JP4831020B2 - Image processing apparatus, image processing method, and image processing program - Google Patents

Description

The present invention relates to an image processing apparatus capable of correcting an image with an easy operation.

  With the popularization of digital cameras and the like, it has become popular to print images taken by individuals using a home printing device. In addition, printing (copying) an image stored on a print medium with a home printing apparatus is also widespread. In such a case, if the acquired image does not have a desired color or tone, it is desired to correct the image before printing.

  Here, for example, Patent Document 1 below discloses a printing apparatus capable of image adjustment. In this printing apparatus, it is necessary to input adjustment data in order to adjust the image quality of the acquired image.

JP 2007-89179 A

  In the printing apparatus as described above, it is necessary to input specific data in order to adjust the image, so knowledge about the image is required, and sensory color adjustment cannot be performed. Further, in the above document, since it is necessary to select or set adjustment data, it is not a simple operation. Furthermore, even if adjustment data is used, it is difficult to predict what image processing will be performed before image correction.

  Accordingly, in order to solve the above-described problems, the present invention provides an image processing apparatus that can predict what image correction is to be performed before image correction and can sensuously desired image correction. With the goal.

In order to achieve the above object, an invention according to claim 1 is directed to an image processing apparatus including a feature amount storage unit, an image acquisition unit, an image storage unit, a feature amount extraction unit, an image correction unit, and a display unit. The means is one or more types of first feature values extracted from one or more types of first images, is a first representative value relating to the hue of the first image, and is divided based on color information. Storing the first feature amount including the first representative value specified for each region , the image acquisition unit acquires a second image, the image storage unit stores a third image, The feature quantity extraction means is a second representative value that is a second representative value related to the hue of the second image based on the second image and includes the second representative value specified for each region. The image correction unit extracts the feature amount storage unit; A third feature quantity extracted from the stored first characteristic amount and the third image, a third representative values regarding hue of the third image, the third specified for each of the regions Based on the third feature value including the representative value , the third representative value is corrected to the first representative value specified for the same region, and values other than the third representative value are corrected. The third image is corrected by interpolation , the display means displays the third image that has been corrected, and the image correction means is configured to display one image according to a predetermined input by the user. The corrected third image is identified, and the second representative value is the same as the second representative value based on the first feature amount and the second feature amount used for image correction of the identified third image. Correction to the first representative value specified for the region For values other than the second representative value, by interpolation, characterized by an image correcting the second image. The third feature amount may be extracted from the third image by the feature amount extraction unit every time the third image is corrected, or is extracted from the third image in advance and stored in the feature amount storage unit. May be.

  According to a second aspect of the present invention, in the image processing apparatus according to the first aspect, the display means displays the third image that has been subjected to the image correction together with the third image.

The invention according to claim 3 is an image processing apparatus comprising a feature quantity storage means, an image acquisition means, a feature quantity extraction means, an image generation means, a display means, a feature quantity selection means, and an image correction means, wherein the feature quantity storage means An area that is one or more types of first feature values extracted from one or more types of first images, is a first representative value related to the hue of the first image, and is divided based on color information Storing the first feature value including the first representative value specified for each, the image acquiring means acquiring a second image, and the feature value extracting means based on the second image ; A second feature value that is a second representative value relating to the hue of the second image and that includes the second representative value specified for each region is extracted, and the image generation means includes the first feature value. based in, a third image including a plurality of color regions, before Each color area, to generate the third image of a single color that is determined by said first representative value included in the first feature amount, wherein the display unit displays the third image, the feature quantity The selecting means selects the first feature amount used for creating the third image selected by the user, and the image correcting means is based on the selected first feature amount and the second feature amount. The second representative value is corrected to the first representative value specified for the same region, and the second image is corrected by interpolating values other than the second representative value. It is characterized by doing.

  According to a fourth aspect of the present invention, in the image processing apparatus of the third aspect, a feature amount related to a hue is extracted from the first image, and the first image is divided into a plurality of regions based on the feature amount related to the hue. For each of the divided areas, a feature value related to other than the hue is extracted, and for each divided area, a representative value of the feature value related to other than the hue is extracted, and the first feature value is a representative value of the feature value related to the hue And a representative value of the feature amount related to other than the hue, the image generation means determines a display color based on the first feature amount, and displays an image having the same number of display colors as the number of divisions of the plurality of regions. It is characterized by generating.

  According to a fifth aspect of the present invention, in the image processing apparatus according to the fourth aspect, for each hue, a region of the hue includes a region that occupies the entire first image that is a basis of the feature amount. The ratio of the area of the display color constituting the third image is the same as the ratio of the entire first image.

  According to a sixth aspect of the present invention, in the image processing apparatus according to the fourth or fifth aspect, the feature amount related to other than the hue is a feature amount related to lightness and / or saturation.

  The invention according to claim 7 is the image processing apparatus according to claim 5 or 6, wherein the display color corresponding to an area in which the ratio of the area to the entire first image is equal to or less than a predetermined amount and the entire second image is occupied. A display color corresponding to an area whose area ratio is a predetermined amount or less is excluded from the display target.

  The invention according to claim 8 is the image processing apparatus according to any one of claims 1 to 7, further comprising correction data generating means for generating correction data based on the first feature quantity and the second feature quantity. Is characterized in that the second image is corrected based on the correction data.

  The invention according to claim 9 is the image processing apparatus according to any one of claims 1 to 8, further comprising correction data creating means, wherein the correction data creating means relates to the hue for each region obtained by dividing the first image. Extracting a representative value of a feature value and a feature value related to other than the hue, extracting a representative value of the feature value related to the hue and a feature value related to other than the hue for each region obtained by dividing the second image, Hue correction data is created based on the representative value of the feature quantity related to the hue of the first image and the representative value of the feature quantity related to the hue of the second image, and the image correction means relates to the hue of each pixel of the second image. A feature amount is corrected based on the hue correction data, and a feature amount related to other than the hue for each pixel of the second image is corrected based on a representative value for each region.

  A tenth aspect of the present invention is the image processing apparatus according to any one of the first to ninth aspects, further comprising a print control unit, wherein the print control unit performs a process for printing the image-corrected second image. It is characterized by.

  According to an eleventh aspect of the present invention, in the image processing apparatus according to any one of the fourth to tenth aspects, the feature value related to the hue is calculated based on an H value in the HSV space.

According to a twelfth aspect of the present invention, in the image processing method, the first feature amount stored in the feature amount storage means is a first representative value relating to the hue of the first image, and is divided based on the color information. The first feature value including the first representative value specified for each region and a third feature value extracted from the third image stored in the image storage means, the third image Based on the third feature value including the third representative value specified for each region, the third representative value is specified for the same region. A third image correcting step for correcting the third image by interpolating the values other than the third representative value, and an image acquiring step for acquiring the second image. based on the second image, the second image A second representative values for hue, display step of displaying the third image that are characteristic amount extraction step, before Symbol correction for extracting second feature amount including the second representative values specified for each of the regions In response to a predetermined input by the user, one image-corrected third image is specified, and based on the first feature value and the second feature value used for image correction of the specified third image. The second representative value is corrected to the first representative value specified for the same region, and values other than the second representative value are interpolated to interpolate the second image. It comprises a second image step to be corrected.

According to a thirteenth aspect of the present invention, in the image processing method, the first feature amount stored in the feature amount storage means is a first representative value relating to the hue of the first image, and is divided based on the color information. A third image including a plurality of color regions based on the first feature amount including the first representative value specified for each region to be processed, wherein each of the color regions includes the first feature amount. An image generating step for generating the third image indicating a single color determined by the first representative value included in the image, an image acquiring step for acquiring a second image, and the second image based on the second image. a second representative values for hue feature extraction step of extracting second feature amounts including the second representative value which is specified for each said area, the display step of displaying the pre-Symbol third image, the user Create selected third image Feature quantity selection step of selecting the first feature quantity used, based on the first feature amount and the second feature quantity said selected above for the second representative value is specified for the same said region It comprises an image correction step of correcting the second image by correcting to the first representative value and interpolating values other than the second representative value .

According to a fourteenth aspect of the present invention, in the image processing program, the first feature value stored in the feature value storage means in the computer is a first representative value relating to the hue of the first image, and is based on the color information. The first feature value including the first representative value specified for each region divided by the image and a third feature value extracted from the third image stored in the image storage means, Based on the third feature value that is the third representative value relating to the hue of the third image and includes the third representative value specified for each region, the third representative value is the same region. A third image correcting step for correcting the third image by correcting to the first representative value specified for the first, and interpolating values other than the third representative value, an image for acquiring the second image Acquisition step, the second image Based in a second representative values regarding hue of the second image feature extraction step of extracting second feature amounts including the second representative values specified for each of the regions, which is pre-Symbol corrected A display step for displaying the third image, and the first feature amount used for image correction of the specified third image by specifying one image-corrected third image in accordance with a predetermined input by the user And based on the second feature value, the second representative value is corrected to the first representative value specified for the same region, and values other than the second representative value are interpolated. Thus, a second image correction step for correcting the second image is executed.

According to a fifteenth aspect of the present invention, in the image processing program, the first feature amount stored in the feature amount storage means in the computer is a first representative value relating to the hue of the first image, and the color information includes A third image including a plurality of color areas based on the first feature value including the first representative value specified for each of the areas divided based on each of the color areas; image generating step of generating the third image of a single color that is determined by said first representative value included in the first feature amounts, image acquisition step of acquiring second image, based on the second image, the first a second representative values regarding hue of two images, the feature extraction step of extracting second feature amounts including the second representative value which is specified for each said area, the display step of displaying the pre-Symbol third image , Selected by user It has been a third image feature quantity selection step of selecting the first feature amount, which is used in, based on the first feature amount and the second feature quantity said selected for the second representative value, Correcting to the first representative value specified for the same region and interpolating values other than the second representative value to perform an image correction step of correcting the second image. Features.

  According to the first aspect of the invention, image correction is performed on the third image based on the stored first feature value and the third feature value extracted from the stored third image, and the result , The feature amount is selected by the selection from the user, and the image correction of the second image is performed using the selected feature amount and the feature amount of the second image. Thus, it is possible to predict what kind of image processing will be performed on the second image, and to perform desired image correction sensuously. Various parameters can be used to specify the hue.

  According to the second aspect of the present invention, the third image before and after correction is displayed at the same time, so it is possible to more clearly confirm what kind of image processing is performed.

  According to the third aspect of the invention, the third image is generated based on the stored feature amount, and the second image is corrected using the feature amount used for the selected image. The user can predict what kind of image processing will be performed on the second image in the previous stage of image correction, and can perform desired image correction sensuously. Further, since it is not necessary to store a display image in advance, the storage capacity can be reduced.

  According to the invention of claim 4, the display color is determined based on the feature amount related to the hue and the feature amount related to other than the hue, and the number of the display colors is the same as the number of the divided areas. It is possible to easily grasp what kind of image processing is performed.

  According to the invention of claim 5, since the ratio of the display color area and the ratio of the divided area of the model image are the same, it is possible to more easily understand what kind of image processing is performed. .

  According to the invention which concerns on Claim 6, the feature-value regarding brightness and / or saturation can be made into the feature-value regarding other than the said hue.

  According to the seventh aspect of the present invention, since the display color corresponding to the model image or the divided region with a small proportion of the input image is not displayed, the display color can be excluded from the color region to be corrected. .

  According to the invention which concerns on Claim 8, there can exist the effect mentioned above.

  According to the ninth aspect of the invention, since different image correction processing is performed separately for the feature amount related to hue and the feature amount related to other than hue, desired image correction processing can be easily performed.

  According to the invention which concerns on Claim 10, the feature-value regarding a hue is computable based on H value in HSV space.

  According to the eleventh aspect of the present invention, since the print control unit is further included, it is possible to print the second image whose image has been corrected.

  The inventions according to claims 12 to 15 can also achieve the effects described above.

[First embodiment of the present invention]
First, an example of the appearance of the image processing apparatus according to the present invention is shown in FIG. An example of the internal configuration of the image processing apparatus 1 is shown in FIG.

  The image processing apparatus 1 is an example of a multi-function printer or the like, and has a scanner 2 for reading image information from a photograph or the like on the upper part (in FIG. 1, the scanner is in a covered state). .) Image information read by the scanner is used as sample information for correcting the color and the like of image information read from the memory slot shown below. Details of the image correction process will be described later.

  The image processing apparatus 1 has a memory slot 3 that functions as an IC card reader for reading image information recorded in an external memory that is a recording medium such as an SD card (trademark) or a CF card (trademark). Here, as the external memory (storage medium), a known medium and format can be appropriately selected. Further, it may be configured to have a plurality of memory slots so as to be applied to a plurality of types of media. In addition, a communication function (for example, a LAN card, not shown) that can be connected to a network such as a LAN to which a PC storing image information is connected is added to the signal line to which the CPU, ROM, RAM, etc. shown in FIG. 2 are connected. Thus, instead of the external memory, desired image information may be read from a network to which the PC is connected. In that case, the image processing apparatus 1 has a communication function.

  The image processing apparatus 1 has an operation panel 4 for performing various operations. Various buttons and the like are arranged on the operation panel 4.

  The image processing apparatus 1 includes a printer 10 illustrated in FIG. The image information subjected to the image correction is printed by the printer 10. The printed paper is discharged from the discharge port 5, for example.

  The image processing apparatus 1 has display means 6. Various character information and images can be displayed. Further, a transparent touch panel may be provided on the front surface of the display unit 6 and a part or all of the functions of the operation panel 4 may be substituted. Moreover, you may comprise so that a touch panel and the operation panel 4 can be used together.

  The image processing apparatus 1 is entirely controlled by a processor (CPU 9). In addition, there are a RAM 7 for temporarily storing information and a ROM 8 for storing predetermined information. Moreover, you may have mass storage means, such as HDD, as needed.

  Each element mentioned above is mutually connected by the signal wire | line.

  Further, various functions (for example, FAX) can be added to the image processing apparatus 1. Further, an interface for connecting to a personal computer or the like and an interface for connecting to another printing apparatus may be provided.

  In addition, the said external appearance is only an example, and it cannot be overemphasized that this invention is not limited to the said external appearance. Moreover, in the above-mentioned external appearance, an apparatus in which all functions are integrated is shown, but some functions may be realized by an external apparatus. Furthermore, the internal configuration is merely an example, and it goes without saying that the present invention is not limited to the internal configuration.

  Next, with regard to basic processing using the image processing apparatus 1 according to the present invention, an outline of user operations and processing of the apparatus body will be described. FIG. 3 shows an outline of the processing. First, the user sets a memory in which an image to be corrected is stored in a memory slot of the image processing apparatus. As described above, as this memory, a known storage medium such as a memory card can be appropriately employed.

  When the memory is set in the memory slot 3 (1), the image processing apparatus recognizes the set memory and causes the user to select an image to be corrected from the images stored in the memory. (2). In addition, the process for selecting an image can employ | adopt suitably a well-known technique (For example, switching and displaying an image sequentially, etc.). Further, the display means 6 may be used.

  When an image to be corrected is determined (3), the image processing apparatus reads the image and writes it in, for example, a RAM (4). Hereinafter, the image may be referred to as an “original image”.

  Next, the image processing apparatus 1 creates and presents a corrected image (5). The correction image to be presented is a sample image or a patch image as will be described later.

  Thereafter, the user selects a desired correction image (6). At this time, the user operates the operation panel 4 or the touch panel.

  Thereafter, the image processing apparatus 1 performs image correction processing of the original image using the feature amount used to create the selected correction image and the feature amount of the selected image (7). Specific contents of the image correction process will be described later.

  If necessary, the corrected original image is printed.

  Next, basic processing in the image processing apparatus 1 will be described. FIG. 4 is a flowchart showing an outline of basic processing in the present embodiment.

First, in S11, the original image is read and written in the RAM 7, for example. Here, the format of the read image is not limited.
In S12, each pixel of the read original image is converted into an HSV parameter. The HSV parameter conversion process will be described later.

  In S13, a second feature value is extracted as a feature value of the original image based on the HSV parameter. Specific processing for extracting the second feature amount will be described later.

  In S14, a correction image is generated. Specific processing for generating the correction image will be described later.

  In S15, the correction image is displayed, the user is allowed to select a desired correction image, and a correction image serving as a model for image correction with respect to the original image is specified. The correction image presentation process will be described later.

  In S16, the first feature amount used to create the specified corrected image is specified. Details of the first feature amount will be described later.

  In S17, the original image is color-corrected based on the first feature value and the second feature value. Specific processing for correction will be described later.

  In S18, the corrected original image is printed. At this time, the HSV parameters are converted into other parameters (for example, RGB parameters) as necessary. The conversion process to RGB parameters will be described later.

  In the above-described processing, L * c * h * parameters may be extracted instead of HSV parameters. Further, the present invention can be realized even with known parameters such as RGB parameters. In the following, a case where HSV parameters are extracted will be described.

  Next, an example of processing for converting into HSV parameters in S12 of FIG. 4 will be described. When the original image is acquired as an RGB parameter, it can be converted into an HSV parameter by the following conversion formula. In addition, the conversion formula shown below is an example, and it cannot be overemphasized that you may convert with another conversion formula.

[RGB → HSV conversion formula]
max (a, b, c) represents the largest value among a, b, and c.
min (a, b, c) represents the smallest value among a, b, and c.
V = max (R ÷ 255, G ÷ 255, B ÷ 255)
When V is not 0
S = {V-min (R, G, B)} ÷ V
When V is 0
S = 0
When {V-min (R, G, B)} is not 0,
r = (V-R ÷ 255) ÷ (V-min (R, G, B)
g = (V-G ÷ 255) ÷ (V-min (R, G, B)
b = (V-B ÷ 255) ÷ (V-min (R, G, B)
When {V-min (R, G, B)} is 0,
r = 0
g = 0
b = 0
When V = R ÷ 255
H = 60 × (bg)
When V = G ÷ 255
H = 60 × (2 + rg)
When V = B ÷ 255
H = 60 × (4 + gr)
However, when H <0
H = H + 360

  Next, the process for extracting the second feature value in S13 of FIG. 4 will be described with reference to FIG. FIG. 5 is a flowchart of the second feature amount extraction process. In the following processing, the H value takes a value of −30 to less than 330. When the H value is not within the above range, by appropriately converting the H value (for example, “H value + 360 × n” or “H value−360 × n”, n is an integer), the value in the above range is taken. adjust.

In S21, the original image is divided into a plurality of regions. Here, the image is divided based on six commonly used hues. Specifically, based on the H value of each pixel,
-R region: -30 or more and less than 30-Y region: 30 or more and less than 90-G region: 90 or more and less than 150-C region: 150 or more and less than 210-B region: 210 or more and less than 270-M region: Divide into 270 or more and less than 330. That is, a process of classifying the constituent pixels of the model image into six classification items according to the classification standard corresponding to the hue value is performed. Here, the correspondence relationship between the region and the H value is an example and can be changed as appropriate.

In S22, “representative value (HSV value) of each region” and “ratio of each region in the original image” are calculated for each region divided in S21. Here, the representative value (HSV value) of each region is defined as follows.
・ Representative value of R region: iHr, iSr, iVr
・ Representative value of G region: iHg, iSg, iVg
・ Representative value of B area: iHb, iSb, iVb
-Typical value of C region: iHc, iSc, iVc
-Typical values in the M region: iHm, iSm, iVm
・ Representative value of Y area: iHy, iSy, iSy

  Here, the representative value can be an average value of each HSV value in each region. Moreover, an intermediate value can be used.

Next, the proportion of each area in the original image is defined as follows.
-Ratio of R area in original image: iRateR
-Ratio of the G area in the original image: iRateG
-Ratio of B area in original image: iRateB
-Ratio of the C area in the original image: iRateC
-Ratio of M area in original image: iRateM
The ratio of the Y area in the original image: iRateY

Here, the ratio is, for example, for the R region,
Although it can be defined by sRateR = (number of pixels in the R region in the original image) / (total number of pixels in the original image), it may be defined by another formula.

  Next, the correction image generated in S14 of FIG. 4 and specified in S15 will be described in detail. FIG. 6 shows an example of information stored in the internal memory of the image processing apparatus 1. As shown in FIG. 6, the internal memory stores a plurality of first feature amounts (feature amount A, feature amount B,...) And sample images. Here, the first feature amount is a feature amount extracted from a predetermined image. The internal memory does not store the predetermined image that is the basis of the first feature value, and stores only the first feature value, so that the storage capacity of the internal memory can be reduced. Each first feature amount may be of the same type as the second feature amount described above.

  One is read from a plurality of first feature values stored in the internal memory, and the sample image is color-corrected using the read first feature value and the third feature value extracted from the sample image. Here, the third feature amount may be stored in advance in the feature amount storage unit in the same manner as the first feature amount, or the third feature amount may be extracted every time the third image is corrected. According to the configuration in which the third feature amount is stored, it is not necessary to extract the third feature amount every time image correction is performed, and thus it is possible to reduce the processing load of the image processing apparatus. Further, according to the configuration in which the third feature value is not stored, the storage capacity can be reduced, and the storage capacity can be prevented from being compressed. The third feature amount may be the same type as the second feature amount described above.

Next, color correction of the sample image will be described. It is assumed that the following information is included as the read first feature amount.
-Typical values of R region: sHr, sSr, sVr
-Typical values in the G region: sHg, sSg, sVg
-Typical values of the B region: sHb, sSb, sVb
-Typical value of C region: sHc, sSc, sVc
-Typical values in the M region: sHm, sSm, sVm
-Typical values of the Y region: sHy, sSy, sSy
-Ratio occupied by R region: sRateR
・ Percentage occupied by G area: sRateG
-Ratio of area B: sRateB
・ Percentage occupied by C area: sRateC
・ Percentage occupied by M area: sRateM
・ Percentage occupied by Y area: sRateY

Further, the following information is included as the third feature amount.
・ Representative values of R region: tHr, tSr, tVr
-Typical values in the G region: tHg, tSg, tVg
-Typical values of the B region: tHb, tSb, tVb
-Representative values of C region: tHc, tSc, tVc
-Typical values in the M region: tHm, tSm, tVm
-Typical values of the Y region: tHy, tSy, tSy
-Ratio occupied by R region: tRateR
・ Percentage occupied by G area: tRateG
-Ratio of area B: tRateB
・ Percentage occupied by C area: tRateC
-Ratio occupied by M region: tRateM
・ Percentage occupied by Y area: tRateY

  First, the conversion process for the H value will be described. The representative value of the H value in the third feature value is plotted on the X axis, and the representative value of the H value in the first feature value is plotted on the Y axis, and the representative value of the H value for each region is plotted. Then, a hue correction table shown in FIG. 7 is created by linear interpolation between the plotted points, for example. The hue correction table shown in FIG. 7 is obtained by taking the H value in the third feature amount as “H” on the X axis and the H value in the first feature amount as “H ′” on the Y axis. Here, when H ′> 360, H ′ = H′-360.

  Then, the H value is corrected by applying the hue correction table to the H value of each pixel of the sample image. More specifically, the corrected H ′ can be defined by the following equation.

H ′ = (y2−y1) ÷ (x2−x1) × H− (y2−y1) ÷ (x2−x1) × x2 + y2
... (Formula 1)
Here, x1, x2, y1, and y2 are defined as follows.

When H <iHr,
(X1, y1) = (tHm-360, sHm-360)
(X2, y2) = (tHr, sHr)

When iHr ≦ H <iHy,
(X1, y1) = (tHr, sHr)
(X2, y2) = (tHy, sHy)

When iHy ≦ H <iHg,
(X1, y1) = (tHy, sHy)
(X2, y2) = (tHg, sHg)

When iHg ≦ H <iHc,
(X1, y1) = (tHg, sHg)
(X2, y2) = (tHc, sHc)

When iHc ≦ H <iHb,
(X1, y1) = (tHc, sHc)
(X2, y2) = (tHb, sHb)

When iHb ≦ H <iHm,
(X1, y1) = (tHb, sHb)
(X2, y2) = (tHm, sHm)

When iHm ≦ H,
(X1, y1) = (tHm, sHm)
(X2, y2) = (tHr + 360, sHr + 360)

Next, correction in the S value and V value of each pixel of the sample image will be described. The S value and the Y value are converted for each area divided by the H value. For example, for the R region:
When S ≦ tSr,
S ′ = S × (sSr ÷ tSr) (Formula 2)
When S> tSr,
S ′ = 1 + (S−1) × {(1−sSr) ÷ (1−tSr)} (Formula 3)
When V ≦ tVr,
V ′ = V × (sVr ÷ tVr) (Formula 4)
When V> tVr,
V ′ = 1 + (V−1) × {(1−sVr) ÷ (1−tVr)} (Formula 5)
It can be calculated by the following formula. Further, other areas can be similarly calculated. In the following, the conversion table defined by the S value conversion formula may be referred to as a saturation correction table, and the conversion table defined by the V value conversion formula may be referred to as a brightness correction table. .

  By performing the above-described processing in the order of the feature amount A and the feature amount B and presenting the sample image that has been subjected to image correction, a corrected image is presented. At this time, as shown in FIG. 8, the pre-correction image and the post-correction image may be displayed simultaneously. Alternatively, a plurality of corrected sample images may be displayed simultaneously and selected by the user.

  Through the above-described processing, the correction image is specified based on the user's selection.

  In the example shown in FIG. 6, the number of sample images is one, but a plurality of sample images may be stored.

  Next, the color correction process of the original image in S16 of FIG. 4 will be described. The original image is corrected using the first feature amount specified in S15 and the second feature amount of the original image. The correction method is the same as the correction method for the sample image described above.

  Next, a conversion formula for converting into a format (for example, RGB value) suitable for the printer 10 in S17 of FIG. 4 will be described. In addition, the conversion formula shown below is an example, and it cannot be overemphasized that you may convert with another conversion formula.

[HSV⇒RGB]
(In, fl, m, and n shown below are parameters used in the process of calculating RGB from HSV)
Let in be the integer part of (H ÷ 60) and fl be the decimal part of (H ÷ 60).
If in is an even number
fl = 1-fl
m = V × (1-S)
n = V × (1-S × fl)
When in is 0
R = V × 255
G = n × 255
B = m × 255
When in is 1
R = n × 255
G = V × 255
B = m × 255
When in is 2
R = m × 255
G = V × 255
B = n × 255
When in is 3
R = m × 255
G = n × 255
B = V × 255
When in is 4
R = n × 255
G = m × 255
B = V × 255
When in is 5
R = V × 255
G = m × 255
B = n × 255

  According to the first embodiment of the present invention described above, the sample image is corrected based on the first feature value stored in advance and the third feature value extracted from the sample image with respect to the sample image stored in advance. The image correction is performed using the first feature amount corresponding to the sample image selected by the user. Further, by performing the above-described image correction processing, the color of the original image can be corrected to the color of the model image for each area divided based on the H value. Further, since the image that is the basis of the first feature value is not stored, but only the first feature value is stored, the storage capacity can be reduced.

[Second Embodiment of Image Correction Processing]
In the second embodiment of the image correction process described below, for each divided area, a part of the image correction process can be stopped and the amount of change can be controlled based on the size of the area. . Thereby, the user can reflect only a part of the hue of the model image in the hue of the original image.

  FIG. 9 shows a flowchart of basic processing of this embodiment. The basic processing flow of this embodiment is the same as that in FIG. 4, but a representative value resetting process (S37) is added after the second feature amount extraction process. Hereinafter, the representative value resetting process will be described with reference to the drawings.

  FIG. 10 is a flowchart of the representative value resetting process in the present embodiment. In S41, it is determined whether or not the divided area is a correction target. In this process, it is determined whether or not the area satisfies a predetermined condition.

  When it is determined that it is a correction target (S41: YES), the process proceeds to S43. If it is determined that it is not a correction target (S41: NO), the process proceeds to S42. In S42, the representative value is reset, and then the process proceeds to S43. A method of resetting the representative value will be described later.

  In S43, it is determined whether or not all the regions (six regions when divided into 6) are determined as correction targets. If an unidentified area remains (S43: NO), the process returns to S41 and the process is repeated. When the determination for all areas is completed (S43: YES), the representative value resetting process is terminated.

[Method using threshold Thre]
As the predetermined condition described above, the magnitude relationship between the size of the divided area and the threshold value Thre can be used. When the ratio of the original image or the model image is smaller than the threshold value Thre, the representative value of the original image and the model image related to the region is changed to the same value, and the above-described changed representative value is used for each pixel described above. Perform the conversion process. Hereinafter, this process will be described. The representative value can be reset as follows.

When sRateR <Thre or iRateR <Thre,
sHr = 0, sSr = 0.5, sVr = 0.5,
iHr = 0, iSr = 0.5, iVr = 0.5

When sRateG <Thre or iRateG <Thre,
sHg = 120, sSg = 0.5, sVg = 0.5,
iHg = 120, iSg = 0.5, iVg = 0.5

When sRateB <Thre or iRateB <Thre,
sHb = 240, sSb = 0.5, sVb = 0.5,
iHb = 240, iSb = 0.5, iVb = 0.5

When sRateC <Thre or iRateC <Thre,
sHc = 180, sSc = 0.5, sVc = 0.5,
iHc = 180, iSc = 0.5, iVc = 0.5

When sRateM <Thre or iRateM <Thre,
sHm = 300, sSm = 0.5, sVm = 0.5,
iHm = 300, iSm = 0.5, iVm = 0.5

When sRateY <Thre or iRateY <Thre,
sHy = 60, sSy = 0.5, sVy = 0.5,
iHy = 60, iSy = 0.5, iVy = 0.5

  In the above-described embodiment, 0.5, which is an intermediate value between possible values (0 to 1), is adopted for the S value and the V value. Moreover, the intermediate value of each area | region was employ | adopted about H value. However, the representative values described above are examples, and the present invention is not limited to the above numerical values.

  By using this value and using the conversion expressions (Expression 2) to (Expression 5) described above for conversion for each pixel, the values are not changed in the S value and the V value. That is, for example, with respect to the R region, when S ≦ iSr, as described above (Formula 2),

    S ′ = S × (sSr ÷ iSr)

In this formula, sSr = 0.5 and iSr = 0.5, so the above formula is

S ′ = S × (0.5 ÷ 0.5) = S (Expression 6)
It becomes. Similarly, when S> iSr, S ′ = S. Similarly, the V value and other regions are not converted.

  Further, in the H value, the point plotted in FIG. 7 is changed to the representative value, so that the conversion amount in that region can be reduced. That is, even when the above-described changing formula (Formula 1) is used, the conversion amount is reduced by changing the representative value.

  Next, a method for determining the threshold value Thre will be described. This value can be determined based on sensory evaluation. In sensory evaluation, it was confirmed that if the area occupied about 6% or more, the area was easily perceived. Therefore, 6% can be adopted as the threshold Thre. However, the present invention is not limited to the threshold Thre of 6%.

  Further, the threshold Thre may be determined so as to extract a region having a relatively large area relative to other regions. For example, if the number of areas to be divided is 6, 1/6, which is the reciprocal thereof, can be set as the threshold value Thre.

  The number of divided areas “6” given as an example of the present invention is the number of vertices excluding white and black, which are achromatic colors, from the RGB space (number of vertices 8) that is one of the color gamuts expressing colors. It is the same as the number “6”. In order for a person to identify a color, six is sufficient as the number of color regions, and if it is less than six, the user may feel that the image has not been converted as in the model image. If the data is divided more finely than 6, the conversion accuracy becomes higher. However, there is a high possibility that the person cannot be identified, and the amount of calculation increases as the number of divisions increases. In the case of using a printer, the time until obtaining an image to be corrected as a printing result is delayed, and there is a high possibility that user dissatisfaction will increase.

  In the example described above, the threshold value is the same in all the regions, but the threshold value Thre may be changed for each region.

[Method using information of maximum area]
In the above-described method, the threshold Thre is set, and the representative value is changed based on the threshold Thre, that is, the image correction processing is stopped and the conversion amount is reduced. Here, an image correction process using information on the maximum area in the image in order to reflect only a specific color of the model image in the original image will be described below.

  In this case, in S41 of FIG. 10, whether or not the area is the largest in both the original image and the model image can be set as a predetermined condition. In this case, the representative value is reset by the following formula. Here, the ratio of the divided area of the model image that has the largest ratio to the model image is iMaxRate. Further, the ratio of the divided area of the original image that has the largest ratio to the original image is sMaxRate.

When sRateR ≠ iMaxRate or iRateR ≠ sMaxRate,
sHr = 0, sSr = 0.5, sVr = 0.5,
iHr = 0, iSr = 0.5, iVr = 0.5

When sRateG ≠ iMaxRate or iRateG ≠ sMaxRate,
sHg = 120, sSg = 0.5, sVg = 0.5,
iHg = 120, iSg = 0.5, iVg = 0.5

When sRateB ≠ iMaxRate or iRateB ≠ sMaxRate,
sHb = 240, sSb = 0.5, sVb = 0.5,
iHb = 240, iSb = 0.5, iVb = 0.5

When sRateC ≠ iMaxRate or iRateC ≠ sMaxRate,
sHc = 180, sSc = 0.5, sVc = 0.5,
iHc = 180, iSc = 0.5, iVc = 0.5

When sRateM ≠ iMaxRate or iRateM ≠ sMaxRate,
sHm = 300, sSm = 0.5, sVm = 0.5,
iHm = 300, iSm = 0.5, iVm = 0.5

When sRateY ≠ iMaxRate or iRateY ≠ sMaxRate,
sHy = 60, sSy = 0.5, sVy = 0.5,
iHy = 60, iSy = 0.5, iVy = 0.5

  As a result, since only the region having the largest area in both the original image and the model image is to be converted, the conversion is not performed for the S value and the V value that are not the conversion target, and the H value is converted. The amount can be reduced.

  Here, when only the region B is to be converted, a hue correction table as shown in FIG. 11 is created. In this hue correction table, the H value representative value (iHc = 180, sHc = 180) in the C region adjacent to the B region in the color space and the H value representative value (iHb, sHb) in the B region are linear. In addition, the representative value of the H value (iHm = 300, sHm = 300) in the M region adjacent to the B region in the color space and the representative value of the H value in the B region (iHb, sHb) are connected by a straight line. It will be.

  Therefore, the C region where the H value is 180 <H ≦ 210 and the M region where the H value is 270 <H ≦ 300 are also converted. This conversion amount becomes larger as the value is closer to the B region.

  As described above, in the second embodiment of the image correction process, a conversion target region can be selected, and even in a region that is not a conversion target, H values adjacent in the color space are partially converted. Therefore, it is possible to prevent a pseudo contour (tone jump) from being generated between the conversion target area and the non-conversion area.

[Third Embodiment of Image Correction Processing]
In the second embodiment of the image correction process, although the conversion amount can be reduced, the conversion amount of the H value of the region not to be converted cannot be set to zero. This is because, as shown in FIG. 11, linear interpolation is performed with the representative value of the region not to be converted, and therefore, it is affected by the representative value of the other region.

  Therefore, a hue correction table as shown in FIG. 12 can be employed. FIG. 12 is a hue correction table in the case where only the B region is to be converted. In this figure, the number of areas to be converted is one, but a plurality of areas may be targeted for correction.

  In FIG. 12, since the H values other than the B area are H ′ = H, image correction is not performed. The H ′ value in the B region can be obtained by the following equation, where the minimum value in the B region is Hmin and the maximum value in the B region is Hmax.

When H <iH,
H ′ = Hmin + (sHb−Hmin) × (H−Hmin) ÷ (iHb−Hmin)

When H> iH,
H ′ = sHb + (Hmax−sHb) × (H−iHb) ÷ (Hmax−iHb)

  By using this equation, only the region to be converted can be converted.

  As described above, in the third embodiment of the image correction process, since only the H value to be converted can be converted, the effect of image correction can be increased.

[Fourth Embodiment of Image Correction Processing]
In the second embodiment of the image correction process, since a correction curve (conversion formula) is independently used for each region with respect to the S value and the V value, a pseudo contour (tone jump) may be generated. . That is, as shown in FIG. 13, each region has a table indicating the relationship between S and S ′, and no consideration is given to the nature of the table in the adjacent region.

  In the present embodiment, as shown in FIG. 14, gradation jumps can be prevented by smoothing the correction curve in each color region.

Specific processing of this embodiment will be described below. The image correction process for a part of the area B will be described with reference to FIGS. 15 and 16, but the contents of the process are basically the same for the other areas.
The corrected S value (Sb ″) in this embodiment is
-H value (H) of the conversion target area,
-H value representative value (Hbmid) of the area to be converted,
A representative value (Hcmid) of the H value in the adjacent region (in this case, the C region) closer to the hue coordinate position of the H value of the pixel to be converted;
-S value (corresponding to Sb ', Hbmid) of the conversion target area converted by the conversion formula corresponding to the above formula (2) (that is, calculated using the saturation correction table of the B area),
-S value of the adjacent area (which corresponds to Sc ', Hcid) converted by the conversion formula corresponding to the above formula (3) (that is, calculated using the saturation correction table of the C area),
Can be obtained by the following equation.

Sb ″ = {(H−Hcmid) × Sb ′ + (Hbmid−H) × Sc ′} ÷
{(Hbmid−Hcmid)} (Expression 7)

Further, the corrected V value (Vb ″) in the present embodiment is
-H value (H) of the conversion target area,
-H value representative value (Hbmid) of the area to be converted,
A representative value (Hcmid) of the H value in the adjacent region (in this case, the C region) closer to the hue coordinate position of the H value of the pixel to be converted;
-V value (corresponding to Vb ', Hbmid) of the conversion target area converted by the conversion formula corresponding to the above formula (4) (that is, calculated using the brightness correction table of the B area),
-S value of the adjacent area (that corresponds to Vc ', Hcid) converted by the conversion formula corresponding to the above formula (5) (that is, calculated using the brightness correction table of the C area),
Can be obtained by the following equation.

Vb ″ = {(H−Hcmid) × Vb ′ + (Hbmid−H) × Vc ′} ÷
{(Hbmid−Hcmid)} (Equation 8)

The above-described processing is performed on part of the B region (H value range: 210 <H ≦ 240) and part of the C region (H value range 180 <H ≦ 210) shown in FIG. Thus, the saturation value (S ″) and the lightness value (V ″) of the output are calculated by weighting calculation according to the hue value (H) of the input.
Thus, the correction effect between the hues can be smoothed.

[Second Embodiment of Correction Image Creation]
In the first embodiment of the present invention described above, a correction image is created using the stored sample image. In the second embodiment for creating a corrected image shown below, the sample image is presented so that the user can intuitively understand the content of the image correction indicated by the feature amount without using the sample image. The basic processing flow is the same as that in FIG. 4, but the correction image specifying processing in S14 is different, and this point will be described in detail.

  In the present embodiment, the internal memory stores only a plurality of first feature amounts as shown in FIG. That is, the sample image is not stored.

  Next, a patch image generation method will be described. As described above, since the first feature amount includes representative values of the H value, S value, and V value in each color region, this information is used. A patch image having six regions as shown in FIG. 19 is generated. Each of the six areas is a single color determined by the representative values of the H value, S value, and V value included in the first feature amount. By presenting this patch image, the user can grasp what kind of image correction is performed. Here, in a case where image correction is not performed for an area in which the proportion of the area in the image is smaller than a predetermined amount, a color area that is not a target for image correction may not be displayed as shown in FIG.

  In the example shown in FIG. 20, the Y region is not corrected. Further, the arrangement of the six color regions is merely an example, and other arrangements may be used. According to the present embodiment, a patch image can be generated using only the feature amount, and the user can grasp an image for image correction.

  Further, in the generation of the patch image, the display ratio of the display color may be the ratio of the area that the first feature amount has. FIG. 21 shows an example of a patch image that reflects the proportion of the area of the first feature amount. In FIG. 21, it can be intuitively understood that the feature amount is obtained from a sample image having a large B area and a narrow Y area.

  Further, instead of a pie chart, a bar-shaped one may be used as shown in FIG.

  In presenting the correction image using the above-described patch image, the user can intuitively grasp the color distribution of the model whose image is corrected.

  Further, according to the image correction processing of the present invention, for example, when it is desired to convert the sky blue to the vivid sea blue with respect to the original image in which the building and the sky are captured as the original image, You can correct the blue color of the original image to the bright blue of the ocean by reading the photo with the scanner.

  Also, if you want to brighten the skin color in an image showing a human face, you can correct the skin color of the original image to a light skin color by reading a picture of the palm that has moved to a bright skin color with a scanner. .

  Since the user does not need to input parameters or the like, he / she does not need any specialized knowledge and can perform desired image correction only by reading an image serving as a model for image correction. Furthermore, since it is possible to automatically select a region to be subjected to image correction, it is possible to stop or reduce correction of regions that are difficult to perceive, and to correct only regions that are easily perceived.

  In addition, this invention is not limited to the said embodiment, Of course, various improvement and deformation | transformation are possible within the range which does not deviate from the summary of this invention. For example, instead of reading a model image from a scanner, the image can be read as a model image from a storage medium. Further, instead of reading the original image from the storage medium, the original image can be read from the scanner. For example, a multifunction machine equipped with a scanner and a printer is described as an embodiment as an image processing apparatus. However, the present invention is not limited to this. For example, an information processing apparatus such as a personal computer performs image correction, and the information processing apparatus. The printer may be configured to perform printing processing.

  Further, the above-described flowchart is merely an example, and the process may be realized by another flowchart as long as it can obtain a result equivalent to the above-described process.

  The present invention can also be realized as an image processing method for executing the above-described processing. Further, the present invention can be realized as a program for causing the computer to execute the image processing method and a recording medium on which the program is recorded.

  Furthermore, not only can the corrected original image be printed, but it can also be stored in a storage medium or transmitted to another device.

It is the figure which showed the external appearance of the image processing apparatus. It is the figure which showed the internal structure of the image processing apparatus. It is the figure which showed the user's operation | movement and the flow of a process of an image processing apparatus. It is a flowchart of the basic processing in 1st Embodiment. It is a flowchart of the 2nd feature-value extraction process. It is the figure which showed the 1st feature-value and sample image which are memorize | stored in an internal memory. It is the figure which showed the hue correction table. It is the figure which showed the example of a display of the sample image before correction | amendment and after correction | amendment. It is a flowchart of the basic process in another embodiment of this invention. It is a flowchart of a representative value reset process. It is the figure which showed the hue correction table. It is the figure which showed the hue correction table. It is the figure which showed the saturation correction table. It is the figure which showed the change of the curve of saturation correction | amendment. It is the figure which showed the saturation correction table in B area | region and C area | region. It is the figure which showed the corrected S value in B area | region and C area | region. It is the figure which showed that a part of B area | region and C area | region became correction object. It is the figure which showed the 1st feature-value memorize | stored in internal memory. It is the figure which showed an example of the patch image. It is the figure which showed an example of the patch image. It is the figure which showed an example of the patch image. It is the figure which showed an example of the patch image.

DESCRIPTION OF SYMBOLS 1 Image processing apparatus 2 Scanner 3 Memory slot 4 Operation panel 5 Ejection port 6 Display means 10 Printer

Claims (15)

In an image processing apparatus comprising feature amount storage means, image acquisition means, image storage means, feature amount extraction means, image correction means, and display means,
The feature amount storage means is one or more types of first feature amounts extracted from one or more types of first images, is a first representative value relating to the hue of the first image, and includes color information. Storing the first feature amount including the first representative value specified for each region divided based on
The image acquisition means acquires a second image,
The image storage means stores a third image,
The feature quantity extraction means is a second representative value that is a second representative value related to the hue of the second image based on the second image and includes the second representative value specified for each region. Extract and
The image correction means is a third feature value extracted from the first feature quantity and the third image stored in the feature quantity storage means, and a third representative value relating to a hue of the third image. Yes, based on the third feature value including the third representative value specified for each region , the third representative value is corrected to the first representative value specified for the same region. For the values other than the third representative value, the third image is corrected by interpolation ,
The display means displays the third image after the image correction,
The image correction means identifies a third image that has been subjected to image correction in response to a predetermined input by a user, and the first feature amount used for image correction of the identified third image and the first image Based on two feature quantities, the second representative value is corrected to the first representative value specified for the same region, and values other than the second representative value are interpolated, thereby Correcting the second image,
An image processing apparatus.   The image processing apparatus according to claim 1, wherein the display unit displays the third image after the image correction together with the third image. In an image processing apparatus including a feature amount storage unit, an image acquisition unit, a feature amount extraction unit, an image generation unit, a display unit, a feature amount selection unit, and an image correction unit.
The feature amount storage means is one or more types of first feature amounts extracted from one or more types of first images, is a first representative value relating to the hue of the first image, and includes color information. Storing the first feature amount including the first representative value specified for each region divided based on
The image acquisition means acquires a second image,
The feature quantity extraction means is a second representative value that is a second representative value related to the hue of the second image based on the second image and includes the second representative value specified for each region. Extract and
The image generation means is a third image including a plurality of color regions based on the first feature amount, and each of the color regions is based on the first representative value included in the first feature amount. Generating the third image showing a single color to be determined ;
The display means displays the third image;
The feature amount selecting means selects the first feature amount used for creating the third image selected by the user,
The image correcting unit corrects the second representative value to the first representative value specified for the same region based on the selected first feature value and the second feature value, For values other than the second representative value, the second image is corrected by interpolation .
An image processing apparatus. A feature quantity related to hue is extracted from the first image,
Dividing the first image into a plurality of regions based on a feature amount relating to the hue;
For each of the divided areas, feature values related to other than hue are extracted,
For each of the divided areas, a representative value of a feature value related to other than hue is extracted,
The first feature amount is a representative value of a feature amount related to the hue and a representative value of a feature amount related to other than the hue,
The image generation means determines a display color based on the first feature amount, and generates an image having the same number of display colors as the number of divisions of the plurality of regions.
The image processing apparatus according to claim 3. The feature amount related to the hue includes, for each hue, the ratio of the region in the entire first image in which the region of the hue is the basis of the feature amount,
The ratio of the display color area constituting the third image is the same as the ratio of the entire first image.
The image processing apparatus according to claim 4. The feature amount related to other than the hue is a feature amount related to lightness and / or saturation.
The image processing apparatus according to claim 4, wherein The display color corresponding to the area where the ratio of the area occupying the entire first image is equal to or less than the predetermined amount, and the display color corresponding to the area where the ratio of the area occupying the entire second image is equal to or less than the predetermined amount Exclude from
The image processing apparatus according to claim 5, wherein the image processing apparatus is an image processing apparatus. Correction data creating means for creating correction data based on the first feature quantity and the second feature quantity;
The image correcting means corrects the second image based on the correction data;
The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. Correction data creating means,
The correction data creating means includes
For each region obtained by dividing the first image, extract a representative value of the feature value related to the hue and a feature value related to other than the hue,
For each region obtained by dividing the second image, extract a representative value of the feature value related to the hue and a feature value related to other than the hue,
Creating hue correction data based on the representative value of the feature quantity related to the hue of the first image and the representative value of the feature quantity related to the hue of the second image;
The image correcting means includes
Correcting a feature amount related to a hue for each pixel of the second image based on the hue correction data;
Correcting a feature amount related to other than the hue for each pixel of the second image based on a representative value for each region;
The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. A printing control unit;
The print control means performs a process for printing the second image after the image correction;
The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. The feature amount related to the hue is calculated based on the H value in the HSV space.
The image processing apparatus according to claim 4, wherein the image processing apparatus is an image processing apparatus. The first feature value stored in the feature value storage means, which is a first representative value relating to the hue of the first image, and is specified for each region divided based on the color information Including the first feature amount and the third feature amount extracted from the third image stored in the image storage means, and a third representative value relating to the hue of the third image, and the region Based on the third feature value including the third representative value specified for each, the third representative value is corrected to the first representative value specified for the same region, For values other than the three representative values, a third image correction step for correcting the third image by interpolation;
An image acquisition step of acquiring a second image;
A feature quantity extraction step for extracting a second feature quantity that is a second representative value related to the hue of the second image and includes the second representative value specified for each region based on the second image ;
Display step of displaying the third image that is pre-Symbol corrected,
In response to a predetermined input by the user, one image-corrected third image is specified, and based on the first feature value and the second feature value used for image correction of the specified third image. The second representative value is corrected to the first representative value specified for the same region, and the second image is corrected by interpolating values other than the second representative value. A second image step,
An image processing method comprising: The first feature value stored in the feature value storage means, which is a first representative value related to the hue of the first image, and is specified for each region to be divided based on color information A third image including a plurality of color regions based on the first feature amount including a value, wherein each of the color regions is determined by the first representative value included in the first feature amount. An image generating step for generating the third image showing a single color;
An image acquisition step of acquiring a second image;
A feature quantity extraction step for extracting a second feature quantity that is a second representative value related to the hue of the second image and includes the second representative value specified for each region based on the second image ;
Display step of displaying the pre-Symbol third image,
A feature amount selection step of selecting the first feature amount used to create the third image selected by the user;
Based on the selected first feature value and the second feature value, the second representative value is corrected to the first representative value specified for the same region, and other than the second representative value. An image correction step for correcting the second image by interpolation ,
An image processing method comprising: On the computer,
The first feature value stored in the feature value storage means, which is a first representative value relating to the hue of the first image, and is specified for each region divided based on the color information Including the first feature amount and the third feature amount extracted from the third image stored in the image storage means, and a third representative value relating to the hue of the third image, and the region Based on the third feature value including the third representative value specified for each, the third representative value is corrected to the first representative value specified for the same region, For values other than the three representative values, a third image correction step for correcting the third image by interpolation;
An image acquisition step of acquiring a second image;
A feature quantity extraction step for extracting a second feature quantity that is a second representative value related to the hue of the second image and includes the second representative value specified for each region based on the second image ;
Display step of displaying the third image that is pre-Symbol corrected,
In response to a predetermined input by the user, one image-corrected third image is specified, and based on the first feature value and the second feature value used for image correction of the specified third image. The second representative value is corrected to the first representative value specified for the same region, and the second image is corrected by interpolating values other than the second representative value. A second image correction step,
An image processing program for executing On the computer,
The first feature value stored in the feature value storage means, which is a first representative value related to the hue of the first image, and is specified for each region to be divided based on color information A third image including a plurality of color regions based on the first feature amount including a value, wherein each of the color regions is determined by the first representative value included in the first feature amount. An image generating step for generating the third image showing a single color;
An image acquisition step of acquiring a second image;
A feature quantity extraction step for extracting a second feature quantity that is a second representative value related to the hue of the second image and includes the second representative value specified for each region based on the second image ;
Display step of displaying the pre-Symbol third image,
A feature amount selection step of selecting the first feature amount used to create the third image selected by the user;
Based on the selected first feature value and the second feature value, the second representative value is corrected to the first representative value specified for the same region, and other than the second representative value. An image correction step for correcting the second image by interpolation ,
An image processing program for executing