JP3289792B2 - Color correction method for specific area of color image - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for correcting the color of a specific area corresponding to each object in an image in a printing process.

[0002]

2. Description of the Related Art When printing a catalog or a flyer of a product, a process of deleting a background portion from an image converted into digital data by a scanner is sometimes performed. As a method for this, a background image and an object portion are separated by binarizing the image, and a mask image (referred to as a cutout mask) in which the background portion is “OFF” and the object portion is “ON” is created. Then, a technique of combining this with an input image to extract only the object portion is used.

[0003] As a method of binarization, pixels in an image plane are mapped to a color space (for example, RGB space), and each pixel is turned "ON (object part)" by clustering in that space.
Or "OFF (background portion)" and binarizes the data.

[0004] It is also possible to perform color correction only in the region extracted in this way.

A technique necessary for extracting a specific area and correcting a color as described above is an area division method based on clustering in a color space.

As shown in FIG. 1, pixels in an image plane are mapped to a color space (for example, an RGB color space), and a cluster boundary set according to a distance from a cluster center of gravity in the space is used. In this method, each pixel is classified and labeled as 1, 2, 3 and the like by clustering, and a region division image is obtained by inverse mapping on an image plane to perform region division.

[0007]

According to this conventional method, when pixels in the same area are always localized at a specific place in the color space, the area can be divided well, but this is not the case in an actual image. Often. Therefore, despite being the same area, it has been a problematic method to be divided into a plurality of areas, different areas to be regarded as one area, or to be used independently.

The present invention has been made to solve the above-mentioned conventional problems, and based on a model of distribution of an image in a color space, a new clustering method has been implemented from a completely different viewpoint from the conventional method. It is another object of the present invention to provide a color correction method for a specific area of a color image, which efficiently performs color correction for a specific area by this method.

[0009]

SUMMARY OF THE INVENTION The present invention provides a method for correcting a color in a specific area of a color image in a color space including a lightness axis .
Characteristic of the color distribution estimated from the reflection model of the object ,
It is modeled as a curve from “black” through “object color” to “white”, and the curve corresponds to a predetermined brightness that can be distinguished.
By mapping each pixel on the two-dimensional parameter space, a distribution in which pixels in the same region are localized at a specific place is obtained, and region division is performed by performing clustering on the two-dimensional parameter space. The above object has been achieved by designating a region on a display and correcting the color of the designated region.

[0010]

Normally, an image is shot by illuminating an object having a three-dimensional spread with illumination light, passing the reflected light through an appropriate lens system, and mapping the reflected light on a two-dimensional plane.

One object has the same spectral reflectance, that is, has the same color, and various gradations occur depending on the relationship between the illumination light, the angle of the object surface, and the position of the viewpoint. However, this gradation changes along a certain curve in the color space. The reason is that the part that is shadowed and the illumination light does not reach is black, and in the area of the object surface where the emission angle determined by the incident angle when the illumination light is incident and the line of sight to the object are close to the surface of the object, In most cases, the mirror is in a specular reflection state, which is a so-called catch light place. In this part, the light of all wavelengths is reflected at a certain reflectance of the illuminating light, so it becomes the same "white" as the illuminating light. Because of the distribution, the pixels in the same area (same object)
In a color space (for example, L * u * v * space), as shown in FIG. 2, it is considered that there is a tendency to concentrate and distribute on a curve of black → object color → white. You can confirm that you are doing. Here, L * represents lightness, the distance from the L * axis in the u * v * plane represents saturation, and the rotation angle represents hue.

Therefore, when viewing the entire image, as shown in FIG. 3, there are a plurality of banana-shaped distributions in which an ellipsoid is bent as many as the number of regions (the number of objects) as shown in FIG. Become.

However, in the conventional method, these are not taken into consideration at all, and as shown by a broken line in FIG. 4, even though the area is the same area (object), it is divided into a plurality of areas. As indicated by a broken line, different regions (objects) may be regarded as one region, and the conventional clustering method is incomplete as a region division method.

In the present invention, the problem of the conventional method is solved by performing clustering based on the distribution model described above so as to separate a plurality of bent ellipsoidal distributions corresponding to each region.

Hereinafter, the clustering method of the present invention will be described in detail.

Now, as shown in FIG. 6, a color space (for example, L * u
* V * space), consider a group of curves passing through a point A representing “black” and a point B representing “white”. Then, any pixel is
Although represented as one point in the color space, it always belongs to one curve in the curve group. That is, one curve corresponds to one pixel.

Since two parameters are sufficient to distinguish each curve, each pixel can be expressed by mapping it to one point on a two-dimensional parameter space. For example, as shown in FIG. 7, as a set of curves, a set of semi-ellipses passing through points A and B is considered, and the position of the origin on the lightness axis is moved according to L = L * -50 (1). Thus, the range that L * can take is 0 ≦ L * ≦ 10
Normalize to 0.

Here, since the plane at which one semiellipse intersects the L = 0 plane is uniquely determined, the group of semielliptic curves is represented by the parameter (u, v *) coordinate value (μ, ν) of the intersection. Can be

Therefore, each pixel can be mapped on the L = 0 plane by a kind of projection operation along the semi-ellipse.

When the distribution of the actual image in the color space is, for example, as shown in FIG. 8, by such mapping, the distribution as shown in FIG. 9 is obtained on the (μ, ν) plane. A distribution localized for each region can be obtained. In this way, after mapping to the feature space, efficient region division can be performed by using a normal clustering method.

In the present invention, using the area information divided into a plurality of areas, for example, using a pointing device such as a mouse on a display, the "ON", "OFF"
Is specified, only pixels belonging to the cluster centroid corresponding to “ON” are moved in the (μ, ν) space,
Correct the color of the specific area.

[0022]

Embodiments of the present invention will be described below in detail with reference to the drawings.

An apparatus for carrying out this embodiment is shown in FIG.
As shown in FIG. 1, the image processing apparatus includes a color space conversion unit 10, a conversion unit 20 for converting into a feature space, a region division unit 30, a region designation unit 40, a color correction unit 50, and an inverse conversion unit 60.

The color space conversion unit 10 receives an input image signal,
For example, an RGB signal is converted into an L * u * v * signal. RG
From B to tristimulus values XYZ in the XYZ coordinate system, from XYZ to L
The conversion to * u * v * has been established, from RGB to XY
The conversion into Z is defined by the following equation (see Makoto Miyahara, “Systematic Image Coding”, IPC, p. 134).

[0025]

(Equation 1)

The conversion from XYZ to L * u * v * is as follows:
It is defined by the following equation (see “Image Analysis Handbook”, supervised by Mikio Takagi and Hirohisa Shimoda, pages 107-108 of the University of Tokyo Press).

[0027]

(Equation 2)

Here, (X 0, Y 0, Z 0) is (X, Y, Z) for a perfectly diffused white surface under a standard light source.
In the case of the standard light source C (color temperature of 6774K), (X0, Y0, Z0) = (98.072, 100.00, 118.225).

In this embodiment, L * u * v * is used as a color space.
Although the color system is used, an equivalent effect can be obtained by considering an appropriate curve group that passes through “black → object color → white” in other color spaces such as the L * a * b * color system. Can be expected.

The conversion unit 20 for converting into a feature space is (L *,
u *, v *) are converted to points (L,
μ, ν). From FIG. 11, the conversion formula is obtained in algebraic geometry, and is as follows.

[0031]

(Equation 3)

The area dividing section 30 samples all the images, generates training data from the values of (μ, ν) for each pixel, and generates ISODATA (Itera) data.
tiveSelf Organizing Data Analysis Technologies
2) clustering by the method (see “Image Analysis Handbook”, supervised by Mikio Takagi and Hirohisa Shimoda, pages 648 to 651 of the University of Tokyo Press).

In the ISODATA method, an appropriate cluster is given as an initial state, and its members are rearranged to obtain a “better cluster” little by little. As a method representative of non-hierarchical clustering (relocation method), It is a technique that has been known for a long time.

FIG. 12 shows the procedure of the ISODATA method.

In the ISODATA method, first, in step 100, parameters such as a relocation convergence condition, a small cluster, a decision condition for isolated data, and a splitting / fusion branching condition are set.

Next, in step 102, the center of gravity of the initial cluster is determined. For example, the total average can be used with the number of initial clusters being one.

Next, in steps 104 to 108, a rearrangement method is performed. Specifically, first, step 104
Then, the distance between each data and the center of gravity of the cluster is calculated, and each data is arranged in the cluster having the minimum distance.
Next, the process proceeds to step 106, where the center of gravity of each cluster is recalculated and corrected in the rearranged clusters. Then
Proceeding to step 108, if the average of the distance between each data and the center of gravity of the cluster does not change as a result of the rearrangement / correction of the center of gravity, it is regarded as converging.

After completion of the rearrangement method, the process proceeds to step 110,
Small clusters with a significantly smaller number of data and isolated data significantly separated from other clusters are excluded from subsequent clustering.

Next, proceeding to step 112, when the minimum value of the distance between the centers of gravity of the clusters is equal to or greater than a certain threshold value and the maximum value of the variance of the clusters is equal to or less than a certain threshold value, the clustering is concluded as having converged. Otherwise, go to step 114 and / or 116.

If the minimum value of the distance between the cluster centroids is equal to or smaller than a certain threshold value, the routine proceeds to step 114, where the cluster pairs are integrated and a new cluster centroid is calculated.

On the other hand, if the maximum value of the variance of the cluster is equal to or greater than a certain threshold, the process proceeds to step 116, where the cluster is divided until the maximum value of the cluster variance is equal to or less than the threshold, and a new cluster centroid is calculated. .

Integration by step 114 or step 1
After the division by 16 is completed, the process returns to step 104 again to repeat the processing.

In this way, cluster division (cluster boundaries are shown by broken lines) and cluster representative points 1, 2, and 3 (shown by circles) as shown in FIG. 13 are obtained.

As described in the section of operation of the present invention, each of the representative points 1, 2, and 3 corresponds to one semi-ellipse representing a region as shown in FIG. After this, it is determined which semi-ellipse each pixel belongs to, labeling is performed, and the region division is completed.

The area designating section 40 designates a specific area from the divided areas.
Corrects the color of the specified area.

Hereinafter, this will be described in detail.

As a method of designating an area, for example, FIG.
As shown in FIG. 5, the image 7 input on the display 70
2 and a color palette 7 corresponding to the cluster centroid of each area
4 is displayed, and the color palette corresponding to the color of the area to be extracted is clicked with the mouse 76 to turn “ON”.
An area is designated, and the other areas are designated as “OFF” areas, and the area is designated.

Alternatively, an image is displayed as shown in FIG.
One point in the area to be designated (for example, the door part of the house in FIG. 15) is clicked with the mouse, and the area belonging to the cluster corresponding to the point designated by the mouse is “ON”, and the other areas are “OFF”. And specify the area. At this time, in order to specify a plurality of areas, this may be repeated.

In order to confirm whether or not an area has been correctly extracted in the above-mentioned area designation,
The pixels in the “OFF” area are displayed in reverse video.

After specifying the area as described above, the color correcting section 50 sets the cluster centroid of the “ON” area to
Specify how much to change in the saturation direction or hue direction, and specify only the pixels belonging to the cluster in the "ON" area.
According to the amount of change, conversion is performed on the (μ, ν) space. For example, as shown in FIG. 16, (μ, ν)
The spatial distribution and the cluster centroid are displayed, and an arbitrary point on the screen is clicked as shown at 80 in FIG. 16, the mouse pointer is moved as at 82, and the amount of change is designated, as shown at 84. By clicking the mouse button again,
The operation for color correction by the color correction unit 50 described later is started for all designated areas. At this time, the cluster center of gravity of the designated area 86 moves so as to follow the movement of the mouse.

The following methods are available for area designation and color correction.

That is, first, as shown in FIG. 17, an image and a distribution in the (μ, ν) space are displayed on the display. In FIG. 18, the mark ● represents the pixel value of each pixel in the (μ, ν) space, and is displayed on the display with a color corresponding to the pixel value, and the color to be corrected is displayed in the (μ, ν) space. So that you can see at a glance where they are. The crosses indicate the cluster centroids.

Next, the color to be corrected is designated by the mouse.
As shown in FIG. 19, the mouse pointer is moved to the cluster centroid of the cluster representing the color area to be corrected, and the color area is designated by pressing (clicking) the mouse button.

At this time, in order to make it clear which region the designated cluster represents in the image, the portion other than the designated region is highlighted as shown in FIG.

Next, as shown in FIG. 21, the movement is performed in the (μ, ν) space by an amount to be changed, and the amount of change is designated.
At this time, only the mark “x” representing the center of gravity of the cluster moves following the pointer. When the movement is completed, click the mouse button again at that position to enter the color correction operation.

The color correction unit 50 performs a color correction operation, and determines how much the hue and saturation directions should be changed from the (μ, ν) values of the cluster centroids before and after the correction. That is, the values of θ and α in FIG. 22 are obtained by calculation. Using the obtained θ and α, as shown in FIG.
The actual pixel value is changed and displayed in the (μ, ν) space.

Finally, at the same time, the actual image is also corrected and displayed, and as shown in FIG. 24, the inverted display is returned to the original state, and the color correction is completed.

The inverse converter 60 determines that the signal after color correction is L
Since μν, this is inversely transformed into an L * u * v * signal.
According to the equation (8), the inverse transformation is as follows.

[0059]

(Equation 4)

This L * u * v * is returned to an RGB signal. The conversion formula for converting L * u * v * into XYZ is as follows.

[0061]

(Equation 5)

The conversion from XYZ to RGB is defined by the following equation.

[0063]

(Equation 6)

By the above-described inverse transformation, an image in which only the specific area is color-corrected is created.

[0065]

As described above, according to the present invention, the brightness axis
The feature of the color distribution estimated from the reflection model of the object on the color space including is modeled as a curve from "black" through "object color" to "white", and the curves can be distinguished . To the predetermined brightness
Since clustering is performed on the corresponding two-dimensional parameter space, pixels in the same region are more likely to be localized at a specific location on the parameter space. As a result, better region division can be performed as compared with the conventional method. This makes it possible to perform color correction of a specific area efficiently.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a conventional clustering method on an RGB color space.

FIG. 2 illustrates L * u * v * for explaining the principle of the present invention.
Diagram showing an example of the distribution of the object color of one object in space

FIG. 3 is a diagram showing an example of an object color distribution of a plurality of objects in the entire image.

FIG. 4 is a diagram showing an example of a division result by a conventional clustering method in an L * u * v * space.

FIG. 5 is a diagram showing another example in L * u * v * space.

FIG. 6 is a view showing a point representing “black” and “white” on an L * u * v * space for explaining the clustering method of the present invention.
Diagram showing a group of curves passing through points representing

FIG. 7 is a diagram showing a state in which a possible range of L * is normalized.

FIG. 8 is a diagram illustrating an example of distribution of an actual image in a color space;

FIG. 9 is also obtained by mapping (μ,
ν) Diagram showing distribution on plane

FIG. 10 is a block diagram showing an overall configuration of an apparatus for implementing an embodiment of the present invention.

FIG. 11 is a diagram for explaining a conversion formula used in a feature space conversion unit of the embodiment.

FIG. 12 is a flowchart for explaining an example of a two-dimensional clustering method used in the region dividing unit of the embodiment.

FIG. 13 is a diagram showing cluster division and cluster representative points obtained by the embodiment.

FIG. 14 shows L * u * v * including the cluster representative points in FIG.
Diagram showing areas in space

FIG. 15 is an explanatory diagram of a display displaying an image for specifying an area with a mouse and a color palette;

FIG. 16 is a diagram showing the distribution of (μ, ν) space and the amount of change in the center of gravity of the cluster;

FIG. 17 shows images and (μ,
ν) Explanatory diagram of display displaying distribution in space

FIG. 18 is a diagram showing pixel values and cluster centroids in (μ, ν) space;

FIG. 19 is a diagram showing a cluster centroid of a color area to be corrected;

FIG. 20 is an explanatory diagram of a display in which an area other than a designated area is highlighted.

FIG. 21 is a diagram showing a change amount of a cluster centroid;

FIG. 22 is a diagram showing a hue direction of a cluster centroid and a change amount of a saturation method;

FIG. 23 is a diagram showing a cluster after correction in which pixel values are moved.

FIG. 24 is an explanatory diagram of a display for displaying an image after color correction.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 10 ... Color space conversion part 20 ... Conversion part to feature space 30 ... Area division part 40 ... Area specification part 50 ... Color correction part 60 ... Inverse conversion part 70 ... Display

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification code FI G06T 11/60 120 G06T 11/60 120A H04N 1/46 H04N 1/40 D 1/60 1/46 Z (58) Fields surveyed (Int.Cl. ⁷ , DB name) G06T ^7/ 00-7/60 H04N 1/46 H04N 1/40-1/419

Claims (1)

(57) [Claims] 1. A reflection model of an object on a color space including a lightness axis.
The characteristic of the color distribution estimated from the color is modeled as a curve from “black” through “object color” to “white”, and the two-dimensional parameter corresponding to a predetermined brightness that can distinguish the curve. > By mapping each pixel on the data space, a distribution is obtained in which the pixels in the same area are localized at a specific location, and the area is divided by performing clustering on the two-dimensional parameter space. A color correction method for a specific area of a color image, wherein an area is specified on a display and the color of the specified area is corrected.