JP2003030669A - Image preparation method and system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image preparation method and system capable of preparing a pattern image which is not identical with a target pattern image though provided with a feature similar to it. SOLUTION: A (reduced) preparation image area in the same size as a (reduced) model image having a pattern to be a model as the area of an image to be prepared is prepared, and the pixel value of an outermost circumferential part in the model image is slightly changed and supplied to each pixel of the pixel imparting part of the preparation image area (a). For each pixel of a pixel decision part in the prepared image area, a mask is arranged on the preparation image area, the mask in the same shape as the above mask is arranged on the model image, and the similarity of a masked area on the preparation image area and the masked area on the model image is obtained while keeping the position of the mask on the preparation image area fixed and moving (b-e) the mask on the model image pixel by one pixel. The pixel whose positional relation with the mask (e) on the model image which is judged as most similar is the same as the positional relation between the mask on the preparation image area and the pixel to be decided is allocated as the pixel on the preparation image area.

Description

Detailed Description of the Invention

[0001]

The present invention uses a model image having a pattern and has a texture similar to that of the model image.
The present invention relates to a technique for creating an image having a slightly different texture.

[0002]

2. Description of the Related Art Conventionally, various pattern images have been used to decorate the surface of building materials and the like. Such a pattern image is obtained by correcting a photographed image and creating it or artificially creating it by a computer operation. In particular, when the pattern is an abstract pattern image, there is a demand to create several types of pattern images that have the characteristic (or texture) but are not the same pattern. I.e. not the same,
There is a desire to increase the variations of images with similar characteristics.

In order to increase the variation of images having similar characteristics as described above, conventionally, an operator uses image creating software to directly create a target image while seeing a target pattern image or create a target image. By modifying it, a similar pattern image was created.

[0004]

However, in the above-described conventional pattern image creating method, since it is performed based on the subjectivity of the operator, the created pattern image loses the target feature of the pattern image, It often happens that the pattern gives the person a completely different impression.

In view of the above points, the present invention provides an image creating method and system having the same characteristics as a target pattern image, but capable of creating non-identical pattern images. It is an issue.

[0006]

In order to solve the above problems, in the present invention, a created image area of the same size as the model image is prepared as an area of the created image, and a predetermined number of pixels including the outermost periphery in the model image are prepared. Attribute information to each pixel corresponding to the created image area based on the attribute information of the created image area, the created image area by determining the attribute information of each pixel other than the pixel already provided attribute information In particular, the attribute information of each pixel is determined by arranging a mask having a predetermined shape on the created image area, arranging a mask having the same shape as the mask on the model image, and While the mask position is fixed, the mask on the model image is moved pixel by pixel, and the similarity between the masked area on the created image area and the masked area on the model image is obtained. The attribute information of pixels having a positional relationship with the mask on the model image determined to have the highest degree of similarity is the same as the positional relationship between the mask and the pixel to be determined on the created image area. It is characterized in that it is performed by assigning it as attribute information of a pixel on the created image area. According to the present invention, when creating a created image of the same size as the pattern image to be the model, the attribute information of the pixels of the same coordinates of the model image is given to the surroundings of the created image with slightly different attributes. Other than the surroundings, the determination is made based on the similarity of the masked areas in both the created image and the model image, and in particular, the attribute information of the pixels around the created image is copied from the corresponding pixel of the model image. Rather, since it is slightly different, it is possible to obtain a slightly different image while leaving the features of the model pattern image.

[0007]

DETAILED DESCRIPTION OF THE INVENTION Embodiments of the present invention will be described in detail below with reference to the drawings. FIG. 1 is a flowchart showing an outline of the image creating method according to the present invention. First, an image having a pattern as a model (hereinafter referred to as a model image) is input (step S1).

Next, a resolution reduction rate, which is a rate at which the resolution is reduced, is set for the input model image (step S2). The resolution reduction rate set here sets how many pixels of the original image are dropped to one pixel. This is done mainly for the purpose of reducing the calculation amount by reducing the number of pixels.

Next, a reduced model image in which the resolution of the model image is reduced is created at the set resolution reduction rate (step S3). The reduced model image is created by giving an average value of horizontal r × vertical r pixels on the model image as a pixel value of one pixel of the reduced model image, where r is the resolution reduction rate. At this time, each pixel of the reduced model image has the given average value as its pixel value, and
Which r × r of the model image the pixel is as the pixel specifying information
It is recorded whether it is obtained based on the number of pixels.
This is used later when restoring to the original size. In the reduced created image, the pixel value and the pixel specifying information are collectively referred to as pixel attribute information.

Then, a reduced created image area having the same size as the reduced model image is prepared (step S4). This reduced created image area is an area for creating a reduced created image in which the resolution of the image to be finally created (hereinafter referred to as created image) is reduced, and is secured in the image memory. The reduced created image area secured here is shown in FIG. The reduced created image area shown in FIG.
Pixels × vertical sy pixels are secured, which means that the reduced model image has a size of horizontal sx pixels × vertical sy pixels.

Next, attribute information is given to the pixels located at the outermost peripheral portion in the reduced created image area as shown in FIG. 2A based on the attribute information of the pixels of the corresponding portion of the model image ( Step S5). Specifically, of the attribute information of each pixel located at the outermost periphery of the reduced model image, the pixel value is slightly changed and given, and the pixel specifying information is copied. Since the reduced model image and the reduced created image area have exactly the same size and the same number of pixels, the pixel values of the pixels having the same coordinates may be slightly changed and the pixel specifying information may be simply copied. To change the pixel value, a maximum changeable value is set in advance, and −1 ≦ RANa
The random number RANa generated in the range of ≦ 1 is changed by the value obtained by multiplying the maximum value. The outermost peripheral portion is a portion shown by hatching in FIG. Here, two pixels including the outermost circumference are the outermost circumference. Here, the reason that the outermost peripheral portion is two pixels is that it is necessary for the calculation of the degree of similarity using a mask having a shape described later. As shown in FIG. 2, the reduced created image area includes a pixel-added portion that is the outermost peripheral portion and other pixel-determined portions. The attribute information of the pixel of the pixel addition portion is obtained by adding the attribute information based on the attribute information of the pixel at the same position in the reduced model image. For the attribute information of the pixel of the pixel determination portion, the following step S6 is performed. Determined by The reduced created image is obtained by giving the attribute information to each pixel in the reduced created image area.

After the attribute information about the pixels in the pixel-added portion of the reduced created image area is obtained, the value of each pixel in the pixel determination portion of the reduced created image area is then determined to obtain the reduced created image. Create (step S6). There are various conceivable orders for determining the pixels in the pixel determining portion, but in the present embodiment, the order is determined from the pixel at the upper left corner shown by hatching in FIG.
To determine the pixel at the upper left corner, a mask corresponding to 12 pixels as shown in the upper left corner is used.
When such a mask is arranged at a position for determining the pixel at the upper left end of the pixel determining portion, it is projected from the pixel determining portion by two pixels in the upward and leftward directions, as shown in FIG. 3A. . It is for this reason that the attribute information for two pixels is previously added to the periphery as the pixel addition portion.

In order to determine the upper left pixel shown by hatching in FIG. 3 (a), specifically, a mask having the same shape as this mask is placed at positions corresponding to all the pixels of the reduced model image. And find the similarity of the masked area. Then, the pixel at the position corresponding to the mask on the reduced model image determined to have the highest degree of similarity is determined as the upper left pixel shown in FIG. 3A, and the attribute information is recorded. As a mask on the reduced model image, first, as shown in FIG.
It is arranged at the position shown in (b), and the degree of similarity between the masked area and the masked area shown in FIG. 3 (a) is obtained. Next, as shown in FIG. 3C, the mask for one pixel is shifted to the right, and the degree of similarity between the masked area and the masked area shown in FIG. 3A is obtained. In the same way, we perform processing to find the similarity for each pixel position,
When the mask reaches the right edge on the reduced model image,
Move the mask down one line to the left edge as shown in (d),
The degree of similarity between the masked area and the masked area shown in FIG. 3A is obtained. In this way, the degree of similarity between the masked area and the masked area shown in FIG. 3A is obtained for the positions corresponding to all the pixels on the reduced model image. For example, when it is determined that the similarity to the masked area at the position shown in FIG. 3E is the highest, the pixels shaded with diagonal lines in FIG.
The pixel is assigned as the upper left pixel shown in FIG. That is, the attribute information of the pixel shown by hatching in FIG. 3E is copied to the pixel at the upper left corner shown in FIG.

Here, in the present invention, a function for calculating the similarity between the masked area in the reduced created image area and the masked area in the reduced model image will be described. As this function, any function may be used as long as it can determine the similarity between the pixel existing at the mask position on the reduced created image area and the pixel existing at the mask position on the reduced model image. In the embodiment, the one shown in the following [Formula 1] is used.

[Formula 1] V = Σi (Rs ² + Gs ² + Bs ² ) where i = 1 to 12 (number of pixels)

In the above [Formula 1], V is an evaluation value for evaluating the degree of similarity, and Rs, Gs, and Bs are the pixels on the reduced image area when RGB color images are used. It is the difference between the pixel values of the respective color components of the pixels on the reduced model image. Therefore, the smaller the value of the evaluation value V, the closer the value is, and it is determined that the degree of similarity is high. Although i = 1 to 12 in the above example,
This is the case where a standard mask as shown in FIG. 3 is used, and it depends on the mask shape.

When the pixel at the upper left corner as shown in FIG. 3A is determined, as shown in FIG. 4A, the mask on the reduced image area is shifted to the right by one pixel and the same process is performed. To do. At this time, the pixels used to obtain the degree of similarity of the masked area are 11 pixels at the outermost peripheral portion of the reduced created image area and the pixel at the upper left corner of the pixel determination portion whose attribute information has already been determined (see FIG. 4). The value of (circle mark in (a)) is used.

Similarly, the pixels in the first row of the pixel determining portion are determined. FIG. 4B shows the position of the mask when determining the rightmost pixel in the first row. Figure 4 (b)
Also in the above, the values of the pixels indicated by the circles have already been determined. When the rightmost pixel in the first row is determined, the pixels in the second row are determined from the right edge instead of the left edge. At this time, as shown in FIG. 4C, the mask used has a shape which is left-right inverted from that used for determining the pixels in the first row. It should be noted that in FIG. 4C as well, the ◯ mark indicates a pixel whose value has already been determined. When the mask as shown in FIG. 4C is used, the mask having the same shape as that shown in FIG. 4C is naturally used as the mask on the reduced model image for obtaining the similarity. Using such a mask, the pixels on the second row are sequentially determined from the right side. Regarding the third line of the pixel determination part, the pixel at the left end is determined using the mask as shown in FIG.
That is, the pixels are determined in the left-right opposite directions by using the mask that is horizontally inverted for each row. Although it is possible to determine all the rows from one direction at all times, in such a case, there may occur a phenomenon in which an unintended flow like a diagonal flow appears on the created image. . In order to eliminate such a problem, it is desirable to determine pixels in a zigzag manner as in the example of FIG.

From the first row to the third row from the bottom of the pixel determining portion, the pixels are determined using a mask of 12 pixels as shown in FIGS. 3 and 4, but the pixel determining portion For the two rows from the bottom, masks having different shapes as shown in FIG. 5 are used. In FIG. 5, the shaded areas are the pixels to be determined, and the circled ones are the already determined pixels. A mask as shown in FIG. 5A is used to determine the pixels in the second row from the bottom. This mask has a shape in which, in addition to the 12 pixels shown in FIGS. 3 and 4, 5 pixels located two rows below the pixel to be determined are added. Further, in order to determine the pixel on the bottom row, a mask as shown in FIG. 5B is used. This mask has a shape in which, in addition to the 12 pixels shown in FIGS. 3 and 4, 10 pixels in the lower two rows of the pixel to be determined are added. The determination of the degree of similarity can be performed by calculating the evaluation value as in [Equation 1].
However, in [Equation 1], i = 1 to 17 in the mask shown in FIG. 5A, and i = 1 to 22 in the mask shown in FIG. 5B.

The reason why the mask having the shape as shown in FIG. 5 is used in determining the pixels for the lower two rows is to reflect the value of the pixel in the pixel-added portion. The pixels in the pixel-added portion are obtained by slightly changing the values from the corresponding positions in the reduced model image as described above. Therefore, reflecting the values of these pixels means that the joint between the lower side of the pixel determination portion and the pixel addition portion is inconspicuous. If only the masks shown in FIGS. 3 and 4 are used and the pixels in the pixel-added portion are not reflected, it seems to the viewer that there is a step between the lower side of the pixel determination portion and the pixel-added portion. It will be. It should be noted that the upper side and the left and right of the pixel determination portion sufficiently reflect the pixel values of the pixel addition portion, as can be seen from the examples shown in FIGS. 3 and 4.

When the reduced created image is obtained by deciding each pixel of the pixel decision part, next, based on the reduced created image, a created image having the same size and the same resolution as the original model image is created ( Step S7). The reduced image is
Since it is created as described above, as its attribute information, which pixel of the reduced model image each pixel is assigned is recorded. Also, each pixel on the reduced model image is
As the attribute information, which r × r pixels of the model image are obtained is recorded. That is, it is possible to know which r × r pixels on the model image correspond to each pixel on the reduced model image. Therefore, each pixel on the reduced created image corresponds to r × r pixels on the model image. By allocating the pixels of, the created image having the same size and the same resolution as the model image is created.

In the process of step S7, when the created image is created from the reduced created image, the corresponding pixel on the model image is obtained from the reduced created image through the reduced model image, and that pixel is directly assigned to the created image. I did
At this time, when the resolution reduction rate is small (r = 3 or so), there is not much problem, but when the resolution reduction rate is large, it is like a lump for each number of pixels corresponding to the resolution reduction rate. Will occur. For example, if the resolution reduction rate r = 40, then 40 × 40
Blocks composed of pixels will be arranged on the created image. At this time, in the portion corresponding to the joint of 40 × 40 pixels, the continuity is not taken into consideration in the arrangement of the adjacent pixels, so that the joint becomes conspicuous. As a result, the entire created image looks like an aggregate of blocks of 40 × 40 pixels.

Therefore, in the process of step S7, the above problem is solved by performing the following process. When the resolution reduction rate r = 40, originally 40 × 40 pixels should be allocated on the created image, but 46 × 46 pixels on the model image are allocated on the created image. In other words, the upper, lower, left, and right 3 pixels are extracted and allocated in excess. The extra extracted pixels are combined with other pixels assigned on the created image.
The synthesis rate at this time is set to a value that becomes smaller as it gets closer to the end of the block of 46 × 46 pixels, and the synthesis rate is changed using a random number. The synthesis rate α is calculated by the following [Formula 2].

[Formula 2] α = DI (X) + RANb

In the above [Formula 2], DI (X) is
Is a function that increases with the distance from the edge of the block,
It takes a value from 0 to 1. RANb is -0.5 to 0.
It is a random number that takes a value of 5. After the calculation, α is corrected to have a value of 0 to 1. In addition, here, 3
The extra pixels are extracted and assigned, but the number of extra pixels is also changed according to the resolution reduction rate. As described above, a created image which is a different image can be obtained while leaving the same characteristics as the model image. An effective method for creating the created image will be described below.

In the above example, in order to reduce the amount of calculation, the reduced image with reduced resolution is generated and then the generated image is generated, but in this case, the problem as shown in FIG. 6 occurs. Occurs. FIG. 6A is an enlarged view of a part (three pixels) of the reduced created image, and FIG. 6B is a partially enlarged view of the created image. Note that FIG. 6 shows a case where the resolution reduction rate r = 3. When r = 3, one pixel on the reduced created image is restored to 9 (3 × 3) pixels on the created image. In that case, the array of 9 pixels is
It is restored in the same state as on the model image. Therefore, FIG.
When the same pixel on the reduced created image is selected three times in succession as shown in (a), the pattern repeats in a narrow range on the created image when restored. this is,
This is because a specific pixel is repeated, as can be seen from the pixels shaded in FIG. 6B.

Therefore, in the present invention, the above-mentioned problem does not occur by not selecting the same pixel as a neighboring pixel. FIG. 7 is a partially enlarged view of the reduced created image. In particular, FIG. 7A shows a case where pixels are determined from left to right, and FIG. 7B shows a case where pixels are determined from right to left. When determining the pixels from the left to the right, when determining the pixels indicated by hatching in FIG. 7A, the pixels should not be the same as the four pixels indicated by the circles. In determining pixels indicated by hatching, the similarity between the masked area on the reduced created image and the masked area on the reduced model image is determined in the same manner as described in the above example. Seeking,
The pixel with the highest degree of similarity is selected, but here, the pixel on the selected reduced model image is not the pixel shown by diagonal lines as it is, but is the same as the four pixels shown by ○. Check if it isn't. As a result, the same pixel as a neighboring pixel is not selected, and the above problem is solved. Further, when pixels are determined from the right to the left, the positional relationship as shown in FIG. 7B, that is, the processing for preventing overlapping with respect to the pixels symmetrical to the case of FIG. 7A is performed. Done.

Next, a system configuration for executing the above-mentioned image creating method will be described. FIG. 8 is a block diagram showing an embodiment of the image creating system according to the present invention. In FIG. 8, the image input means 1 has a function of inputting a model image. As the image inputting means 1, when a model image is already prepared as digital data, it can be realized by a reading device capable of reading an electronic recording medium recording the digital data, and the model image is a physical medium such as paper. If it is prepared by (1), it can be realized by an optical reading device such as a scanner.

The parameter setting means 2 is for setting the resolution reduction rate r in step S2 of FIG. 1, and can be realized by an input device such as a mouse or a keyboard. The parameter setting means 2 is also used to set various necessary parameters such as setting random numbers.

The mask shape storage means 3 stores the shapes of the masks to be arranged on both the reduced created image and the reduced model image for pixel determination in the pixel determination portion, as described in step S6 of FIG. It is for memory.

The arithmetic and control unit 4 plays a central role in the image forming system according to the present invention, and has a pixel determining unit 4a and a resolution converting unit 4b. The pixel determining unit 4a has a function of executing the processes of steps S4 to S6 of FIG. 1, and secures an area for creating a reduced created image on the image memory 5 to determine pixels. The resolution conversion means 4b has a function of executing the processing of steps S3 and S7 of FIG. 1, and creates a reduced model image from the model image according to the set resolution reduction rate and also creates it from the reduced creation image. Create an image. The arithmetic and control unit 4 is realized by a CPU and a memory of a computer, and the pixel determining means 4a and the resolution converting means 4b which are specific functions are realized by a dedicated software program installed in the computer.

The image memory 5 is a storage area for creating a reduced created image, and secures a storage area of the same size as the reduced model image created according to the resolution reduction rate set for the model image, and performs calculation. The pixel attribute information determined by the control device 4 is stored.

Although the preferred embodiments of the present invention have been described above, the present invention is not limited to the above embodiments, and various modifications can be made. For example, in the above embodiment, in order to reduce the load of the arithmetic processing, the model image is reduced and
After creating the reduced created image of the reduced size, the resolution is restored to create the created image. However, if the calculation processing load is not taken into consideration, the image memory will be created with the same size as the model image. The image area is secured, and the attribute information of the pixel at the same position of the model image is given to the outermost peripheral portion of the created image area by slightly changing the pixel value. The pixels may be determined by obtaining the degree of similarity between the area and the masked area on the model image.

[0034]

As described above, according to the present invention,
A prepared image area of the same size as the model image is prepared as an area of the created image, and attribute information is given to each corresponding pixel of the created image area based on the attribute information of a predetermined number of pixels including the outermost circumference in the model image, A created image is created by determining the attribute information of each pixel other than the pixels to which the attribute information has already been given in the created image area. In particular, the determination of the attribute information of each pixel is performed by setting a predetermined shape on the created image area. A mask of the same shape as the mask is placed on the model image, and the mask on the model image is moved one pixel at a time while the mask on the created image area is fixed. The similarity between the masked area on the area and the masked area on the model image is obtained, and the positional relationship between the mask on the model image determined to have the highest similarity is the mask in the created image area. The attribute information of a pixel having the same positional relationship as that of the pixel to be determined is assigned as the attribute information of the pixel in the created image area. It is possible to obtain a slightly different image while leaving the above.

[Brief description of drawings]

FIG. 1 is a flowchart of an image creating method according to the present invention.

FIG. 2 is a diagram showing a reduced created image area secured on an image memory.

FIG. 3 is a diagram showing a relationship between a reduced created image area and a reduced model image, and a mask arranged thereon.

FIG. 4 is a diagram showing a relationship between a reduced created image area and a mask when the order of pixel determination is changed left and right alternately.

FIG. 5 is a diagram showing a relationship between a reduced image area and a mask when performing a seamless process of a lower portion of a pixel determination portion.

FIG. 6 is a diagram showing a pixel relationship when the same pixel is continuously selected on a reduced created image.

FIG. 7 is a diagram showing a positional relationship between a pixel to be determined and a pixel whose duplication should be prohibited.

FIG. 8 is a configuration diagram showing an embodiment of an image creating system according to the present invention.

[Explanation of symbols]

1. Image input means 2. Parameter setting means 3 ... Mask shape storage means 4 ... Arithmetic control device 4a ... Pixel determining means 4b ... Resolution conversion means 5 ... Image memory

   ─────────────────────────────────────────────────── ─── Continued front page    F term (reference) 5B057 AA01 CA08 CA12 CA16 CB08                       CB12 CB16 CC02 CD05 CE08                       DA07 DB02 DB09 DC34 DC36                 5B080 GA22 GA29                 5L096 BA08 DA01 EA03 FA69 GA10                       JA03

Claims (5)

[Claims] 1. A method of using a model image having a desired pattern to create an image expressing a pattern equivalent to the pattern expressed by the model image, which is an image to be created. The prepared image area having the same size as the model image is prepared as the area of the model image, and the corresponding portion of the created image area based on the attribute information of the pixels located in the outermost peripheral portion including the outermost periphery in the model image. Pixel information giving step of giving attribute information to each pixel of the pixel giving portion, and each pixel of the pixel determining portion which is an area other than the pixel giving portion given the attribute information in the pixel information giving step in the created image area Pixel information determining step of determining attribute information of the pixel information determining step, and determining each pixel in the pixel information determining step includes arranging a mask having a predetermined shape on the created image area, and forming the same shape as the mask. A mask having a circular pattern is arranged on the model image, and the mask on the model image is masked on the model image while moving the mask on the model image by one pixel while the position of the mask is fixed on the model image. The positional relationship between the area and the mask on the model image for which the similarity between the masked area on the model image is determined and the similarity is determined to be the highest, and the pixel to be determined as the mask on the created image area And an attribute information of a pixel having the same positional relationship as that of the attribute information of the pixel on the created image area. 2. When determining each pixel of the pixel determining portion,
For the last predetermined number of rows of the pixel determining portion, a mask having a shape different from the mask shape is used, and as the pixels to be masked by the mask, the predetermined number of pixel applying portions located below the pixel determining portion are used. The image creating method according to claim 1, wherein the pixels of the row are used. 3. A method of using a model image having a desired pattern to create an image expressing a pattern equivalent to the pattern expressed by the model image, comprising the step of setting a resolution reduction rate. A step of creating a reduced model image in which the resolution of the model image is reduced according to the set resolution reduction rate; a step of preparing a reduced created image area of the same size as the reduced model image; A pixel information giving step of giving attribute information to each pixel of a pixel-added portion which is a corresponding portion of the reduced created image area, based on attribute information of pixels located in the outermost peripheral portion including the outer circumference; A pixel information determining step of determining attribute information of each pixel of a pixel determining portion which is an area other than the pixel assigning portion to which the attribute information is given in the pixel information giving step; Creating a created image of the same size as the original model image based on the attribute information of each pixel of the reduced created image obtained in the pixel information determining step, and determining each pixel in the pixel information determining step. Is arranged a mask of a predetermined shape on the reduced created image area, a mask of the same shape as the mask is placed on the reduced model image, the position of the mask on the reduced created image area is fixed, While moving the mask on the reduced model image by one pixel, the similarity between the masked region on the reduced created image region and the masked region on the reduced model image is obtained, and the similarity is highest. The attribute information of the pixel having the positional relationship with the mask on the reduced model image determined to be the same as the positional relationship between the mask and the pixel to be determined on the reduced created image area. Is performed as attribute information of pixels on the reduced created image area, and the step of creating the created image is performed on the reduced model image assigned to each pixel according to the attribute information of the reduced created image. The created image is created by specifying a plurality of pixels on the corresponding model image via pixels and arranging the plurality of pixels on the model image in correspondence with each pixel of the reduced created image. An image creation method characterized by the fact that there is. 4. An image input means for inputting a model image having a desired pattern, and a prepared image area having the same size as the model image as an area of the created image which is an image to be created. The attribute information is given to each pixel of the pixel-added portion which is the corresponding portion of the created image area based on the attribute information of the pixel located in the outermost peripheral portion including And a pixel determining unit that determines attribute information of each pixel of a pixel determining portion that is an area other than the pixel-added portion, wherein each pixel is determined by the pixel determining unit in a predetermined shape on the created image area. The mask having the same shape as the mask is placed on the model image, and the mask on the model image is moved by one pixel while the position of the mask on the created image area is fixed. While, obtains the similarity of the masked area on the masked area the model image by the creation image area, the positional relationship between the mask on the model image in which the similarity is determined to highest,
The attribute information of a pixel having the same positional relationship as the positional relationship between the mask and the pixel to be determined on the created image area is assigned as the attribute information of the pixel on the created image area. Characteristic image creation system. 5. A step of preparing, in a computer, a created image area having the same size as a model image as an area of an created image which is an image to be created, and attributes of pixels located in an outermost peripheral portion including an outermost circumference in the model image. A pixel information giving step of giving attribute information to each pixel of a pixel giving portion which is a corresponding portion of the created image area based on information;
The pixel information determination step of determining the attribute information of each pixel of the pixel determination portion, which is an area other than the pixel addition portion to which the attribute information is given in the pixel information addition step, is executed, and the determination of each pixel in the pixel information determination step is performed. , A mask of a predetermined shape is placed on the created image area, a mask of the same shape as the mask is placed on the model image, and the position of the mask on the created image area is fixed, and the mask is placed on the model image. While moving the mask of 1 pixel by 1 pixel, the degree of similarity between the masked area on the created image area and the masked area on the model image is calculated, and the model image determined to have the highest similarity is calculated. Attribute information of pixels having a positional relationship with the mask that is the same as the positional relationship between the mask on the created image area and the pixel to be determined on the created image area. A program that is performed by assigning it as attribute information of the pixel.