JP2001352454A - Image conversion method and device, and computer- readable recording medium with image conversion program recorded thereon - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image conversion device that converts a color image, expressed in colors into a monochromatic image so as not to lose easy-to-view performance. SOLUTION: A scanner reads a multi-color print original and a computer receives an image (S1). Colors used in the received image are discriminated (S2). The gray scale after conversion is decided, depending on the color information used in the image (S3). The received color image is converted into a monochromatic image with the decided gray scale (S4), and a display device displays (outputs) the image after the conversion (S5).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image conversion method and apparatus, and a computer-readable recording medium storing an image conversion program, and more particularly to an image conversion method for converting a multicolor printed document image into a readable monochrome image. The present invention relates to an apparatus and a computer-readable recording medium on which an image conversion program is recorded.

[0002]

2. Description of the Related Art In an electronic book producing apparatus, a digital copying machine, an electronic filing system, or the like, a color input image may be converted into a monochrome image and then output. Generally, conversion from a color image to a monochrome image is performed by extracting a luminance component from the color image. The following equation (1) is an equation for extracting a luminance component (I) from a red (R) component, a green (G) component, and a blue (B) component of a color image.

I = 0.299R + 0.587G + 0.114B (1) Equation (1) is determined based on human visual characteristics, and by using equation (1), a full-color image such as a photograph can be naturally converted. It can be converted to a monochrome image with a simple feeling.

In digital copiers and the like, in addition to such a method in which the arithmetic mean of each of the R, G, and B components is used as a luminance component, a color image is converted into a monochrome image by using the G component itself as a luminance component. The method of doing is also adopted.

[0005] However, when the arithmetic mean value or the G component is used as the luminance component, a colored portion, particularly a color portion such as yellow or green, is converted lighter than black. For this reason,
The impression given to the viewer of the document may be different from that of the color image.

When arithmetic averaging is performed, the difference in color before conversion may not be reflected after conversion. For example, when converting multi-colored originals, such as textbooks and learning reference books, in which important words are emphasized in color, and graphs or diagrams that are color-coded for each item, into monochrome images, the parts to be emphasized are conversely lightened. There is a problem that all colors are converted to the same density and cannot be distinguished from others.

In order to solve such a problem, for example,
Japanese Patent Application No. 0-13621 proposes a method of automatically determining the color of an image and converting the image into a natural monochrome image. According to this, the colors used in an image are determined based on the distribution of hue, saturation, and lightness, and the mixture ratio of the color components is automatically determined according to the determined colors. It can be converted to a monochrome image. Further, if the user manually specifies the mixture ratio, the image can be converted into a monochrome image as desired by the user.

Japanese Patent Application Laid-Open No. Hei 7-121733 proposes a method in which a color is determined for each area on a document, and the size of a colored character is represented differently from the others.
According to this method, a group of pixels on a document image is divided into meaningful small regions, and the size of the characters is changed according to the color of the characters in the small regions to convert them into a monochrome image.

[0009]

However, Japanese Patent Laid-Open Publication
In the color discrimination method proposed in Japanese Patent No. -13621, a histogram of hues weighted by saturation is obtained, and a hue having the maximum value is set as a representative hue. For this reason, it is not possible to determine two or more colors. Also, since the colors used are selected from the six colors of red, yellow, green, light blue, blue, and magenta, and the mixture ratio of R, G, and B is determined, it is appropriate for halftone colors. In some cases, a high mixing ratio cannot be obtained.

The method proposed in Japanese Patent Application Laid-Open No. 2000-13621 in which the mixing ratio of R, G, and B can be freely changed has the following problems. For example, red and black 2
When converting a color printed image to a monochrome image, R, G, B
If the mixture ratio is set to 0: 0.5: 0.5, the portion written in red can be converted to a darker portion. Similarly, when converting a three-color printed image of red, blue, and black into a monochrome image, R, G,
When the mixture ratio of B is set to 0: 1: 0, the portion written in red and blue can be made darker, and when the mixture ratio of B becomes 0.3: 0.7: 0, blue becomes darkest and red becomes slightly darker. Adjustments such as thinning can also be made.
However, since there are infinite combinations of colors, it is difficult to prepare all of these mixing ratios in advance. Further, the adjustment of the density cannot be performed easily. Further, in the case of a document using three or more colors of ink, it is difficult to calculate the mixture ratio itself.

Also, the method proposed in Japanese Patent Application Laid-Open No. Hei 7-121733, in which the color is determined for each area on a document and the size of the colored character is changed to represent the character, has the following problems. is there. For example, in a document such as a report, if the heading is red and the subheading is blue, those areas are detected, and the effect of making the character easier to read is obtained by enlarging the characters. However, in the case of a document such as a textbook or learning reference book where some parts of the paragraph are written in red,
It is difficult to determine the color for each area, and if the character size is changed, the impression and layout of the entire document may be different from those before conversion. Further, when a color-coded graph or figure is converted to monochrome, there is a problem that it becomes impossible to distinguish each color.

SUMMARY OF THE INVENTION An object of the present invention is to provide an image conversion method and apparatus capable of converting a color image represented by a plurality of colors into a monochrome image without impairing the visibility, and an image conversion method. An object of the present invention is to provide a computer-readable recording medium on which a program is recorded.

Another object of the present invention is to record an image conversion method and apparatus and an image conversion program which do not impair highlighting even when an image highlighted by using color is converted into a monochrome image. To provide a computer-readable recording medium.

[0014]

An image conversion method according to an aspect of the present invention converts a color image into a monochrome image. The image conversion method includes a step of determining a plurality of colors included in the color image, a step of determining a converted density of each pixel included in the color image based on the color information, and a step of determining a color component of each pixel of the color image. To the determined concentration.

For each of the plurality of colors included in the color image, the converted density is determined from the color information. Therefore, even when a plurality of colors having the same lightness are mixed, it is possible to automatically determine the converted density of each color and convert the color into a monochrome image that does not impair the visibility even after the conversion.

An image conversion method according to another aspect of the present invention comprises:
Convert a color image to a monochrome image. The image conversion method includes a step of determining a plurality of colors included in the color image, a step of receiving, from a user, an instruction on a density after the conversion for each of the plurality of colors, Conversion into the determined density.

For each of the plurality of colors included in the color image, the user specifies the converted density, and the color components are converted to the specified density. For this reason, the user can freely specify the converted density of each color, so that the monochrome image can be converted as desired.

Preferably, the step of converting includes a step of converting to a determined or designated density, and a step of further converting the converted density using a weighting function having a larger value for a pixel having higher saturation. .

Colors that appear light before conversion are also converted lightly after conversion. For this reason, a light color, a ground color, or the like painted on the figure can be converted with a natural density.

An image conversion method according to another aspect of the present invention comprises:
Convert a color image to a monochrome image. The image conversion method includes a step of determining a color included in the color image, a step of extracting a character region for each determined color, and a step of determining a character decoration method based on color information for each determined color. And applying the determined decoration to the character area and converting it to a monochrome image.

A different decoration is applied to the character area for each character color. For this reason, even when a character highlighted in a color image is converted to a monochrome image, the character can be emphasized.

An image conversion method according to another aspect of the present invention comprises:
Convert a color image to a monochrome image. The image conversion method includes a step of determining a color included in the color image, a step of extracting a character area for each of the determined colors, a step of receiving, from the user, an instruction regarding a decoration method for each of the determined colors, Decorated text area,
Converting to a monochrome image.

The user can specify a decoration method for each character color. Therefore, the user can decorate the character area as desired and convert it to a monochrome image.

An image conversion method according to another aspect of the present invention converts a color image into a monochrome image. The image conversion method includes a step of determining a color included in a color image, a step of extracting a region having the color for each determined color, and determining a texture based on color information for each determined color. And a step of applying the determined texture to the area and converting the area into a monochrome image.

A different texture is applied to an area included in a color image for each color, and the area is converted to a monochrome image. Therefore, even when an image such as a graph expressing a difference in data by a difference in color is converted to a monochrome image, the difference in data can be appropriately represented.

An image conversion device according to still another aspect of the present invention converts a color image into a monochrome image. The image conversion device includes: a unit for determining a plurality of colors included in the color image; a unit for determining a converted density based on color information for each pixel included in the color image; Means for converting the color components of the pixels into the determined density.

For each of a plurality of colors included in the color image, the converted density is determined from the color information. Therefore, even when a plurality of colors having the same lightness are mixed, it is possible to automatically determine the converted density of each color and convert the color into a monochrome image that does not impair the visibility even after the conversion.

An image converter according to still another aspect of the present invention converts a color image into a monochrome image. The image conversion device includes a unit for determining a color included in the color image, a unit for extracting a character area for each of the determined colors, and a character decoration method based on color information for each of the determined colors. And means for applying the determined decoration to the character area and converting it to a monochrome image.

Different decorations are applied to the character area for each character color. For this reason, even when a character highlighted in a color image is converted to a monochrome image, the character can be emphasized.

An image conversion apparatus according to still another aspect of the present invention converts a color image into a monochrome image. The image conversion apparatus includes: a unit for determining a color included in the color image; a unit for extracting a region having the color for each of the determined colors; and a color information for each of the determined colors. It includes means for determining a texture, and means for applying the determined texture to an area and converting the area to a monochrome image.

A different texture is applied to an area included in a color image for each color, and the area is converted to a monochrome image. Therefore, even when an image such as a graph expressing a difference in data by a difference in color is converted to a monochrome image, the difference in data can be appropriately represented.

According to still another aspect of the present invention, there is provided a computer-readable recording medium comprising: a step of determining a plurality of colors included in a color image; and a step of determining a density of each pixel included in the color image based on color information. Is determined, and a step of converting the color component of each pixel of the color image into the determined density is recorded on an image conversion program.

For each of the plurality of colors included in the color image, the converted density is determined from the color information. Therefore, even when a plurality of colors having the same lightness are mixed, it is possible to automatically determine the converted density of each color and convert the color into a monochrome image that does not impair the visibility even after the conversion.

According to still another aspect of the present invention, there is provided a computer-readable recording medium comprising: a step of determining a color included in a color image; a step of extracting a character area for each of the determined colors; Further, an image conversion program for causing a computer to execute a step of determining a character decoration method based on color information and a step of applying the determined decoration to a character area and converting the character area into a monochrome image is recorded.

Different decorations are applied to the character area for each character color. For this reason, even when a character highlighted in a color image is converted to a monochrome image, the character can be emphasized.

A computer-readable recording medium according to still another aspect of the present invention includes a step of determining a color included in a color image, a step of extracting an area having the color for each determined color, An image conversion program for causing a computer to execute a step of determining a texture based on color information and a step of applying the determined texture to an area and converting the area into a monochrome image for each of the obtained colors is recorded.

A different texture is applied to the area included in the color image for each color, and the area is converted to a monochrome image. Therefore, even when an image such as a graph expressing a difference in data by a difference in color is converted to a monochrome image, the difference in data can be appropriately represented.

[0038]

DESCRIPTION OF THE PREFERRED EMBODIMENTS [First Embodiment] Referring to FIG. 1, an image conversion apparatus according to an embodiment of the present invention includes a computer 41, a keyboard 45 for giving instructions to computer 41, and A mouse 46, a display 42 for displaying various information, a magnetic tape device 43 for reading a program executed by the computer 41, a CD-ROM (Compact Disc-Read Only Mem
ory) device 47, a communication modem 49, and a scanner 50 for reading a color original.

A program for performing image conversion is recorded on a magnetic tape 44 or a CD-ROM 48 which is a recording medium readable by a computer 41 and read by a magnetic tape device 43 or a CD-ROM device 47, respectively. Alternatively, it is read by the communication modem 49 via the communication line.

Referring to FIG. 2, computer 41 includes a CPU (Central Processing Unit) 54 for executing a program read via magnetic tape device 43, CD-ROM device 47 or communication modem 49, and a computer. ROM (Read Only Memory) 51 for storing other programs and data necessary for the operation of 41
And a RAM (Random Access Memo) for storing the program, parameters for executing the program, calculation results, and the like.
ry) 52 and a magnetic disk 53 for storing programs, image data, and the like.

The image conversion process will be described with reference to FIG. The multicolor original is read by the scanner 50, and an image is input to the computer 41 (S1). The color used in the input image is determined (S2).
The converted density is determined according to the color information used in the image (S3). The color input image is converted into a monochrome image having the determined density (S4), and the converted image is displayed (output) on the display 42 (S5).

The processing in S1 may be input from an image reading device such as a copying machine or a camera other than the scanner 50. Alternatively, the original may be read from a magnetic disk 53 or the like in which an image from which the original has been read is stored.

Further, the original of the image to be read may be not only a multicolored document, a graph and a diagram, but also a color photograph or a computer graphics.

In S5, an image is displayed on the display 42, and the display 42 displays a CRT (Cathode Rad).
y Tube) display and LCD (Liquid Crystal Displ)
ay). Further, an image may be output to an image output device such as a printer or a communication device such as a facsimile instead of the display 42. Further, the converted image may be written on a magnetic disk 53, a floppy (registered trademark) disk, a magneto-optical disk, or the like.

The processing in S2 of FIG. 3 will be described with reference to FIG. The image input from the scanner 50 is converted into hue (H), saturation (S), and lightness (I) for each predetermined unit (S21). The conversion method to HSI is generally known. Therefore, the detailed description will not be repeated here.

A histogram of the hue H weighted by the saturation S is obtained (S22). The color used in the image is determined from the obtained histogram (S23). Finally, information on the determined color is output (S24).

Referring to FIG. 5, S22 and S2 in FIG.
The process 3 will be described. FIG. 5 is a graph in which the horizontal axis is the sum of the hue H and the vertical axis is the sum of the saturation S, in which the values of the saturation S are added for all the pixels having the same hue H. However, to determine the colors used in the image,
Pixels having a saturation value S or less are determined to be achromatic and are not added. From these, the hue H at which the sum of the saturation S is maximized is selected, and this is set as the hues H0 and H1 of the colors used in the image. In order to obtain the maximum value from the histogram, the hues H2 and H3 of the valley portion are detected by using the discriminant analysis method, and the maximum value of the saturation S between the valleys is set to the maximum value. When there are a plurality of valleys, all the local maxima are obtained by repeatedly using the discriminant analysis method. Discriminant analysis is
This is a generally known method. Therefore, the detailed description will not be repeated here.

A pixel having a hue within a predetermined range around the determined hue is represented by the determined hue.
For example, when the obtained hue is H0, H0 ± 5
Are represented by the hue H0.

When no maximum value is found, it is determined that the input image is a full-color image or a monochrome image.
To determine the color used in the image, another method may be used, or the user may specify the color.

Referring to FIG. 6, the processing in S3 of FIG. 3 will be described. If the image is originally monochrome or full-color based on the number of colors of the input image determined in the process of S2, the density I of each pixel is determined by the above equation (1) (S31).

When only one color is used in the image,
There is a high possibility that the color is used in a place to be emphasized in the manuscript. For this reason, the density is determined so that the color is converted to a higher density (S32). The density may be determined so that achromatic pixels are lightly converted and the colored pixels are further emphasized.

When a plurality of colors are used in an image,
The average value of the saturation S is obtained for each color, and the conversion is performed by changing the density stepwise in descending order of the average value of the saturation S (S33). For example, the colors used in the image are red, green, and blue, and the average values of the saturations S are 0.8, 0.6, and 0.4, respectively.
, Red is the darkest, green is the next darkest,
Converts blue to be the lightest. The maximum value of the saturation S may be used instead of the average value of the saturation S, or the achromatic pixels may be thinly converted as in the case of one color so that the colored pixels are further emphasized. The concentration may be determined. Also, in general documents, letters written in red are often used for emphasis because they are easy to get attention. Therefore, when there is a red color in the image, it may be converted to be darker than other colors.

Referring to FIG. 7, the processing in S4 of FIG. 3 will be described. If the image is monochrome or full color (YES in S41), a conversion from a color image to a monochrome image is performed according to equation (1) (S42).

If the image is other than monochrome or full color (NO in S41), the average value of each of the R, G, and B components is determined for a certain pixel in the image, and the average value is used as the luminance component I (S43). . Next, this pixel is subjected to HSI conversion, and it is determined whether or not the pixel is a pixel for which density conversion has been designated by the process of S3 (S44).

If the saturation S is equal to or smaller than the predetermined threshold value SA0 (NO in S44), the luminance component I obtained in S43 is output as it is as the converted density (S46). When density conversion of the luminance component I is performed, a converted density I 'is obtained according to a function as shown in FIG. That is, when increasing the density, the conversion is performed so that the pixels of the color become entirely bright according to the conversion method shown in the graph of FIG. 8A, and when decreasing the density, the conversion is performed as shown in the graph of FIG. According to the conversion method used, conversion is performed so that the entire image becomes dark (S45). The point Il is fixed, and a specific color can be made darker or lighter by manipulating the threshold value I0 for each color.

At this time, a coefficient W obtained by a weighting function as shown in FIG. 9 may be used to reduce the degree of density conversion for a pixel having a small saturation S. That is, the converted density I ″ is obtained as in the following equation (2).

I ″ = I + W × (I′−I) (2) In this way, the amount of change in density after conversion for a pixel having a light color (small saturation S) becomes small. It is possible to prevent a contour of a character or a picture from becoming unnatural near SA0, and to obtain a natural monochrome image.

If there is no designation for density conversion (N in S44)
O), the luminance component I obtained in S43 is output as it is as the converted density (S46).

This process is performed for all the pixels in the image. Here, the average I of each of the R, G, and B components is shown in FIG.
And conversion according to the function of FIG. 9, but a function in which the coefficients of R, G, and B in equation (1) are freely changed may be prepared for each color, and image conversion may be performed according to the function. . The density conversion may be performed in a color space other than the HSI space.

As described above, according to the present embodiment, for each of a plurality of colors included in a color image, the converted density is determined from the color information. Therefore, even when a plurality of colors having the same lightness are mixed, it is possible to automatically determine the converted density of each color and convert the color into a monochrome image that does not impair the visibility even after the conversion. [Second Embodiment] The hardware configuration of the image conversion apparatus according to the second embodiment is the same as the hardware configuration of the image conversion apparatus according to the first embodiment. Therefore, the detailed description will not be repeated here.

Referring to FIG. 10, an image conversion process performed by the image conversion apparatus according to the second embodiment will be described.

As described with reference to FIG. 3, the image read by the scanner 50 is input to the computer 41, and the color used in the image is determined (S1).
And S2). The processing in S1 and S2 is the same as in the first embodiment. Therefore, the detailed description will not be repeated here.

The density of the converted image is designated for each color used in the image (S6). After the input image is converted to a monochrome image having the designated density (S4), the converted image is displayed (output) on the display 42 (S5). The processing in S4 and S5 is the same as in the first embodiment. Therefore, the detailed description will not be repeated here.

Next, the processing in S6 will be described. First
In the image conversion processing according to the embodiment, the density after conversion is automatically determined according to the color information used in the image so that the converted monochrome image can be easily viewed like the color image before conversion. (S3 in FIG. 3). On the other hand, in the process of S6 of the present embodiment, the user specifies the density after image conversion using the mouse 46, the keyboard 45, a microphone (not shown), or the like.

The user designates the density of each color and the density of an achromatic color while looking at the display 42. FIG. 11 shows an example of the density designation screen displayed on the display 42.
The image input to the computer 41 is displayed in the image display area 1
1 is displayed. Further, the color determined by the processing in S2 is displayed in the determination color display areas 12 and 13. The user can independently change the density of each color or achromatic color by sliding any of the density adjustment knobs 14, 15, and 16 left and right. The result of the conversion is displayed in the image display area 11. By performing such an operation, it is possible to make a certain color the same as the background color so that it cannot be seen, or to emphasize a certain color by making it darker and making an achromatic color lighter.

According to the present embodiment, for each of a plurality of colors included in a color image, the user specifies the converted density, and the color components are converted to the specified density. For this reason, the user can freely specify the converted density of each color, so that the monochrome image can be converted as desired. [Third Embodiment] The hardware configuration of the image conversion apparatus according to the third embodiment is the same as the hardware configuration of the image conversion apparatus according to the first embodiment. Therefore, the detailed description will not be repeated here.

Referring to FIG. 12, an image conversion process performed by the image conversion apparatus according to the third embodiment will be described.

The processing in S1 and S2 is the same as in the first embodiment. Therefore, the detailed description will not be repeated here.

The character area in the image is extracted for each color (S7). The decoration method after the conversion of the character string in the image is automatically determined for each color (S8). The colored character string in the image is decorated with the decoration determined in S8, and is converted into a monochrome image (S9). The converted image is displayed (output) on the display 42 (S5).

Referring to FIG. 13, the process in S7 of FIG. 12 will be described. 2 for each color determined in the process of S2
Create a value image. That is, an image is created in which the pixel value of the pixel having the color of interest is 1 and the pixel value of the pixel having any other color or achromatic pixel is 0. Such a binary image is created by the number of colors. (S71). Labeling processing is performed on these images to extract a rectangular area (S72). The labeling processing method and the rectangular area extraction method are generally known. Therefore, the detailed description will not be repeated here.

A graph is created in which the horizontal axis is the size of a rectangle and the vertical axis is the number of rectangles for each color, and the size of the rectangle when the number of rectangles is the maximum is estimated as the character size of that color ( S7
3). A rectangle much larger than the character size is determined to be incorrectly extracted or is a chart area, and is excluded from the character area. Estimate character spacing from character size. For example,
Estimate half the width of the character size as the character spacing. Rectangles that are closer than the character spacing are integrated, and a character area is extracted for each color (S74).

Referring to FIG. 14, the process in S8 of FIG. 12 will be described. If the image is originally monochrome or full color, a character area cannot be extracted for each color based on the number of colors of the input image determined in S2. Therefore, equation (1)
To determine the density I of each pixel (YES in S81, S
31).

When one color is used in an image, it is highly likely that the color is used in a portion of the document to be emphasized. Therefore, the character written in that color is inverted and converted (NO in S81, YES in S82, S83).
The decoration method is not limited to reverse display, but may be any decoration such as shading or underlining that is emphasized as compared with surrounding characters.

When a plurality of colors are used in an image,
The decoration is made different for each color, and conversion is performed so that each character is emphasized (NO in S81, NO in S82, S
84). For example, the colors used in the image are red, green, and blue
If it is a color, the character area written in red is inverted, the character area written in green is shaded, and the character area written in blue is underlined. Of course, these decorations may be replaced with other decorations.

Next, the processing in S9 of FIG. 12 will be described. Pixels that are not character areas of any color in the input image are converted to a monochrome image according to equation (1). The pixels in the character area extracted in S7 are converted into a monochrome image after the decoration determined in S8 is added.

As described above, according to the present embodiment, a different decoration is applied to the character area for each character color. For this reason, even when a character highlighted in a color image is converted to a monochrome image, the character can be emphasized. [Fourth Embodiment] The hardware configuration of the image conversion apparatus according to the fourth embodiment is the same as the hardware configuration of the image conversion apparatus according to the first embodiment. Therefore, the detailed description will not be repeated here.

Referring to FIG. 15, image conversion processing by the image conversion apparatus according to the present embodiment will be described. The image conversion processing according to the present embodiment uses the processing of S10 instead of the processing of S8 in the image conversion processing of the third embodiment described with reference to FIG. Other processes are the same as in the third embodiment. Therefore, the detailed description will not be repeated here.

The processing in S10 will be described. In S8 of FIG. 12, the decoration to be added after the conversion is automatically determined according to the color information used in the image so that the monochrome image after the conversion can be easily viewed like the color image before the conversion. On the other hand, in S10, the user sets the mouse 46,
The decoration to be added to the character tilt area in the image is designated by using the keyboard 45 or a microphone.

The user looks at the display 42,
Specify the decoration. FIG. 16 shows an example of a decoration method designation screen displayed on the display 42. Computer 4
The image input to 1 is displayed in the image display area 11. Further, the color determined by the processing in S2 is displayed in the determination color display areas 12 and 13. The user can independently specify the decoration of the character written in each color from the decoration method selection menu 17 or 18. The conversion result with the specified decoration is displayed in the image display area 11. The decoration method is inverted, shaded, underlined, wavy,
Includes frames, masks, strikethroughs, large and small fonts.

According to the present embodiment, the user can designate a decoration method for each character color. For this reason,
The user can decorate the character area as desired and convert it to a monochrome image. [Fifth Embodiment] The hardware configuration of the image conversion apparatus according to the fifth embodiment is the same as the hardware configuration of the image conversion apparatus according to the first embodiment. Therefore, the detailed description will not be repeated here.

Referring to FIG. 17, an image conversion process performed by the image conversion apparatus according to the fifth embodiment will be described.
The image stored in the magnetic disk 53 or the like is read (S
l), the color used in the image is determined (S)
2).

A region is extracted for each color (S51).
The converted monochrome texture of the area is determined for each color (S52). The area extracted in the processing of S51 is converted into the texture area determined in the processing of S52 (S53). The converted monochrome image is displayed on the display 4
2 or output to a printer (not shown) (S5).

Next, the processing of S51 will be described. S2
A binary image is created for each color determined in the above processing.
That is, the pixel value of the pixel having the color of interest is set to 1,
An image is created in which the pixel values of pixels having other colors or achromatic pixels are 0. Such a binary image is created by the number of colors. Labeling processing is performed on these images, and regions are extracted for each color. Labeling processing methods are generally known. Therefore, the detailed description will not be repeated here.

The processing in S52 will be described. If the image is originally monochrome or full color, the density I of each pixel is determined by the above equation (1) based on the number of colors of the input image determined in the process of S2. When the color used in the image is one color, it is converted to a texture such as a diagonal line or a rope so that the area drawn in that color can be distinguished even if it becomes a monochrome image.

When there are a plurality of colors used in the image, the average value of the saturation S is obtained for each color, and the conversion is performed by changing the texture density in the descending order of the average value of the saturation S. For example, if the colors used in the image are red, green, and blue, and the average values of the saturations are 0.8, 0.6, and 0.4, respectively, red is the most dense color. , The green is converted to the next denser slash, and the blue to the least dense slash. Saturation S
The maximum value may be used instead of the average value of, or the shaded line may be changed to another texture. Further, regardless of the saturation S of each color, the distinction may be made by changing the type of the texture according to the color, such as oblique lines, grids, and shading. Further, the user may manually specify the type of texture.

The processing in S53 will be described. An uncolored area in the input image is converted to a monochrome image according to the above equation (1). The pixels in the colored area are changed to the texture specified in S52 and converted to a monochrome image.

For example, FIG. 18 shows a graph which is color-coded into three colors and displayed in a texture so that the graph is easy to see.

According to the present embodiment, a different texture is applied to an area included in a color image for each color.
Converted to a monochrome image. Therefore, even when an image such as a graph expressing a difference in data by a difference in color is converted to a monochrome image, the difference in data can be appropriately represented.

[0089]

According to the present invention, for each of a plurality of colors included in a color image, the converted density is determined from the color information. Therefore, even when a plurality of colors having the same lightness are mixed, it is possible to automatically determine the converted density of each color and convert the color into a monochrome image that does not impair the visibility even after the conversion.

[Brief description of the drawings]

FIG. 1 is an external view of an image conversion device.

FIG. 2 is a hardware configuration diagram of the image conversion apparatus.

FIG. 3 is a flowchart of an image conversion process according to the first embodiment.

FIG. 4 is a detailed flowchart of S2 in FIG.

FIG. 5 is a graph for explaining S22 and S23 in FIG. 4;

FIG. 6 is a detailed flowchart of S3 in FIG. 3;

FIG. 7 is a detailed flowchart of S4 in FIG. 3;

FIG. 8 is a graph for explaining a density conversion function in S43 of FIG. 7;

FIG. 9 is a graph for explaining a weight function at the time of conversion in S43 of FIG. 7;

FIG. 10 is a flowchart of an image conversion process according to the second embodiment.

FIG. 11 is a diagram illustrating an example of a density designation screen displayed on a display.

FIG. 12 is a flowchart of an image conversion process according to the third embodiment.

FIG. 13 is a detailed flowchart of S7 in FIG.

FIG. 14 is a detailed flowchart of S8 in FIG.

FIG. 15 is a flowchart of an image conversion process according to the fourth embodiment.

FIG. 16 is a diagram showing an example of a decoration method designation screen displayed on a display.

FIG. 17 is a flowchart of an image conversion process according to the fifth embodiment.

FIG. 18 is a diagram illustrating an example of a graph converted by the image conversion processing according to the fifth embodiment.

[Explanation of symbols]

11 image display area, 12 discrimination color display area, 17 decoration method selection menu, 41 computer, 42 display, 43 magnetic tape device, 44 magnetic tape,
45 keyboard, 46 mouse, 47 CD-ROM
Device, 48 CD-ROM, 49 communication modem, 50
Scanner, 51 ROM, 52 RAM, 53 magnetic disk, 54 CPU.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 1/40 H04N 1/40 FF term (Reference) 5B057 AA11 BA02 BA25 CA01 CA08 CA12 CA16 CB02 CB07 CB12 CB16 CC02 CE13 CE18 DA08 DA12 DB02 DB06 DB09 DC19 DC25 DC36 5C077 MP05 MP06 MP08 PP15 PP27 PP28 PP31 PP32. GA41

Claims (15)

[Claims] 1. An image conversion method for converting a color image into a monochrome image, comprising: determining a plurality of colors included in the color image; and converting each pixel included in the color image based on color information. An image conversion method, comprising: determining a subsequent density; and converting a color component of each pixel of the color image to the determined density. 2. An image conversion method for converting a color image into a monochrome image, comprising: a step of determining a plurality of colors included in the color image; and an instruction for a converted density for each of the plurality of colors. An image conversion method, comprising: receiving from a user; and converting a color component of each pixel of the color image into a designated density. 3. The image conversion according to claim 1, wherein the step of determining includes determining a plurality of colors based on a hue and saturation distribution of each pixel included in the color image. Method. 4. The step of determining includes a step of determining a converted density based on the saturation of each pixel,
The image conversion method according to claim 1. 5. The step of converting includes a step of converting to a determined or designated density, and a step of further converting the converted density by using a weighting function having a larger value for a pixel having higher saturation. ,
The image conversion method according to claim 1. 6. An image conversion method for converting a color image into a monochrome image, the method comprising: determining a color included in the color image; and extracting a character area for each determined color. An image conversion method, comprising: a step of determining a character decoration method for each color based on color information; and a step of applying the determined decoration to the character region and converting the character region into a monochrome image. 7. An image conversion method for converting a color image into a monochrome image, comprising: determining a color included in the color image; and extracting a character region for each determined color. An image conversion method, comprising: receiving an instruction regarding a decoration method from a user for each color; and applying a specified decoration to the character area and converting the character area into a monochrome image. 8. The step of extracting includes, for each of the determined colors, a step of extracting an area having the color, and a step of determining whether the area is a character area based on the size of the extracted area. The image conversion method according to claim 6, further comprising: extracting a character area from the determined result. 9. An image conversion method for converting a color image into a monochrome image, comprising: determining a color included in the color image; and extracting, for each determined color, an area having the color. An image conversion method, comprising: determining a texture based on color information for each determined color; and applying the determined texture to the area to convert the area into a monochrome image. 10. An image conversion apparatus for converting a color image into a monochrome image, comprising: means for determining a plurality of colors included in the color image; and color information for each pixel included in the color image. An image conversion apparatus, comprising: means for determining a density after conversion based on the density; and means for converting a color component of each pixel of the color image into the determined density. 11. An image conversion apparatus for converting a color image into a monochrome image, comprising: means for determining a color included in the color image; and means for extracting a character area for each determined color. An image conversion device, comprising: means for determining a character decoration method based on color information for each determined color; and means for applying the determined decoration to the character area and converting it to a monochrome image. 12. An image conversion apparatus for converting a color image into a monochrome image, comprising: means for determining a color included in the color image; and extracting an area having the color for each determined color. An image conversion apparatus, comprising: means for determining a texture based on color information for each determined color; and means for applying the determined texture to the area and converting the area to a monochrome image. 13. A step of determining a plurality of colors included in a color image; a step of determining a density after conversion based on color information for each pixel included in the color image; A computer-readable recording medium that stores an image conversion program that causes a computer to execute a step of converting a color component into a determined density. 14. A step of determining a color included in a color image, a step of extracting a character region for each determined color, and a step of determining a character decoration method based on color information for each determined color. And a computer-readable recording medium storing an image conversion program for causing a computer to execute the step of applying the determined decoration to the character area and converting the image into a monochrome image. 15. A step of determining a color included in a color image, a step of extracting a region having the color for each determined color, and determining a texture based on color information for each determined color. And a computer-readable recording medium storing an image conversion program for causing a computer to execute the step of: applying the determined texture to the area and converting the area to a monochrome image.