JP6187119B2 - Image color adjustment apparatus, image color adjustment method, and program - Google Patents

Description

  The present invention relates to an image color adjustment apparatus that performs color adjustment on a target image.

  In recent years, with the spread and deep cultivation of IT technology, consumer product purchase forms have also changed, and electronic merchant services capable of purchasing products via the Web are rapidly growing. As an electronic trading business service for consumers, a Web service (hereinafter referred to as an EC (Electronic Commerce) site) that allows customers to easily purchase products at home has become widespread, and there is a style of purchasing products through EC sites. It is becoming a new culture as a product purchase. In addition, in order to respond to such consumer values, the number of providers and mechanisms that provide services are still increasing.

  By the way, in order for a service provider to construct a product purchase EC site for consumers, it is indispensable to take a product image. It is the current mainstream to take a few cuts.

  In the early stage of the EC site launch, the photographer of the EC site took a photograph and corrected the image in order to accurately convey the texture, atmosphere and color of the product.

  In general, various image correction methods have been proposed. For example, Patent Document 1 discloses that when a replica is created, two images with and without flash are continuously photographed, and the subject color with flash is set without flash. Techniques for matching colors have been proposed.

JP 2011-124955 A

  In recent years, there has been a demand for shooting speed and low shooting cost that can handle mass-product shooting in a short period of time, so for example, shooting with fixed shooting conditions to maintain shooting speed and shooting cost can be reduced. In order to do this, there are an increasing number of cases where non-professional photographers and staff take pictures and manage products.

  As a result, it has become difficult to maintain photo quality. In particular, one of the problems caused by the current shooting style is “color difference for each shooting cut of the same product”. For EC site users who have to decide whether or not to purchase with the color of the posted photo, the color difference is a fatal problem, and the reliability of the site itself is impaired. The color difference must be resolved by some method.

  As a general method for resolving the color difference, manual image retouching can be mentioned. However, as described above, due to recent changes in the shooting style, in the case of shooting by a photographer or worker who does not have skills Therefore, there is a need for a skillless and simple color matching method that does not require advanced correction technology.

  However, with the technique described in Patent Document 1, for example, when the shooting angles such as hanging shooting and up shooting are different, it is difficult to easily perform color matching without skill.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to provide an image color adjustment device that can easily perform color adjustment on images of the same subject with different shooting angles. That is.

A first invention for achieving the above-described object is an image color adjustment device for color-adjusting image data of the same subject having different shooting angles, and performs reference image data and color adjustment that are targets of color adjustment. Input means for inputting desired matching image data, reference marking image data in which the subject area of the reference image data is marked, and image creation means for creating matching marking image data in which the subject area of the matching image data is marked First color acquisition means for acquiring a first pixel color of the subject area of the reference image based on the marking information of the reference marking image data, and a subject of the matching image based on the marking information of the matching marking image data The second pixel of the region A second color acquisition means for acquiring a main color space area determining means for determining a main color space area from the second pixel color acquired by the second color acquisition means, and the main color space area Approximate color space region search means for searching whether there is a region with a high distribution density of the first pixel color acquired by the first color acquisition means in a peripheral region of the color space region corresponding to As a result of the search by the approximate color space area search means, when an approximate color space area exists in the reference image data, an average value of the second pixel colors in the main color space area and the approximate color space area A difference value calculating unit that calculates a difference value from an average value of the first pixel colors, and a color map that color-maps the main color space region to the approximate color space region based on a calculation result by the difference value calculating unit And means comprising An image color adjustment apparatus.
According to the first invention, color adjustment can be easily performed on images of the same subject having different shooting angles.

The main color space region determining means determines a small color space region having a high pixel density distribution of the second pixel color as a main color space region.
As a result, a main color space region having a high pixel density distribution can be easily searched.

The approximate color space area search means is a small space having a high pixel density distribution of the first pixel color in the same area as the main color space area determined by the main color space area determination means and its peripheral area. A region is searched as the approximate color space region.
As a result, the approximate color space region and the main color space region can be associated with each other.

The color mapping means attenuates the mapping intensity according to the distance in the color space from the color mapping center point.
As a result, the closer to the average value, the closer the color map intensity becomes to 1.0, and the closer to the average value, the closer to the color map intensity to 0.0.

The image creating means creates a mask image from matching marking image data in which the subject area of the matching image data is marked, and the color mapping means color maps only the mask area in the mask image.
As a result, the color mapping can be applied only to the mask region.

According to a second aspect of the present invention, there is provided an image color adjustment method performed by an image color adjustment device that performs color adjustment on image data of the same subject having different shooting angles, and reference image data that is a target of color adjustment, and matching for which color adjustment is desired. An input step of inputting image data; reference marking image data in which a subject region of the reference image data is marked; and an image creation step of creating matching marking image data in which a subject region of the matching image data is marked; Based on the marking information of the reference marking image data, a first color acquisition step of acquiring a first pixel color of the subject area of the reference image; and based on the marking information of the matching marking image data, Second A second color acquisition step of acquiring a primary color; a main color space region determination step of determining a main color space region from the second pixel color acquired in the second color acquisition step; and the main color Approximate color space region search step for searching whether there is a region having a high distribution density of the first pixel color acquired in the first color acquisition step in a peripheral region of the color space region corresponding to the space region As a result of the search in the approximate color space area search step, if an approximate color space area exists in the reference image data, the average value of the second pixel color in the main color space area and the approximate color space area A difference value calculation step of calculating a difference value from an average value of the first pixel colors in the image, and a color mapping of the main color space region to the approximate color space region based on a calculation result of the difference value calculation step A color mapping step that is an image color adjustment method characterized by including the.
According to the second invention, color adjustment can be easily performed on images of the same subject having different shooting angles.

According to a third aspect of the present invention, there is provided a computer, an input unit that inputs reference image data that is a target of color adjustment, and matching image data that is desired to be color adjusted, reference marking image data in which a subject area of the reference image data is marked, And image creation means for creating matching marking image data in which the subject area of the matching image data is marked, and a first pixel color of the subject area of the reference image is acquired based on the marking information of the reference marking image data 1 color acquisition means, based on the marking information of the matching marking image data, second color acquisition means for acquiring the second pixel color of the subject area of the matchon image, and the second color acquisition means acquired by the second color acquisition means From the second pixel color to the main color space region A main color space region determining means to determine, and a region having a high distribution density of the first pixel color obtained by the first color obtaining device exists in a peripheral region of the color space region corresponding to the main color space region. As a result of the search by the approximate color space area search means for searching whether or not the approximate color space area exists in the reference image data, the second color in the main color space area A difference value calculation means for calculating a difference value from an average value of pixel colors and an average value of the first pixel colors in the approximate color space area, and the main color space area based on a calculation result by the difference value calculation means Is a program for functioning as color mapping means for performing color mapping on the approximate color space region.
By installing the program of the third invention on a general-purpose computer, the image color adjusting device of the first invention can be obtained.

  According to the present invention, it is possible to easily perform color adjustment on images of the same subject having different shooting angles.

It is a figure which shows the structural example of the hardware of the image color adjustment apparatus which concerns on embodiment of this invention. It is a block diagram which shows the function structural example of an image color adjustment apparatus. It is a figure which shows an example of an input / input image. It is a figure which shows an example of a marking image. It is a figure which shows an example of the pixel distribution of a reference image, and the pixel distribution of a matching image. It is a figure which shows typically a mode that a main color space area | region is searched. It is a figure which shows typically a mode that an approximate color space area | region is searched. It is a figure which shows typically the average value of the pixel color which belongs to an approximate color space area | region, and the average value of the pixel color which belongs to the main color space area | region of a matching image. It is a figure which shows the waveform of the weighting intensity function f (x). It is a flowchart explaining an image color adjustment process. It is a figure explaining the mapping process in case a color map does not interfere. It is a figure explaining the mapping process in case a color map does not interfere.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[Embodiments of the present invention]
FIG. 1 is a diagram illustrating a hardware configuration example of an image color adjusting apparatus 1 according to an embodiment of the present invention. Note that the hardware configuration in FIG. 1 is an example, and various configurations can be adopted depending on the application and purpose.

  The image color adjustment apparatus 1 includes a control unit 11, a storage unit 12, a media input / output unit 13, a communication control unit 14, an input unit 15, a display unit 16, a peripheral device I / F unit 17 and the like connected via a bus 18. Is done.

  The control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The CPU calls and executes a program stored in the storage unit 12, ROM, recording medium, or the like to a work memory area on the RAM, drives and controls each device connected via the bus 18, and controls the image color adjusting device 1. The process to be described later is realized. The ROM is a non-volatile memory, and permanently stores a boot program of the image color adjustment apparatus 1, a program such as BIOS (Basic Input / Output System), data, and the like. The RAM is a volatile memory, and temporarily stores a program, data, and the like loaded from the storage unit 12, ROM, recording medium, and the like, and includes a work area used by the control unit 11 to perform various processes.

  The storage unit 12 is an HDD (hard disk drive) or the like, and stores a program executed by the control unit 11, data necessary for program execution, an OS (operating system), and the like. As for the program, a control program corresponding to the OS and an application program for causing the image color adjusting apparatus 1 to execute processing to be described later are stored. Each of these program codes is read by the control unit 11 as necessary, transferred to the RAM, read by the CPU, and executed as various means.

  The media input / output unit 13 (drive device) inputs / outputs data, for example, media such as a CD drive (-ROM, -R, -RW, etc.), DVD drive (-ROM, -R, -RW, etc.) Has input / output devices.

  The communication control unit 14 includes a communication control device, a communication port, and the like, and is a communication interface that mediates communication between the image color adjustment device 1 and the network, and performs communication control between other devices via the network. . The network may be wired or wireless.

  The input unit 15 inputs data and includes, for example, a keyboard, a pointing device such as a mouse, and an input device such as a numeric keypad. An operation instruction, an operation instruction, data input, and the like can be performed on the image color adjustment apparatus 1 via the input unit 15.

  The display unit 16 includes a display device such as a CRT monitor and a liquid crystal panel, and a logic circuit (such as a video adapter) for realizing the video function of the image color adjusting device 1 in cooperation with the display device.

The peripheral device I / F (interface) unit 17 is a port for connecting the peripheral device to the image color adjusting device 1, and the image color adjusting device 1 receives data from the peripheral device via the peripheral device I / F unit 17. Send and receive. The peripheral device I / F unit 17 is a USB (Universal Serial
Bus) and IEEE (The Institute of
Electrical and Electronics Engineers) 1394, RS-235C, etc., and usually has a plurality of peripheral devices I / F. The connection form with the peripheral device may be wired or wireless.

  The bus 18 is a path that mediates transmission / reception of control signals, data signals, and the like between the devices.

  FIG. 2 is a block diagram illustrating a functional configuration example of the image color adjusting apparatus 1. At least a part of the functional units shown in FIG. 2 is realized by executing an image color adjustment processing program by the control unit 11 of FIG.

  The image input unit 21 receives the RGB of the same subject having different shooting angles from the media and the peripheral device via the storage unit 12, the media input / output unit 13, the communication control unit 14, or the peripheral device I / F (interface) unit 17. An image is input, an image that is a target of color adjustment is set as a reference image, and an image that is subjected to color adjustment is output as a matching image to the image creating unit 22. For example, a reference image R as shown in FIG. 3A and a matching image M as shown in FIG. 3B are input to the image input unit 21 and output to the image creation unit 22.

  The image creation unit 22 creates a reference marking image and a matching marking image based on the marking instruction input by the user via the input unit 15.

  For example, when the user designates the marking MK1 for the subject area that is the target of color adjustment in the reference image R (FIG. 3A), the image creating unit 22 uses the reference as shown in FIG. A marking image RM is created. In addition, the user instructs the marking MK2 for the subject area for which color adjustment is to be performed on the matching image M (FIG. 3B). It should be noted that it is desirable to generate an alpha mask for at least the matching image M in order to prevent color changes other than the region where color adjustment is desired. Therefore, for the matching image M, the marking MK3 is instructed even for an area where the color is not desired to be changed. In response to these instructions, the image creating unit 22 creates a matching marking image MM as shown in FIG. For the matching image M, an alpha mask image α as shown in FIG. 4C is generated based on the marking information of the matching marking image MM. Then, color mapping is performed only on the alpha mask area αA by a process described later.

  An algorithm for generating an alpha mask using the marking information is a known technique and is described in, for example, “A Closed Form Solution to Natural Image matting”.

The Lab conversion unit 23 converts the reference image and the matching image from the image creation unit 22 from the RGB space to the Lab color space. As a conversion method from the RGB space to the Lab color space, a known method can be used.
The Lab color space is a type of complementary color space, “L” representing lightness (brightness), “a” representing chromaticity from red (R) to green (G), and blue (B) to yellow (Y 3) “b” representing the chromaticity of), and the amount of change in this three-dimensional space is corrected to be proportional to the impression of the visual color change caused by the change, all that can be perceived by humans It is a color model that represents the color of.

  The Lab conversion unit 23 supplies the reference image R and the matching image M converted to the Lab color space to the first color acquisition unit 24 and the second color acquisition unit 25, respectively.

  The first color acquisition unit 24 acquires, from the reference image R, the pixel color (reference color) of the same coordinates marked for the subject area that is the target of color adjustment in the reference marking image RM. In the example of FIG. 4A, the pixel color on the trajectory followed by the marking MK1 in the reference marking image RM is acquired from the reference image R. The acquired pixel color (reference color) is output to the approximate color space region search unit 26.

  The second color acquisition unit 25 acquires, from the matching image M, the pixel color (matching color) of the same coordinates marked for the subject region in the matching marking image MM that is desired to be color-adjusted. In the example of FIG. 4C, the pixel color in the alpha mask area αA is acquired from the matching image M. The acquired pixel color (matching color) is output to the main color space region determination unit 27.

  FIG. 5 shows an example of the pixel distribution DR of the reference image R acquired by the first color acquisition unit 24 and the pixel distribution DM of the matching image M acquired by the second color acquisition unit 25 in the Lab color space. Show.

The main color space region determination unit 26 is smaller than at least the entire Lab color space in the pixel distribution DM of the matching image M on the Lab color space acquired by the second color acquisition unit 25, for example, (L ^* × a ^* × b ^* ) = a small color space region B having a size of 20 × 16 × 16 is arbitrarily set. As shown on the left side of FIG. 6, the main color space area determination unit 26 scans the entire Lab color space in the order of the small color space areas B1, B2, B3, B4... Using the small color space area B. Then, as shown at the tip of arrow A1 in FIG. 6, the small color space region Bm having a high pixel distribution density is searched (determined) as the main color space region.

なお、主要色空間領域は複数個あってもよい。 As a method for determining whether or not it is the main color space region, for example, there is a determination method using a threshold as shown in the following equation (1). That is, the small color space region that satisfies the condition of Expression (1) is determined as the main color space region of the matching image.

There may be a plurality of main color space regions.

  Returning to the description of FIG. As shown on the left side of FIG. 7, the approximate color space region search unit 27 determines the main color space region Bm determined in the pixel distribution DM of the matching image M on the Lab color space acquired by the second color acquisition unit 25. Thus, as shown at the tip of arrow A2 in FIG. 7, a peripheral area Bm + 1 centered on the main color space area Bm is searched.

  As a result of the search, the approximate color space region determination unit 27 determines a small color space region in which the maximum number of pixels are distributed in the search region (that is, the peripheral region Bm + 1 including the main color space region Bm) as a main part of the matching image M. The color space region Bn of the reference image R including the color corresponding to the color space region Bm is estimated, and the approximate color space region DR of the reference image R and the main color space region DM of the matching image M are associated. At the time of association, if there is no small space area having the number of pixels equal to or greater than the threshold, the association is not performed. This associating process is performed for all the color space regions extracted as the main colors of the matching image.

  As shown in FIG. 8, the difference value calculation unit 28 uses the average value μ1 of pixel colors belonging to the approximate color space region DR of the reference image R associated by the approximate color space region search unit 27 and the main color space of the matching image M. An average value μ2 of pixel colors belonging to the region DM is calculated.

The difference value calculation unit 28 calculates a difference value Lab vector of the calculated average value of the color distribution of each color space region according to the following equation (2). In Expression (2), μ _L1 , μ _a1 , and μ _b1 represent average values of the luminance component L ^* , the color component a ^* , and the color component b ^* of the pixel colors that belong to the approximate color space region DR, respectively, and μ _L2 , μ _a2 and μ _b2 represent average values of the luminance components L ^* , color components a ^* , and color components b ^* of the pixel colors belonging to the main color space region DM, respectively.

The color mapping unit 29 performs subtraction (pixel conversion) on the pixels of the matching image M using the difference value calculated by the difference value calculation unit 28 as the mapping intensity. The mapping intensity is converted from pixel values while being weighted by the color of the pixel values. More specifically, the same pixel value as the average value of the luminance component L ^* , color component a ^* , and color component b ^* of the pixel color belonging to the main color space region DM of the matching image M calculated by the difference value calculation unit 28. The mapping intensity becomes 1 and the mapping intensity is attenuated as the color space distance of each pixel value is away from the average value (the minimum mapping intensity is 0).

If the weighting intensity function that is the mapping intensity is f (x), it is represented by a Gaussian function as shown in the following equation (3). In Equation (3), σ is a parameter that controls the weight of the Gaussian function.

Figure 9 is a diagram showing a waveform of a weighting intensity function f (x) in the spatial distance (L ^*) from the luminance component of the primary color space region Bm during color mapping L ^* of the average value mu _L2. As shown in FIG. 9, the weighting intensity function f (x) has a normal distribution. That is, the pixel of the matching image M is closer to the luminance component ^{L *} of the average value _{mu L2,} mapping intensity becomes close to 1.0, as the distance from the average value _{mu L2,} mapping strength is close to 0.0 Become.

Then, the color mapping unit 29 converts (color maps) the pixels of the matching image M according to the following equation (4). In Expression (4), G _L (i, j), G _a (i, j), G _b (i, j) represent pixel values after color mapping, and I _L (i, j), I _a (I, j) and I _b (i, j) represent pixel values of the matching image M, and μ _L12 , μ _a12 , and μ _b12 represent the luminance component L ^* and the color component a ^* of the color distribution in each color space region ^. , Each represents a difference value of the average values of the color components b ^* , and m represents a parameter for adjusting the color mapping intensity.

Furthermore, in the equation _{(4), f L (x} ), f a (x), f b (x) represents a weighting intensity function, respectively, is expressed by the following equation (5).

  The RGB conversion unit 30 converts the matching image M on which the color mapping is performed in the color mapping unit 29 from the Lab color space to the RGB color space.

(Image color adjustment processing)
FIG. 10 is a flowchart for explaining image color adjustment processing executed by the image color adjustment apparatus 1.

  In step S <b> 1, the RGB image input unit 21 outputs an RGB image for color adjustment of the image via the storage unit 12, the media input / output unit 13, the communication control unit 14, or the peripheral device I / F (interface) unit 17. input. For example, a reference image R that is a color matching target shown in FIG. 3A and a matching image M that performs color matching shown in FIG. 3B are input.

  In step S <b> 2, the image creation unit 22 creates a marking image based on the marking instruction input by the user via the input unit 15 from the image input in the process of step S <b> 1. For example, a reference marking image RM shown in FIG. 4A and a matching marking image MM shown in FIG. 4B are created. Furthermore, an alpha mask image α shown in FIG. 4C is created based on the marking information of the matching marking image MM.

  In step S3, the Lab converter 23 converts the reference image R and the matching image M acquired in step S1 from the RGB space to the Lab color space.

  In step S4, the first color acquisition unit 24 uses the pixel color of the same coordinates marked on the subject area that is the target of color matching in the reference marking image RM (on the trajectory followed by the marking MK1 in FIG. 4A). Are obtained from the reference image R.

  In step S5, the second color acquisition unit 24 uses the pixel color of the same coordinates marked for the subject area to be color-matched in the matching marking image MM (pixels in the alpha mask area αA shown in FIG. 4C). Color) is acquired from the matching image M.

  In step S6, the main color space region determination unit 26 searches (determines) the small color space region Bm in the pixel distribution DM of the matching image M on the Lab color space acquired in the process of step S5 (FIG. 6). .

  In step S7, the approximate color space region search unit 27 searches the peripheral region Bm + 1 of the main color space region Bm determined in the pixel distribution DM of the matching image M on the Lab color space acquired in the process of step S5, The small color space region in which the maximum number of pixels is distributed is estimated as the color space region Bn of the reference image R including a color corresponding to the main color space region Bm of the matching image M, and the approximate color space region DR of the reference image R is estimated. And the main color space region DM of the matching image M are associated (FIG. 7).

  In step S <b> 8, the difference value calculation unit 28 calculates the pixel color belonging to the main color space region DM of the matching image M and the average value μ <b> 1 of the pixel colors belonging to the approximate color space region DR of the reference image R associated in the process of step S <b> 7. The average value μ2 is calculated.

  In step S9, the difference value calculation unit 28 calculates the difference value Lab vector of the average value of the color distribution of each color space region calculated in the process of step S8 according to the above equation (2).

  In step S <b> 10, the color mapping unit 29 selects a target pixel to be color mapped in the alpha mask area Aα of the matching image M. Specifically, if the value of each pixel of the alpha mask image is α (for example, 0 to 255 in the case of an 8-bit image) and the threshold is β, matching of the same coordinates as the pixel of the alpha mask image where α> β is satisfied. Color mapping is performed on the pixels of the image M, and color mapping is not performed on the pixels of the matching image M having the same coordinates as the pixels of the alpha mask image where α <β.

  In step S11, the color mapping unit 29 uses the difference value calculated in the process of step S9 as a mapping intensity with the weighting intensity function f (x) as shown in the above expression (3), according to the above expression (4). As shown, the target pixel selected in step S10 is color mapped (pixel conversion).

  In step S12, the control unit 11 selects all pixels in the alpha mask area Aα of the matching image M as target pixels, determines whether or not color mapping processing has been performed, and has not yet been selected as target pixels. If it is determined that there is, the process returns to step S10 and the above-described processing is repeatedly executed.

  In step S12, when the control unit 11 selects all the pixels in the alpha mask area Aα of the matching image M as target pixels and determines that the color mapping process has been performed, the control unit 11 proceeds to step S13. In step S <b> 13, the RGB conversion unit 30 converts the color-mapped matching image M from the Lab color space to the RGB color space.

  With the above processing, color adjustment can be easily performed.

  When color mapping is performed, when the approximate color space region DR of the plurality of reference images R is associated with the main color space region DM of the matching image M, the color mapping interferes if both are close color space regions. There is a fear. Therefore, when there are a plurality of main color space regions to be color mapped, for example, the main color space regions that may cause interference are compared, and priority is given to the color mapping of the main color space region with a large number of pixels included, Color maps obtained from other main color space regions are not applied.

  Here, with reference to FIG. 11 and FIG. 12, a specific example of mapping processing when color mapping does not interfere and mapping processing when color mapping interferes will be described.

  FIG. 11 is a diagram for explaining mapping processing when color mapping does not interfere.

As shown in FIG. 11, primary colors ^L * ^a * ^{b *} Average value of color distribution A spatial domain and color distribution C of ^L * ^a * ^{b *} average of approximate color space region of the reference image R1 of matching images M1 after the color mapping process by the difference value, further the color distribution B of the primary color space region of the matching image M2 ^{L * a} * ^b * color distribution D of the average value and the reference image R2 ^{L * a} * ^b * average of Perform color mapping using the difference value.

  FIG. 12 is a diagram for explaining color mapping processing when color mapping interferes.

As shown in FIG. 12, the number of pixels included in the color distribution A of the main color space region of the matching image M1 is 1000, and the number of pixels included in the color distribution B of the main color space region of the matching image M2 is 100. The color mapping based on the difference value between the L ^* a ^* b ^* average value of the color distribution B in the main color space region of the matching image M2 and the L ^* a ^* b ^* average value of the color distribution D of the reference image R2 with a small number of pixels Processing is excluded, and color mapping processing based on a difference value between the L ^* a ^* b ^* average value of the color distribution A in the main color space region of the matching image M1 and the L ^* a ^* b ^* average value of the color distribution C of the reference image R1 Only do.

The conditions of the color mapping process shown in FIGS. 11 and 12 are the average value of the color distribution A in the main color space region of the matching image M1 (L1, a1, b1), and the color distribution in the main color space region of the matching image M2. When the average value of B is (L2, a2, b2), the Euclidean distance d is expressed by the following equation (6).

  In the case of d ≧ 6σ, after the color mapping process by the difference value of the color distribution A in the main color space area, the color mapping process by the difference value of the color distribution B in the main color space area is further performed. On the other hand, in the case of d <6σ, the color mapping process using the difference value of the color distribution B in the main color space area with a small number of pixels is excluded, and the color mapping process using the difference value of the color distribution A in the main color space area with a large number of pixels is excluded. Only do.

[Effects of the embodiment of the present invention]
As described above, according to the present embodiment, the average value of the color distribution of the pixel colors marked for the subject area of the reference image that is the target of color adjustment and the marking for the subject area for color adjustment are performed. A weighting intensity function is determined based on the difference value of the average values of the color distributions of the pixel colors, and color mapping can be easily performed based on the weighting intensity function.

  The preferred embodiments of the image color adjusting device and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these naturally belong to the technical scope of the present invention. Understood.

DESCRIPTION OF SYMBOLS 1 ......... Image color adjustment apparatus 21 ......... Image input part 22 ......... Image creation part 23 ......... Lab conversion part 24 ......... First color acquisition part 25 ......... Second color acquisition part 26 ......... Main color space region determination unit 27 ......... Approximate color space region search unit 28 ......... Difference value calculation unit 29 ......... Color mapping unit

Claims (7)

An image color adjustment device for color-adjusting image data of the same subject with different shooting angles,
Input means for inputting reference image data to be a color adjustment target and matching image data to be color-adjusted;
Reference marking image data in which the subject area of the reference image data is marked; and image creation means for creating matching marking image data in which the subject area of the matching image data is marked;
First color acquisition means for acquiring a first pixel color of the subject area of the reference image based on the marking information of the reference marking image data;
Second color acquisition means for acquiring a second pixel color of a subject area of the matching image based on the marking information of the matching marking image data;
A main color space area determining means for determining a main color space area from the second pixel color acquired by the second color acquiring means;
Approximate color space for searching whether there is a region having a high distribution density of the first pixel color acquired by the first color acquisition means in a peripheral region of a color space region corresponding to the main color space region Region search means;
As a result of the search by the approximate color space area search means, when an approximate color space area exists in the reference image data, an average value of the second pixel colors in the main color space area and the approximate color space area Difference value calculating means for calculating a difference value from an average value of the first pixel colors;
Color mapping means for color-mapping the main color space area to the approximate color space area based on a calculation result by the difference value calculation means;
An image color adjusting device comprising: The image color adjustment apparatus according to claim 1, wherein the main color space area determining unit determines a small color space area having a high pixel density distribution of the second pixel color as a main color space area. The approximate color space area search means is a small space having a high pixel density distribution of the first pixel color in the same area as the main color space area determined by the main color space area determination means and its peripheral area. The image color adjustment apparatus according to claim 1, wherein an area is searched as the approximate color space area. The image color adjusting apparatus according to claim 1, wherein the color mapping unit attenuates the mapping intensity according to a distance in a color space from a color mapping center point. The image creating means creates a mask image from matching marking image data in which a subject area of the matching image data is marked,
The image color adjusting apparatus according to claim 1, wherein the color mapping unit performs color mapping only on a mask region in the mask image. There is an image color adjustment method performed by an image color adjustment device that performs color adjustment on image data of the same subject with different shooting angles,
An input step for inputting reference image data to be a color adjustment target and matching image data to be color-adjusted;
Reference marking image data in which the subject area of the reference image data is marked, and image creation step of creating matching marking image data in which the subject area of the matching image data is marked;
A first color acquisition step of acquiring a first pixel color of a subject area of the reference image based on the marking information of the reference marking image data;
A second color acquisition step of acquiring a second pixel color of a subject area of the matching image based on the marking information of the matching marking image data;
A main color space region determining step for determining a main color space region from the second pixel color acquired in the second color acquisition step;
Approximate color space for searching whether there is a region having a high distribution density of the first pixel color acquired in the first color acquisition step in a peripheral region of the color space region corresponding to the main color space region Region search step;
As a result of the search in the approximate color space region search step, when an approximate color space region exists in the reference image data, an average value of the second pixel colors in the main color space region and the approximate color space region A difference value calculating step of calculating a difference value from an average value of the first pixel colors;
A color mapping step for color-mapping the main color space region to the approximate color space region based on a calculation result obtained by the difference value calculating step;
An image color adjustment method comprising: A program for causing a computer to function as an image color adjustment device that performs color adjustment on image data of the same subject with different shooting angles,
The computer,
Input means for inputting reference image data to be a color adjustment target and matching image data to be color-adjusted;
Reference marking image data in which the subject area of the reference image data is marked; and image creation means for creating matching marking image data in which the subject area of the matching image data is marked;
First color acquisition means for acquiring a first pixel color of a subject area of a reference image based on marking information of the reference marking image data;
Second color acquisition means for acquiring a second pixel color of the subject area of the matching image based on the marking information of the matching marking image data;
A main color space area determining means for determining a main color space area from the second pixel color acquired by the second color acquiring means;
Approximate color space for searching whether there is a region having a high distribution density of the first pixel color acquired by the first color acquisition means in a peripheral region of a color space region corresponding to the main color space region Area search means,
As a result of the search by the approximate color space area search means, when an approximate color space area exists in the reference image data, an average value of the second pixel colors in the main color space area and the approximate color space area Difference value calculating means for calculating a difference value from an average value of the first pixel colors;
Color mapping means for color-mapping the main color space area to the approximate color space area based on a calculation result by the difference value calculation means;
Program to function as.

Images