquely)
In consideration of the number of pixels and the positional relationship of the non-image portion, it is determined whether or not deletion is really possible (see FIG. 6).

Hereinafter, the step of deleting the branch portion of the thinned image data will be described in detail. 1. If the non-image portion of the adjacent eight pixels is 7 or more, the pixel becomes an end point and cannot be deleted. Therefore, the judgment is made when the non-image portion is 6 or less. Become.

2. If the number obtained by subtracting the number of non-line drawing portions obliquely from the number of non-line drawing portions of four adjacent pixels is 1, the number is deleted. The number of non-line drawing portions sandwiching the diagonal is, for example, a value counted as 1 when all three points on the left, upper left, and upper are non-line drawing portions, and the maximum value is four. For example, deletion can be determined as follows. Example 1) Of the eight adjacent pixels, the non-image portion is 6, and the adjacent 4 are
If the non-image part of the pixel is 2 and the non-image part sandwiching the diagonal is 0, it cannot be deleted. Example 2) Of the eight adjacent pixels, the non-image area is 5, and the adjacent 4
If the non-image part of the pixel is 2 and the non-image part sandwiching the diagonal is 0, it cannot be deleted. Example 3) Of the eight adjacent pixels, the non-image part is 4, and the adjacent 4
When the non-image part of the pixel is 2 and the non-image part sandwiching the diagonal is 1, it is a deletion capability. Example 4) Of the eight adjacent pixels, the non-image portion is 6, and the adjacent 4 are
If the non-image part of the pixel is 3 and the non-image part sandwiching the diagonal is 1, it cannot be deleted.

In the thin line image data to be set, specifically, a Z-shaped operation from the upper left and a reverse scan from the lower right are alternately repeated to determine a pixel to be deleted. At this time, it is checked whether or not only the upper and lower portions of the four pixels are non-image portions when viewed from the upper left, and when left and right are scanned in the opposite direction, the left and right and upper and lower portions are checked. Then, the process is continued until there are no more deletable points.

Step 307 (S307) Next, the areas set in the above steps are merged with areas of similar colors and grouped, and the subdivided areas are reduced to a certain number of areas. More specifically, the closed area set in the above process is detected by scanning, the color status of the area is calculated and stored, and areas having similar colors are merged. The number of regions after the merging is preferably merged until the number of regions becomes 5 to 10.

Step 308 (S 308) Next, by storing the merged area set in the above process as image mask data in the storage device 203,
This processing step ends. Note that the mask data is sent to the next step, and is used when creating cutout image data or when changing the background of the image data.

The storage medium storing the program according to the present invention constitutes the present invention. Then, by reading the program from the storage medium into the system or the device, the system or the device operates in a predetermined method. In addition,
In this example, the medium storing the above program is a CD-R
Although OM is used, the system can be used as a medium on which a program is recorded from a network such as FD, MO, or the Internet.

[0031]

As described above, in the mask forming apparatus and the recording medium on which the mask forming program is recorded according to the present invention, the mask can be easily formed without making detailed settings in the mask forming step, and the work time is remarkable. Shortening can be achieved.

Further, a mask can be easily formed from image data of a photograph taken in a natural environment, and a mask for an image region having a complicated shape can be easily formed.

[Brief description of the drawings]

FIG. 1 is a functional block diagram showing a configuration of a mask producing apparatus according to the present invention.

FIG. 2 is a block diagram illustrating a schematic configuration of a mask producing apparatus according to the present invention.

FIG. 3 is a flowchart showing a flow of the mask producing apparatus of the present invention.

FIG. 4 is a density histogram diagram used when generating binarized image data.

FIG. 5 is schematic thinned image data displayed on a display.

FIG. 6 is schematic region fixed image data displayed on a display.

[Description of Signs] 101 ... Image Input Device 102 ... Storage Unit 103 ... Edge Image Creation Unit 104 ... 2
Valued image creation means 105 ・ ・ ・ Thinned image creation means 106 ・ ・ ・ Image deletion means 107 ・ ・ ・ Color quantization means 108 ・ ・ ・ Mask creation means 109 ・ ・ ・ Display means 110 ・ ・ ・ Image output means 201 ... Image input device 202 ... Input device 203 ... Storage device 204 ... Processing device 205 ... Output device 206 ... Display device 207 ... CD-ROM 211 ... C
PU 212 ・ ・ ・ RAM 213 ・ ・ ・ R
OM

Claims (4)

[Claims] 1. An image data input unit, an edge image creating unit for creating edge image data from the image data, and a binary image creating unit for creating binary image data by binarizing the image data. A thinned image creating means for creating thinned image data from the binary image data and the edge image data; a combined image creating means for combining thinned image data to create combined image data; and the combined image data A mask creating means for creating a mask from the data; and a storage means for storing the data. 2. An apparatus according to claim 1, further comprising an image deleting means for deleting an end portion such as a branch portion of said thinned image data. 3. Image data is input, edge image data is created from the image data, the image data is binarized to generate binarized image data, and the edge image data and the binarized image data are generated. A recording medium storing a program for causing thinned image data to be created, merging the thinned image data to create merged image data, creating a mask from the merged image data, and storing the data; . 4. The recording medium according to claim 3, wherein an end portion such as a branch portion of said thinned image data is deleted.