JP2914074B2 - Limited color determining method and apparatus - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a color display device capable of displaying a digitized natural image with only a small number of colors at the same time. Represented by a few colors,
The present invention relates to a limited color determination method and apparatus for selecting and displaying colors without discomfort so that colors are assigned to components having large color differences as much as possible.

[0002]

2. Description of the Related Art Generally, a color image used in a color display device is represented by RGB color components, and each color image is digitized to about 8 bits. In a full color display, 24 bits for each pixel, or 2 ²⁴
Colors can be displayed simultaneously, and a natural image can be displayed to the human eye without discomfort.

On the other hand, CD-ROM, CD-I, CAD
(Computer Aided Design), CAI (Computer Assis)
In the world of ted instruction and graphics, a color display device that can simultaneously display only a limited number of colors is often used. In the case of a normal color map display, the capacity per pixel of the image memory is 8
Since it is a bit, the number of colors that can be displayed simultaneously is up to 2 ⁸ = 256. With a limited number of colors such as 256 colors, it is difficult to display a natural image without deterioration, but there are many demands for making this possible. Furthermore, CD-ROM and CD-I
In the world, since various data such as characters, voices, and images are contained in a limited data capacity, there is a strong demand for compression to a small number of colors such as 32 colors or less in order to store data as small as possible.

[0004] For this purpose, conventionally, a method of displaying a natural image on a color map display with a limited number of colors while minimizing visual deterioration has been known. For example, 256 image data of two ^24-color full color
As a method of reducing the number of representative colors to about the same as the color, for example, when a color is represented by three primary colors of R, G, and B,
A space represented by a three-dimensional rectangular coordinate system having coordinates of G and B values is defined as a color space, and the color distribution of pixels included in full-color image data is analyzed. Select a display color that is large for the distributed color area and small for the color area with a small distribution, register it in the color map, assign the representative color closest to each pixel, and assign the color code of the representative color to each of the image memories. In some cases, approximate display is performed by writing data at pixel positions.

As one of the methods for selecting a representative color as described above, Otsu's discriminant analysis (IEICE (D). J63-D, 4, pp. 349-3)
56. Showa 55-4.). Further, the color space is not limited to one that expresses a color by a combination of three primary colors of RGB, but also L ^* u ^* v ^* and L ^{* in} consideration of human color difference ^.
a ^* b ^* uniform color space (recommended by the CIE (International Commission on Illumination)) and the like, and the discriminant analysis method can be performed using these color spaces. In addition, a method using the visual characteristics of humans and further applying a dithering method (Journal of the Institute of Image Electronics Engineers of Japan, Vol. 18, No. 5, (1989) p. 293-301; Tajima, Ikeda) and the like have been proposed.

[0006]

By the way, when a limited number of colors such as 32 colors is obtained by the above-mentioned conventional method, that is, a limited color display algorithm of about 256 colors, an average color is selected. There is a problem that the color of the approximate image based on the representative color becomes cloudy. Therefore, 3
Displaying a natural image with a small number of colors, such as two, is inefficient because it is necessary to manually or manually perform color assignment suitable for human vision.

In the conventional method, each pixel of the image data is arranged in the color space, and the representative color is determined from the distribution of the pixels in the color space. The relationship between colors and colors was not taken into account. For example, in the case of image data in which the sky and the sea are drawn, in the arrangement on the image, the pixels in the sky and the pixels in the sea are vertically separated, but in the color space, Since the colors of the blue and the blue are substantially the same, the pixels indicating the sky and the sea are partially overlapped and distributed, and the pixels of the sky and the sea are substantially distributed in a lump.

Therefore, when the representative color is determined by the above-described conventional method, the representative color is selected from a portion of the color space which is a cluster of pixels of blue color, and the number of representative colors is greatly reduced. In such a case, a substantially similar representative color is selected for the sky and the sea, and there is a problem that the color difference between the sky and the sea is almost eliminated. That is, when there is a similar subject having a different color on the image data, it is not possible to select to change the representative color depending on the subject.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a method and an apparatus for determining a limited color which automatically solves the above-mentioned problem and calculates a small number of colors such as 32 colors of a natural image and displays the natural image without a sense of incongruity. .

[0010]

According to the present invention, there is provided a method for determining a limited color, comprising: converting color image data represented by a coordinate system of three primary colors;
The uniform color space is divided into two regions by performing conversion to a coordinate system of a uniform color space and performing discriminant analysis on the frequency distribution of each pixel of the image data in the converted coordinate system,
Further, a representative color is obtained by repeating division of the divided area into two areas, and the image data is approximated by a limited number of designated representative colors of the image data. Color of each pixel arranged in
From the distribution on the image array of each minute, each pixel on the image array
The numerical value of the cohesiveness of the color components of
Of the color components of each pixel on the image array
The color space is newly added to the color space in association with each color component of the pixel.
By setting the coordinate axis indicating the unity of the minute
A multidimensional space is provided, and the uniform color
The above multidimensional space is sequentially divided into a plurality of regions instead of intervening
When dividing the multidimensional space, the multidimensional space
Against or between the distribution of each pixel of the image data in the area obtained by dividing a multi-dimensional space, obtains the principal component axis by performing principal component analysis, then, the multi above principal component axis
Project each pixel developed in the dimensional space or the above area, and then on the principal component axis where each pixel is projected,
Obtains a frequency distribution of the pixels, by performing discriminant analysis on the frequency distribution, obtains a dividing threshold on the principal component axis, in the dividing threshold on the major component axis, the multidimensional
Dividing the space or region by a curved surface perpendicular to the principal component axis is a means for solving the above problem.

[0011]

[0012]

Further, the limited color determining apparatus of the present invention converts color image data expressed by a coordinate system of three primary colors into a coordinate system of a uniform color space, and converts each pixel of the image data in the converted coordinate system. The representative color is obtained by repeating discriminant analysis on the frequency distribution of the above, dividing the uniform color space into two regions, and further dividing the divided region into two regions, thereby obtaining the representative color, and specifying the image data. The approximate display is performed using the limited number of representative colors, and the color component of each pixel arranged on the image of the image data is obtained from the distribution on the image array of the color component of each pixel. Numericalization means for digitizing the goodness of the unity of the components, and the goodness of the color components of each pixel on the digitized image array in association with each color component of each pixel, and newly in the color space. Unity of color components A multi-dimensional space is provided by setting a coordinate axis indicating goodness, and a principal component analysis is performed on a distribution of each pixel of the image data in the multi-dimensional space or a region obtained by dividing the multi-dimensional space, by performing a principal component analysis. The principal component axis calculating means, the projecting means for projecting each pixel developed in the multidimensional space or the area on the principal component axis, and the principal component axis on which each pixel is projected, A frequency distribution calculating means for obtaining a frequency distribution; a division threshold calculating means for performing a discriminant analysis on the frequency distribution to obtain a dividing threshold on the principal component axis; A means for solving the above-mentioned problem is provided with an area dividing means for dividing the dimensional space or the area by a curved surface perpendicular to the principal component axis.

[0014]

[0015]

[0016]

SUMMARY OF According to limited color determination method and limited color determining apparatus of the above claims 1 and 2 wherein, instead of the uniform color space, a coordinate axis of the uniform color space, good chunk of the color components in the image sequence A multidimensional space is provided by adding coordinate axes indicating
Since the representative color is determined by the discriminant analysis in the multidimensional space, the distribution of the hue on the image array is reflected on the determined representative color. Here, the goodness of the unity of the color components of each pixel on the image array will be described. In general, objects drawn on an image are represented by relatively similar colors.
For example, the sea and sky contain many blue-based colors, and apples contain many red-based colors. Then, in a portion where the sea and the sky are drawn on the image array, pixels having a bluish color are present collectively, and this is expressed as goodness of unity.

The goodness of the unity of the color components of each pixel on the image array is determined by, for example, how many pixels of similar colors exist together, and how many pixels of similar colors exist in an arbitrary range. It can be converted into a numerical value by measuring whether or not it exists.

[0018] Also, by obtaining a dividing threshold on principal component axis calculated by the main component analysis, the representative color obtained by discrimination analysis method, for each pixel of the image data developed in the four-dimensional space The distribution information is reflected more.

[0019]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the limited color determining apparatus according to the present invention will be described below with reference to the drawings. As shown in FIG. 1, the limited color determination device of this embodiment includes an image storage unit 1 for storing color image data, and an upper 4-bit image for storing upper 4 bits of the image data stored in the image storage unit 1. Storage means 2; mosaic image calculation means 3 for dividing the upper 4 bits of image data stored in the upper 4 bit image storage means into partial cells of a size determined according to the image size; and mosaic image calculation means 3 The mosaic cell color determining means 4 for obtaining a color component which predominantly exists in the cell for each cell of the mosaic image divided into partial cells according to the above, and the mosaic cell color obtained by the mosaic cell color determining means 4 is stored. And the continuity of appearance of the same mosaic cell color in adjacent cells in the mosaic image in each of the four directions of vertical, horizontal, left diagonal, and right diagonal. And a continuity value calculating means 6 for quantifying the continuity as a continuity value, and a continuity value storing means for storing the continuity value of each color component quantified by the continuity value calculating means 6 7 is provided.

Further, the above-mentioned limited color determining apparatus is described in (1) below.
The RGB data of the color image is converted to L ^* a ^* b by the equations (7) to (7).
^* Color conversion means 8 for color-converting data for each pixel, L ^* , a
Each pixel is developed based on its L ^* a ^* b ^* and continuity value in a four-dimensional space spanned by ^* , b ^* and the continuity value of the color component, and a set of each pixel in the four-dimensional space = cluster , A principal component axis calculating means 10 for calculating a principal component and a principal component axis (principal component vector) of the cluster by principal component analysis, and a main component calculated by the principal component axis calculating means 10. A main component storage unit 11 for storing components and a main component axis; a color component projection unit 12 for projecting each color component onto the main component axis stored in the main component storage unit 11; A principal component axis projection value storage unit 13 for storing a result of projecting the principal component axis onto the principal component axis, a projection value histogram calculation unit 14 for calculating a histogram of values read from each principal component axis projection value storage unit 13, And a projection histogram storage unit 15 for storing the calculated histogram by Kagechi histogram calculating means 14.

Then, the limited color determining device includes an average / variance calculating means 16 for calculating an average and a variance from the histogram stored in the projection value histogram storing means 15.
And the average / variance calculated by the average / variance calculation means 16.
Mean / variance storage means 17 for storing the variance, weighted variance calculation means 18 for obtaining a weighted variance based on the variance stored in the mean / variance storage means 17, and the principal component stored in the principal component storage means 11. On the axis, a division threshold value determining unit 19 for obtaining a division threshold value by discriminant analysis based on the histogram stored in the projection value histogram storage unit 15
A dividing threshold value storing means 20 for storing the dividing threshold value obtained by the dividing threshold value determining means 19; a cluster dividing means 21 for dividing the cluster into two in accordance with the weighting variance in descending order of the dividing variance; A cluster management storage unit 22 for managing information of a cluster newly formed by dividing the cluster by the clustering unit; and a cluster sorting unit 23 for sorting each cluster formed by the cluster dividing unit 19 according to its principal component value.
The operation of each of the above means 2 to 23 is performed until the cluster having the largest principal component value obtained by the cluster sorting means 23 is no longer divided into clusters or the number of clusters reaches a specified number of colors. And a cluster division control unit 24 that repeats the above processing.

Further, the limited color determination device reads out the limited color obtained by performing the operations of the above-mentioned units 2 to 24 from the average / dispersion storage unit 16 and performs the inverse conversion of the color conversion unit 8 by the color conversion unit 25. A representative color allocating unit 26 that replaces the color of each pixel with the limited color by using the limited color cluster number from the cluster storage unit 9; and a limited color color pallet operation unit 27 that sorts the limited colors by distance in a color space. When,
And a color correction unit 28 that enables partial color correction on a screen on which a color image is approximately displayed in a limited color obtained by performing the operations of the units 2 to 27 described above.

The image storage means 1 has an image memory 1a and stores (R, G,
B) A value (each color component is 8 bits) is stored. The upper 4-bit image storage unit 2 stores the upper 4 bits of each pixel (RGB) value of the image data stored in the image storage unit 1.

The mosaic image calculation means 3 is composed of the image storage means 1
1 for each of the vertical and horizontal directions corresponding to the size of the image stored in
An arbitrary size of about / 30 is calculated, and the image data stored in the high-order 4-bit image storage means 2 is divided by a rectangular area of the obtained size = cell. Mosaic cell color determination means 4
Is a color component present in the cell for each cell of the image data divided into cells by the mosaic image calculation unit 3 (the value of the upper 4 bits stored in the upper 4 bit image storage unit 2). Is determined as a mosaic cell color.

If there are a plurality of color components that are present in a quarter or more, it is checked if there are more than one-half, and if so, the color components are present. The average value of the components is taken as the mosaic cell color. If there is one color component present in the cell at least 1/4, the color component is taken as the mosaic cell color. The average value of the color components in the mosaic cell is defined as the mosaic cell color. The mosaic cell color storage unit 5 stores the mosaic cell color determined by the mosaic cell color determination unit 4 as mosaic image data.

The continuity value calculating means 6 is the same as the above cells in the four directions of vertical, horizontal, diagonally left and diagonally right in each cell on the mosaic image data stored in the mosaic cell color storage means 5. The number of times the cell color continues continuously is determined as a continuity value. The continuity value storage means 7 assigns the continuity value obtained for each cell to the pixels included in each cell, and stores the continuity value in the same array as the pixels on the image data.

The color conversion means 8 converts the (R, G, B) values of each pixel of the image data into (L ^* , a ^* , b ^* ) values using a conversion formula described later. The cluster storage means 9 stores L ^* ,
Each pixel is developed in a four-dimensional space spanned by a ^* and b ^* and the continuity values of the color components, and a set of pixels in the four-dimensional space = cluster is stored. Here, the cluster indicates a divided part of the four-dimensional space when the four-dimensional space is divided using discriminant analysis as described later, and a cluster number is assigned to each divided part. For each cluster number, the position on the coordinates of the divided portion of the four-dimensional space and the pixels included in the cluster are stored.

The principal component axis calculating means 10 applies a four-component principal component analysis method to pixels included in each cluster and having L ^* , a ^* , b ^* and continuity values of the color components. A principal component and a principal component vector (principal component axis) are obtained.
The principal component storage means 11 stores the principal components and principal component axes obtained by the principal component axis computing means 10.

The color component projecting means 12 comprises a main component storing means 11
The color components of each pixel are projected onto the principal component axis obtained in step (1). The principal component axis projection value storage means 13 stores the result of projecting the color component of each pixel onto the principal component axis.

The projection value histogram calculator 14 calculates a histogram at an appropriate sampling interval for the distribution of each pixel projected on the principal component axis read from the principal component axis projection value storage 13. The projection value histogram storage unit 15 stores the histogram obtained by the projection value histogram calculation unit 14. The average / variance calculation means 16 calculates the average and variance of the projection values included in the cluster read from the principal component axis projection value storage means 13. The average / variance storage unit 17 stores the average / variance calculated by the average / variance calculation unit 16.
Store the variance.

The weighted variance calculating means 18 obtains a weighted variance by multiplying the variance by the relative frequency of the number of pixels included in each cluster with respect to the total number of pixels. The division threshold value determining means 19 determines the division threshold value as described later by the conventional Otsu's discriminant analysis. Division threshold storage means 20
Stores the division threshold value obtained by the division threshold value determining means 19.

The cluster dividing means 21 divides the cluster into two using the principal component axis division threshold read from the division threshold storage means 20.

The cluster management information storage means 22 stores the address where the color information of each cluster is stored, the sorting order up to that point, the number of components in the cluster, the principal component value of the cluster, and the like. The cluster sorting unit 23 sorts each cluster by the principal component value read from the cluster management information storage unit 22 and sets the result in the cluster management information storage unit 22.

The cluster division control means 23 repeats these processes until the total number of clusters divided by the cluster division means 21 reaches the specified number of colors or there are no more clusters to be divided. Control. The color conversion unit 25 performs the inverse conversion of the color conversion unit 8,
The value of (L ^* , a ^* , b ^* ) of the obtained representative color is represented by (R, G,
Convert to the value of B).

After the above division is completed, the representative color allocating means 26 reads out the average color of each cluster from the average / dispersion storage means 15 as a limited color, and adopts the average color as the representative color of each cluster. In the original image data,
The average color of the cluster is assigned to the pixels included in each cluster, and replaced by the value converted by the color conversion unit 25. That is, the representative color allocating unit 27 reads the cluster number and the pixels included in the cluster of each cluster number from the cluster storage unit 9 and sets the average color of the cluster of each cluster number as the color of the pixel included in the cluster of the cluster number. The color of each pixel is replaced with the value converted by the color conversion means 26. The limited color color pallet calculation means 27 sorts the obtained representative colors in terms of distance in a uniform color space (L ^* , a ^* , b ^* ).

The color correcting means 28 corrects the display image by enclosing the color of the display image in a rectangle in accordance with an instruction from the mouse, and focusing on the portion of the color to be changed in the rectangle and clicking the mouse. The place and the color to be chosen are to be selected. When the selected color is corrected and changed by the color correcting means 28, there are two methods. One is to change the color selected as described above to another color registered in the color map 30d. It is exchanged for the representative color. That is, after the color to be changed is selected, the color correcting unit 28 displays the representative color registered in the color map 30d as a limited color palette screen.

On the displayed limited color color palette screen, the representative colors are sorted by the distance in the uniform color space, that is, the color difference by the limited color color palette calculation means 27, and colors having close color differences are displayed adjacently. The representative color to be changed, which is selected as described above, is displayed in a blinking manner, and a color close to the representative color to be changed can be selected.

Then, for example, a representative color similar to the representative color to be changed is searched from the color palette screen, and the representative color is designated on the color palette screen, whereby the representative color to be changed is replaced with the designated representative color. It is supposed to. That is, the representative color at the location of the display image designated by the mouse can be replaced with another representative color. In this case, only the color of the place specified by the mouse on the display image first is replaced with one of the representative colors that have been determined.

Another method of correcting and changing the color is to change the representative color registered in the color map 30d.
After selecting the representative color to be changed as described above, the color pallet screen is displayed, and the selected color is highlighted. A 24-bit full color color palette is displayed together with the limited color palette screen. In the case of this correction method, the color selected on the representative color palette is replaced with the color designated by the mouse on the full color palette.

That is, by performing this operation, for the selected representative color, the data itself of the color map 30d is changed, and on the display screen, the data other than the place designated by the mouse is selected. All the portions using the same representative color as the representative color are changed in color.

The limited color determination device having the above configuration displays full-color image data in a limited display color on the color map display device 30 using the limited color determination method. In this embodiment, the color map display device 30 can also display the image data stored in the image storage unit 1 in full color, and compare the full color image with the limited color image. Thus, the color can be corrected by the color correcting means 28. Note that reference numeral 30c denotes the image memory 1a,
It is a D / A converter for displaying the image data of 30a on the display 30b.

Next, a method for determining a limited color using the limited color determining apparatus will be described with reference to the flowchart of FIG. 2 and FIGS. (A) Measurement of the degree of color change of image data to be displayed In the conventional method, the degree of color change of image data,
When measuring whether the color of each pixel in the image and the color of the pixel in the vicinity of the pixel are significantly different or substantially the same, the image represented by each of RGB 8 bits is used. RGB data is converted to a uniform color space such as L ^* a ^* b ^* or the like, and measurement is performed using the magnitude of the color difference.

However, the color change of the image data changes continuously not on the color space but on the image.
It is necessary to consider the continuity on the image. Continuity in a color space does not necessarily indicate continuity in an image. Therefore, in the present embodiment, the color continuity of each color component on an image is checked, and the color continuity is reflected on a color space, thereby specifying a gradual change in color in image data to be displayed. In addition, in the color continuity on the image, when similar colors are continuously present on the image, it indicates that pixels of similar colors are collectively present on the image, and Is an index indicating the goodness of unity of the color components.

The color continuity on an image is calculated by calculating the color difference between each pixel and its neighboring pixels. The smaller the color difference, the higher the continuity, and the larger the color difference, the less the continuity. In the embodiment, the continuity is measured as follows.
First, by storing the value of the upper 4 bits of each pixel of the image data to be displayed in the limited color stored in the image storage unit 1 in the upper 4 bit image storage unit, the image data represented by the upper 4 bits is stored. Is created (step S1).

Next, the mosaic image calculating means 6
The image data is divided on a mesh by cells having a size of 1/20 to 1/40 of the image size to create a mosaic cell image (step S2). Then, as described above, the value of the color component occupying 1/4 or more in the cell (the average value when there are a plurality of 1/4 or more color components) by the mosaic cell color determination means 4 as described above.
Is the mosaic cell color.

The method of selecting the mosaic cell color is not limited to the above method. For example, for each cell, the values of the upper 4 bits of the color components (RGB values) included in the cell are compared, and the principal component analysis is performed. The first principal component vector is obtained when the contribution ratio of the first principal component is 80% or more, and the first and second principal component vectors are obtained when the contribution ratio of the first principal component is less than 80%. Find the composite vector, and
If the contribution rate of the second principal component is less than 80%, a composite vector of the first, second, and third principal component vectors may be obtained and adopted as the mosaic cell color of the cell ( Step S3). Then, a mosaic image in which the mosaic cell colors are assigned to the cells as described above is created, and stored in the mosaic cell color storage unit 5.

The continuity value calculating means 6 calculates the representative value of each cell thus obtained as shown in FIG.
Four (8) radiations of vertical (upper / lower), horizontal (left / right), diagonal left (diagonally upper left / lower left lower), diagonal right (diagonally upper right / lower right lower) The continuity is examined by comparing the representative values of the cells arranged continuously in the direction and checking whether the same value (mosaic cell color of the upper 4 bits) appears continuously.

As shown in FIG. 4, a specific method of calculating the continuity is to first compare the representative value of the cell of interest 41a with the representative value of the cells 41 while sequentially moving along the above-mentioned direction, and to determine the same value. Is counted. When the same value no longer appears, the counting in that direction ends. The above operation is performed in the above eight directions, and the total count of the number of appearances of the same value is defined as the continuity value of the cell of interest 41a. The above operation is performed with all the cells 41 of the image data as the target cell 41a, and the continuity values of all the cells are measured. In FIG. 4, the continuity value of each of the two cells of interest 41a is 3. The continuity value calculated for each cell is
The continuity value of the pixels included in each cell is used.

When selecting a representative color described later, L
Assume a four-dimensional space in which the coordinate axes of the continuity values are added to the ^* a ^* b ^* space. That is, a coordinate axis of the continuity value is created (step S4).

In the method of measuring the continuity value described above, the image data is temporarily converted into a mosaic image, and the color of each mosaic cell of the mosaic image is set to the color that predominates in the mosaic cell, and the entire mosaic image is converted. Although the continuity value of each cell is measured over the range, the image data may be divided into a plurality of regions, and the continuity value may be measured in each of the divided regions.

As a method of dividing the image data into a plurality of areas, for example, the edge of the subject in the image data is emphasized, the contour of the subject is extracted, and the image data is divided by the contour. A known method for dividing a digital image, such as a method for dividing a region by obtaining a spatial frequency distribution using a frequency conversion such as a discrete cosine transform used in JPEG or the like, can be used.

The numerical value of the unity of the color components of each pixel on the image array is not necessarily limited to the above-described measurement of the continuity value. In the above, a method of calculating the ratio of pixels of similar colors may be used.

(B) Conversion to Uniform Color Space In order to select a representative color, first, the color distribution of image data is arranged in a color space. At this time, the uniform color space is set in consideration of human visual characteristics. use. As a uniform color space, the above L ^* u ^*
Use v ^* or L ^* a ^* b ^* . Therefore, the value of each pixel of the image data composed of RGB data is represented by L ^* u ^* v ^* or
Convert to L ^* a ^* b ^* . In the present embodiment, as an example, the details of the conversion by the color conversion means 8 will be described using L ^* a ^* b ^* .

Conversion from RGB data to L ^* a ^* b ^* is performed by the following equation via the XYZ system recommended by CIE 1931. X = 0.61R + 0.17G + 0.20B, (1) Y = 0.36R + 0.59G + 0.11B, (2) Z = 0.066G + 1.12B (3)

When Y / Y _n > 0.008856, L ^* = 116 (Y / Y _n ) ^1/3 −16 (4) When Y / Y _n ≦ 0.008856, L ^* = 903.3 ( Y / Y _n ) (5) X / X _n > 0.008856, Y / Y _n > 0.00885
6, in the case of _{Z / Z n> 0.008856, a} * = 500 {(X / X n) 1/3 - (Y / Y n) 1/3}, (6) b * = 200 {(Y / Y _n ) ^1/3 − (Z / Z _n ) ^1/3 ｝ (7)

0.0088 for X / X _n , Y / Y _n and Z / Z _n
When there are 56 or less, the above equations (6) and (7)
(X / X _n ) ^1/3 , (Y / Y _n ) ^1/3 and (Z / Z _n ) ^1/3 terms are 7.787 (X / X _n ) +16/116 7.787 ( Y / Y _n ) +16/116 7.787 (Z / Z _n ) +16/116. Here, the chromaticity of R, G, B and white is N
It conforms to the TSC television standard. The RGB data of the NTSC television standard is converted into the L ^* a ^* b ^* data recommended by the CIE according to the above conversion formula (step S5).

The four-dimensional space spanned by the L ^* , a ^* , and b ^* axes and continuity values is stored as a cluster image by the cluster storage means 9 (step S6). The cluster storage unit 9 stores clusters that are sequentially divided with cluster numbers, and stores the pixels included in each cluster.

(C) Determination of Principal Component and Principal Component Axis by Principal Component Analysis Principal component analysis will be briefly described with reference to FIG. Note that FIG. 5 shows a two-dimensional distribution of pixels with two variables of the pixels 42... For the sake of simplicity.
As shown in FIG. 5, when the pixels having the bivariates x1 and x2 are plotted, if the group of these pixels is sufficiently close to one straight line, the dispersion of the points on this two-dimensional plane becomes It can be represented by a scatter of one-dimensional points.

In this sense, the direction in which the scatter of the points is greatest, that is, the 0Z direction in the figure can be found, and the component of the 0Z direction of each point can be used as a comprehensive index. This can be similarly considered for an n-dimensional space with n variables. Considering the distribution of n-variable data in this way, the direction with the largest scatter in the n-dimensional space, that is, the direction with the largest variance, is considered to be the direction most suitable for representing the distribution. This variance value is called a principal component, and this direction is called a principal component axis. In this embodiment, the principal component axis calculation means 10 obtains the principal component and the principal component axis for the pixels distributed in the four-dimensional space by a well-known four-component principal component analysis method (step S7).

(D) Creation of Histogram Next, each pixel is projected onto the principal component axis (step S
8). That is, a line perpendicular to the principal component axis is drawn from each pixel distributed on the four-dimensional space, and the intersection of the line and the principal component axis is defined as the position of each pixel projected on the principal component axis. Then, the principal component axis is divided at appropriate class intervals, and the distribution of projected pixels included in each class is set as a histogram (step S9).

(E) Selection of a representative color by the discriminant analysis method The selection of the representative color by the discriminant analysis method of this embodiment is basically the same as that of the above-mentioned prior art, and a threshold is obtained by using a histogram. The color space is sequentially divided into a large number of clusters at the threshold value. In the present embodiment, a four-dimensional space in which coordinate axes representing the continuity are set is used in the color space, and the color space is further divided on the principal component axis. Discriminant analysis is performed using the histogram of the projected pixels.

Here, the principal component axis of each cluster is determined by the principal component axis computing means 10 as described above. Also, in the four-dimensional space or the cluster divided as described later from the histogram,
Cluster (initially a four-dimensional space) by distributed operation means 17
The average and variance of the pixels projected on the principal component axis are calculated (step S10). Further, the weighted distributed operation means 1
8, the weighted variance of each cluster is obtained, the cluster having the largest weighted variance is obtained, and the main component axis of the cluster having the largest weighted variance is divided by the division threshold determined as follows. Will be.

[0063] Here will be described a method for determining the threshold value T _i by the discrimination analysis of dividing threshold determining means 19. When the number of pixel areas S N, the number of pixels in the density values i and n _i, the occurrence probability q _i is given by the following equation. q _i = n _i / N Then, with the density value k, the section [a, b] is divided into two sections C ₁
[A, k] and C ₂ [k + 1, b] are assumed, and the pixel occurrence probabilities ω ₁ , ω ₂ , the average value μ ₁ , μ ₂ , and the variance σ ₁ ² , σ ₂ ² a weighted variance sum sigma _w ² given by: when the determined density values k so as to minimize. σ _w ² = ω ₁ ω ₂ (μ ₁ −μ ₂ )

The value k that maximizes σ _B ² (that is, the threshold value T _{i to be obtained} ) can be obtained sequentially as shown in the following equation (1).

(Equation 1) Here, μ _T is the total average and is shown in the following equation 2.

(Equation 2)

[0065] As described above, it is possible to determine the threshold value T _i of each color component and the continuity values (step S1
1). Then, on the basis of the calculated threshold value T _i , the cluster dividing means 19 divides the four-dimensional space into two clusters on the curved surface orthogonal to the principal component axis on the principal component axis determined by the principal component axis calculating means 10 (FIG. Step S12).

Next, in the newly divided cluster, the principal component and the principal component axis are obtained by the principal component axis calculating means 10 (step S7 '), and the principal component values are compared among all clusters by the cluster sorting means 23. Then, the clusters having the largest principal component value are obtained by sorting the clusters in descending order of the principal component value (step S14) (step S14).
15), this cluster is a cluster to be divided next.
Then, in the obtained cluster, a threshold value T1 is obtained as if the color space was divided, and the cluster is further divided into two clusters.

As described above, of all the divided clusters, the cluster having the largest weighted variance is obtained.
The process of dividing the obtained cluster into two as described above is repeated. Then, when the number of divided clusters becomes equal to the number of representative colors to be displayed, the division ends (step S13). Next, the representative color allocating unit 26 sets the average value of the density values for each color component in each cluster as the representative color (step S16), and the color converting unit 25 performs the inverse conversion of the color converting unit 8 on the representative color. The representative color is R
The GB value is set (step S17).

The representative color is registered as a color code in the color map 30d of the color map display device 30, and the color distribution in the color space of the color image data to be displayed is associated with each of the clusters. A color similar to the original color of the pixel (the average color of the cluster to which the pixel belongs) is assigned to the pixel as a color code from the color map 30d. In this manner, the image data of which color is assigned to each pixel and whose color is limited is displayed on the display 30b of the color map display device 30 having the color map 30d in which the color code is registered.

As described above, according to the limited color determining apparatus of this embodiment, first, the pixel value (R, G, B) is set to (L ^* ,
a ^* , b ^* ). Then, each pixel value (R, G, B)
A mosaic image is obtained from the upper bit image by the mosaic image calculation means, the continuity of the representative color of the mosaic cell on the screen is quantified, and the continuity value axis is determined by associating each pixel with the mosaic image. Then, a principal component axis of each cluster is obtained for a cluster image obtained by expanding an image in a four-dimensional space spanned by four axes including the three axes L ^* , a ^* , and b ^* obtained previously.

Next, the process of dividing the cluster into two by the division threshold value on the principal component axis obtained by applying the discriminant analysis by the division threshold value determination means is repeated. Then, when the target number of colors is reached, the division of the cluster ends. After the division is completed, the representative color of each cluster is assigned to an image, stored in a color map, and displayed approximately on a color display with a predetermined number of colors. For a full-color display device, the original image is also displayed and can be compared on the display. When a part of the limited color is changed in this comparison, the color can be easily corrected by the color correcting unit 28 and the limited color palette unit 27.

From the above, the color image limited color display method and apparatus of the present invention can be used to display a natural image which should be originally displayed on a full color display apparatus even on a color map display apparatus capable of simultaneously displaying only a limited number of limited colors. Can be displayed. In particular, for natural image display on a CD-ROM or the like where it is necessary to reduce the number of colors, such as 50 colors or less, by determining limited colors in consideration of the continuity of colors on the image, the color change By assigning as few limited colors as possible to a portion having a small number of colors and assigning colors as much as possible to a portion having a large color difference, a limited color can be obtained effectively.

Further, in the case of a moving image, by compressing each image into a small number of colors, a limited color for a plurality of images can be realized by a combination of the small number of colors, which is very effective for data compression. is there. Processing time is required to reduce the number of colors according to the present invention, but when displaying a compressed image obtained by this method, decoding processing is not required, so instant display is possible without depending on machines or systems. It is. Of course, the image data of which the number of colors has been reduced according to the present invention may be subjected to the recommended image compression using JPEG or the like, and the compression rate is more effectively increased. For these reasons, the limited color determination method and apparatus of the present invention can be expected to be used in many industrial fields.

Note that the entirety of these processes can be configured as a program on a general-purpose computer and executed. Further, the memory capacity per pixel of the original image data does not necessarily have to be 24 bits, and the upper bits used for specifying the color change need not be the upper 4 bits. The number of high-order bits to be taken may be changed depending on the memory capacity per pixel of the original image data.

[0074]

[0075]

Effects of the Invention According to the limited color determination method and limited color determining apparatus of the above claims 1 and 2, wherein, when determining the representative colors by discriminant analysis, the pixels of the image data to the three coordinate axes of the uniform color space Since the representative color is determined from the distribution of pixels in this multidimensional space, the representative color is determined from the distribution of pixels in this multidimensional space, by expanding the numerical value of the coherence of the color components of the pixels on the image array. When determining, the hue distribution on the image can be reflected.

[0076] Further, determine the principal component axis by the main component analysis, since performing the determination of the threshold by the discrimination analysis on frequency distribution of pixels projected on the major component axis, distribution of pixels of the four-dimensional space Can be determined. Therefore, when the image data is displayed with a small number of representative colors, it is possible for the human eyes not to feel uncomfortable.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating an outline of a limited color determining apparatus according to an embodiment.

FIG. 2 is a flowchart illustrating an algorithm according to a limited color determination method of the embodiment.

FIG. 3 is a diagram for explaining the above-described limited color determining method.

FIG. 4 is a view for explaining the above-described limited color determining method.

FIG. 5 is a drawing for explaining the above-described limited color determining method.

[Explanation of symbols]

2 Upper 4-bit image storage means (Numerization means) 3 Mosaic image calculation means (Numerization means) 4 Mosaic cell color determination means (Numerization means) 5 Mosaic cell color storage means (Numerization means) 6 Continuity value calculation means (Numericalizing means) 7 Continuity value storing means (Numericalizing means) 10 Main component axis calculating means 12 Color component axis projecting means (Projecting means) 14 Projection value histogram calculating means (Frequency distribution calculating means) 19 Division threshold value determining means ( Dividing threshold calculating means) 21 Cluster dividing means (area dividing means)

Claims (2)

(57) [Claims] 1. A color image data expressed by a coordinate system of three primary colors is converted into a coordinate system of a uniform color space, and discrimination analysis is performed on a frequency distribution of each pixel of the image data in the converted coordinate system. The representative color is obtained by repeating the process of dividing the uniform color space into two regions, and further dividing the divided region into two regions to obtain a representative color. In the limited color determination method for approximating the display, the color component of each pixel arranged on the image of the image data is
From the distribution on the image array, the color of each pixel on the image array
The goodness of the unity of the components is digitized, and the color components of each pixel on this digitized image array are grouped.
The goodness of the ball is associated with each color component of each pixel,
Newly set coordinate axes indicating the goodness of color component cohesion
By providing a multidimensional space, the above discrimination analysis allows the multidimensional space to be used instead of the uniform color space.
It is assumed that the original space is sequentially divided into a plurality of regions, and in dividing the multi-dimensional space , principal component analysis is performed on the distribution of each pixel of the image data in the multi-dimensional space or the divided region of the multi-dimensional space. The main component axis is obtained by performing the above operation. Then, each pixel developed in the multidimensional space or the area is projected on the main component axis. Then, on the main component axis on which each pixel is projected, A frequency distribution is obtained, and a discrimination analysis is performed on the frequency distribution to obtain a division threshold value on the principal component axis. In the division threshold value on the principal component axis, the multidimensional space or region is divided into the main component axis. A limited color determining method, characterized in that the limited color is divided by a curved surface perpendicular to the image. 2. Converting color image data expressed in a coordinate system of three primary colors into a coordinate system of a uniform color space, and performing discriminant analysis on a frequency distribution of each pixel of the image data in the converted coordinate system. The representative color is obtained by repeating the process of dividing the uniform color space into two regions, and further dividing the divided region into two regions, thereby obtaining a representative color having a limited number of colors by specifying the image data. In the limited color determination device that approximates the display of the image data, the value of the unity of the color components of each pixel on the image array is numerically determined from the distribution of the color components of each pixel arranged on the image of the image data on the image array. a digitizing means for reduction, the goodness chunk of newly color components to the color space in association with each color component of each pixel of the goodness of unity of the color components of each pixel on the digitized image sequences The coordinate axes The multidimensional space formed by a constant, the multi-dimensional space if
Or the above image data in a region obtained by dividing a multidimensional space.
By performing principal component analysis on the distribution of each pixel of
A principal axis calculating means for determining a principal axis; and a principal axis of each pixel on the principal axis on which each pixel is projected.
A frequency distribution calculating means for obtaining a frequency distribution, and performing discriminant analysis on the frequency distribution,
Means for calculating a division threshold value on a principal component axis;
And in the division threshold on the principal component axis, a multidimensional space or
For the area that divides the above area by a curved surface perpendicular to the above principal component axis
And a splitting means.
Place.