JP4069649B2 - Image processing apparatus, image processing method, and image processing program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing apparatus, an image processing method, and an image processing program for performing image correction processing with different contents on image data to be processed depending on the image type.
[0002]
[Prior art]
In recent years, digital image data input to a printer has been diversified along with improvement in performance of a computer environment, application software, etc., so that image data input to a printer differs depending on the image type. It is necessary to output the content after performing image correction processing. For example, for image data representing a natural image such as a photograph, image correction processing such as gradation correction, contrast correction, and color balance correction is performed in order to obtain a preferable image quality, while a computer generated CG (Computer Graphics) For image data representing graphic images such as images, an extra image correction process is not performed in order to correctly reflect the creation intention.
[0003]
In order to realize such image correction processing according to the image type, it is necessary to determine the image type of the image data to be processed. Conventionally, the following methods have been proposed as a method for determining the image type. For example, in Japanese Patent Laid-Open No. 10-200758, attention is paid to the fact that a graphic image uses fewer colors than a natural image, and by detecting the number of used colors of image data to be processed, the image data becomes natural. Discriminating whether an image is a graphic image or a graphic image is disclosed. Further, for example, in Japanese Patent Laid-Open No. 2000-32287, attention is paid to the fact that when the distribution of the number of used colors is made into a histogram, there is a bias or gap in the distribution in the case of a graphic image. It is disclosed that a number is detected and its distribution is made into a histogram to determine whether the image data represents a natural image or a graphic image. Also, for example, in Japanese Patent Application Laid-Open No. 8-204954, attention is paid to the fact that the difference between adjacent pixels is the same for each color in the case of a graphic image, and the difference between adjacent pixels in the image data to be processed is all. It is disclosed that it is determined whether or not the image data represents a natural image or a graphic image by determining whether or not the colors match.
[0004]
[Problems to be solved by the invention]
However, conventionally, when image correction processing according to the image type is realized, it is binaryly determined whether the image data to be processed represents a natural image or a graphic image. Since whether or not to perform the image correction process is switched according to the determination result, there is a possibility that the following problem may occur.
[0005]
Recently, the high performance of computer environment and application software is particularly remarkable, so the number of colors used and the number of gradations also increase in graphic images, making it easy to form complex graphics and coloring. This makes it possible to realize expressions close to natural images. Therefore, in the determination of the binary image type as described above, an appropriate determination result is not always obtained, and an image having characteristics near the determination threshold is corrected with a slight difference, Inconveniences such as not being done. This is because the number of colors used and the number of gradations in graphic images have increased, so that discrimination based on the number of colors used and histogram distribution shape, etc., cannot be sufficiently differentiated between natural images and graphic images. Further, in binary discrimination, there is a possibility that the correction result may vary greatly even if there is a slight difference in features.
[0006]
Therefore, the present invention does not simply determine the image type in a binary manner, but allows the amount of correction for image data to be continuously adjusted by considering natural image quality or graphic image quality. An object of the present invention is to provide an image processing apparatus, an image processing method, and an image processing program capable of appropriately performing an image correction process according to an image type.
[0007]
[Means for Solving the Problems]
The present invention provides an image processing apparatus devised to achieve the above object, a difference value calculating means for calculating a difference value between pixels around a target pixel for image data to be processed, and the difference value calculating means A difference value frequency totaling unit that totalizes the distribution frequency of the difference value calculated by the feature, a feature amount extraction unit that extracts the feature amount from the distribution frequency totaled by the difference value frequency totaling unit, Extracting feature values of the image data from the distribution of brightness values, saturation values, and hue values in the image data, and calculating brightness correction amount, saturation correction amount, and hue correction amount for the image data based on the feature amounts Do Correction amount calculating means; A correction amount adjustment unit that performs adjustment with an adjustment strength that reflects the feature amount extracted by the feature amount extraction unit with respect to the correction amount calculated by the correction amount calculation unit, and a post-adjustment by the correction amount adjustment unit And a correction execution unit that performs an image correction process on the image data according to a correction amount.
[0008]
The present invention is also an image processing method devised to achieve the above object. That is, an image processing method for performing predetermined image correction processing on image data to be processed, a difference value calculating step of calculating a difference value between pixels around a target pixel for the image data, A difference value frequency counting step for counting the distribution frequency of the difference value calculated in the difference value calculating step, and a feature value extracting step for extracting the feature value from the distribution frequency counted in the difference value frequency counting step; Extracting feature values of the image data from the distribution of brightness values, saturation values, and hue values in the image data, and calculating brightness correction amount, saturation correction amount, and hue correction amount for the image data based on the feature amounts Do A correction amount calculating step; A correction amount adjustment step for performing adjustment with an adjustment intensity reflecting the feature amount extracted in the feature amount extraction step with respect to the correction amount calculated in the correction amount calculation step; and after the adjustment in the correction amount adjustment step And a correction execution step of performing an image correction process on the image data according to a correction amount.
[0009]
Further, the present invention is an image processing program devised to achieve the above object, a computer for calculating a difference value between pixels around a target pixel for image data to be processed; A difference value frequency totaling unit that totals the distribution frequency of the difference value calculated by the difference value calculation unit; a feature amount extraction unit that extracts the feature amount from the distribution frequency totaled by the difference value frequency totaling unit; Extracting feature values of the image data from the distribution of brightness values, saturation values, and hue values in the image data, and calculating brightness correction amount, saturation correction amount, and hue correction amount for the image data based on the feature amounts Do Correction amount calculating means; A correction amount adjustment unit that performs adjustment with an adjustment strength that reflects the feature amount extracted by the feature amount extraction unit with respect to the correction amount calculated by the correction amount calculation unit, and a post-adjustment by the correction amount adjustment unit The image processing apparatus functions as a correction execution unit that performs an image correction process on the image data according to a correction amount.
[0010]
In the image processing apparatus having the above-described configuration, the image processing method having the above-described procedure, and the computer executing the image processing program having the above-described configuration, a difference value between pixels around the target pixel is calculated, and the distribution frequency of the calculated difference values is aggregated. . From the distribution frequency, which is a result of the aggregation, for example, a regular degree of gradation (gradation smoothness) is known. Therefore, if the feature amount is extracted from the aggregated distribution frequency, the graphic image quality of the image data to be processed, for example, is continuously specified instead of binary by the feature amount. Therefore, this continuous feature amount Adjust the brightness correction amount, saturation correction amount, and hue correction amount of the image data with the adjustment strength that reflects the If the image correction process is performed on the image data with the correction amount, the image correction process is not binary but continuous, and if the correction amount is determined to be 0, the image correction process is not substantially performed. become. That is, when performing image correction processing, continuous correction processing according to the image characteristics of image data to be processed can be performed without requiring binary control such as natural image / graphic image discrimination. It becomes possible.
[0011]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an image processing apparatus, an image processing method, and an image processing program according to the present invention will be described with reference to the drawings.
[0012]
First, the configuration of the image processing apparatus according to the present invention will be described. The image processing apparatus described here performs image correction processing such as gradation correction, contrast correction, and color balance correction on image data to be processed. Note that details of the image correction process are well known, and thus the description thereof is omitted here.
[0013]
Since the image processing apparatus described here performs image correction processing on image data, for example, a copying machine, a scanner apparatus, a printer apparatus, a FAX apparatus, a computer apparatus having an image processing function, etc. Thus, it is used by being mounted on various devices that handle image data. Furthermore, it may be used on a network system in which these various devices are connected to each other by wire or wirelessly. The details of these various devices are also well known, and the description thereof is omitted here.
[0014]
FIG. 1 is a block diagram showing a schematic configuration example of an image processing apparatus according to the present invention. As shown in the figure, the image processing apparatus described here is roughly composed of a graphic degree calculation unit 10, an adaptive correction amount calculation unit 20, and a correction execution unit 30.
[0015]
The graphic degree calculation unit 10 calculates the graphic image quality (hereinafter referred to as “graphic degree”), which is one of the image characteristics in the image data to be processed. For this purpose, the graphic degree calculation unit 10 calculates a difference value between pixels around the target pixel for the image data to be processed, and a distribution frequency of the difference values calculated by the difference value calculation unit 11. Difference value frequency totaling unit 12 and a feature amount extracting unit 13 that extracts the feature amount from the distribution frequency totaled by the difference value frequency totaling unit 12.
[0016]
The adaptive correction amount calculation unit 20 determines a correction amount for the image data to be processed based on the graphic degree calculated by the graphic degree calculation unit 10. For this purpose, the adaptive correction amount calculating unit 20 includes a histogram totaling unit 21 that histograms the distributions of lightness values, saturation values, and hue values in the image data to be processed, and a tabulated result from the histogram totaling unit 21. A feature amount extraction unit 22 that extracts a feature amount in the image data to be processed, and a lightness correction amount, a saturation correction amount, and a hue for the image data to be processed based on the feature amount extracted by the feature amount extraction unit 22 A correction amount calculation unit 23 that calculates a correction amount, and a correction amount adjustment unit 24 that reflects the graphic degree calculated by the graphic degree calculation unit 10 in each correction amount calculated by the correction amount calculation unit 23 are provided.
[0017]
The correction execution unit 30 performs image correction processing on the image data to be processed, specifically, the lightness value, the saturation value, and the hue value in the image data based on the correction amount determined by the adaptive correction amount calculation unit 20. Is what you do.
[0018]
These units 10 to 30 can be realized by hardware such as ASIC (Application Specified Integrated Circuit). However, it may be realized by software. That is, each of these units 10 to 30 may be realized by a microprocessor having a function as a computer executing a predetermined image processing program. In this case, it is conceivable that the image processing program is stored in advance in a microprocessor or a storage element connected to the microprocessor, but even if it is stored and provided in a computer-readable storage medium, Alternatively, it may be distributed via wired or wireless communication means.
[0019]
Next, an example of processing operation in the image processing apparatus having the above configuration (or a microprocessor that executes an image processing program), that is, an image processing method according to the present invention will be described. FIG. 2 is a flowchart showing an example of the procedure of the image processing method according to the present invention.
[0020]
When there is input of image data (a set of pixel values) to be processed (step 101, hereinafter “step” is abbreviated as “S”), the image processing apparatus performs color conversion processing such as HSL conversion on the image data. Perform (S102). Normally, gradations used to represent graphic images are created on RGB, but when converted to lightness, saturation, and hue signals represented by HSL, for example, the hue is constant and the saturation and lightness change. Or the signal value of lightness, saturation, or hue is fixed (no change in signal value) such that only the lightness changes with a constant saturation. This is because it is easier to distinguish between a natural image and a graphic image than in the above determination. Therefore, when the input image data consists of lightness, saturation, and hue signals from the beginning, color conversion processing is not necessary.
[0021]
In the image processing apparatus, before the image correction process is performed on the image data including the lightness, saturation, and hue signals, first, the graphic degree calculation unit 10 is used when calculating the graphic degree. Variable initialization is performed (S103). That is, variable g = 0 and variable all = 0. Details of these variables g and all will be described later.
[0022]
When variable initialization is performed, subsequently, in the graphic degree calculation unit 10, the difference value calculation unit 11 calculates a difference value (absolute value) between pixels in a region around the pixel of interest (hereinafter referred to as “region of interest”) ( S104). Here, the calculation of the difference value will be described in detail. FIG. 3 is an explanatory diagram showing an outline of difference value calculation. For example, as shown in FIG. 3A, the difference value calculation unit 11 calculates the difference between two pixels adjacent to the left and right of the target pixel in the target region (pixels located in the ± 1 portion in the figure). The difference between the lightness value, the saturation value, and the hue value is calculated. Also, as shown in FIG. 3 (b), for two pixels located one pixel on the left and right sides of the pixel of interest (pixels located in the ± 2 portion in the figure), the brightness value between the pixels, the chroma The difference between the degree value and the hue value may be calculated.
[0023]
As described above, the difference value calculation unit 11 calculates the difference value between the pixels having an interval of one pixel or more (at least for the target pixel) as the difference value between the pixels in the target region. Depending on the reason. When calculating the difference value between pixels that are separated to some extent, the relevance between the pixels is lower than when calculating the difference value between adjacent pixels. On the other hand, if it is a graphic image, the difference value between pixels does not become as large as that in the case of a natural image even if it is slightly separated. That is, it becomes easy to distinguish between a natural image and a graphic image. Therefore, a difference value between pixels having an interval of one pixel or more is calculated. In addition, it is considered that it is appropriate to leave about 1 to 3 pixels between the pixels.
[0024]
As shown in FIG. 2, the difference value frequency totaling unit 12 compares the difference value obtained by the calculation in the difference value calculating unit 11 with a preset threshold th_edg (S105). As a result of the comparison, if the difference value exceeds the threshold th_edg, the difference value frequency counting unit 12 does not include the difference value in the subsequent counting. This is because the portion of the difference value exceeding the threshold th_edg corresponds to the edge portion on the image, and can exist in both the natural image and the graphic image. This is because a portion that is not appropriate as a material for determining the distinction between a natural image and a graphic image is excluded.
[0025]
On the other hand, if the difference value is equal to or less than the threshold th_edg, the difference value frequency counting unit 12 determines whether or not the difference value belongs to the preset difference value ranges a1 to a2 (S106). As the difference value range a1 to a2, for example, in order to tabulate the graphic degree representing the graphic image, setting is made so as to place importance on the distribution frequency of a region having a small difference value, that is, a region having a small difference value is set. It is possible. This is because graphic images are composed of gentle, regular gradations and uniform parts, so that the difference value between pixels tends to be small, whereas natural images do not have such regularity. Because.
[0026]
FIG. 4 is an explanatory diagram showing a specific example of the result of counting the distribution frequency of the difference values between the graphic image and the natural image. As is clear from the example in the figure, in the case of a graphic image, the difference value between pixels always tends to be small, so the distribution is concentrated in a region where the difference value is small (shadow part in the figure) ( This is not the case with natural images (see FIG. 4A) (see FIG. 4B). Therefore, if the difference value range a1 to a2 is set so as to emphasize the distribution frequency of the region having a small difference value, it can be said that it becomes easy to distinguish between the natural image and the graphic image.
[0027]
The difference value region to be emphasized, that is, the set value of the difference value range a1 to a2, differs depending on the gradation value of the image data to be processed. For example, when the maximum difference value is 50, about 10% of the difference value region is set. It can be considered to be about 0 to 5 corresponding to the region. More preferably, a1 = 0 and a2 = 2 can be considered in order to increase the ease of discrimination.
[0028]
In FIG. 2, if the difference value obtained by the calculation in the difference value calculation unit 11 belongs to the difference value range a1 to a2, the difference value frequency counting unit 12 belongs to the difference value range a1 to a2. The variable g representing the accumulated number of difference values is counted up (S107), and the variable all representing the total number of difference values to be counted is counted up (S108). If the difference value obtained by the calculation in the difference value calculation unit 11 does not belong to the difference value range a1 to a2, the difference value frequency counting unit 12 sets the variable all without counting up the variable g. Count up (S108).
[0029]
The difference value calculation unit 11 and the difference value frequency totaling unit 12 repeat the above processing until all pixel values of the image data to be processed are completed. That is, as a result of determining whether or not the processing has been completed for all the pixels (S109), if the processing has not been completed, after moving the region of interest (pixel of interest) (S110), the difference value calculation process described above again for the region of interest The difference value frequency is aggregated (S104 to S110). However, at this time, it is not always necessary to perform the difference value calculation process or the like for all of the pixel values constituting the image data to be processed. That is, the difference value calculation unit 11 and the difference value frequency totaling unit 12 may perform difference value calculation processing or the like by appropriately thinning out pixels (regions of interest).
[0030]
Thereafter, in the graphic degree calculation unit 10, the feature amount extraction unit 13 extracts the feature amount from the result of counting up the variables g and all by the difference value frequency totaling unit 12. Specifically, g / all is obtained as a feature quantity from the variable g and the variable all (S111). This feature amount represents the graphic degree of the image data to be processed, that is, how gentle the image data to be processed is composed of regular gradations and uniform portions. Therefore, the image data composed of regular gradations and uniform portions has a higher graphic degree (closer to 1), but the image data other than that has a low graphic degree (closer to 0).
[0031]
When the graphic degree of the image data is extracted, the feature amount extraction unit 13 further calculates an adjustment strength for the image data to be processed based on the graphic degree (S112). The calculation of the adjustment strength may be performed using a preset function. FIG. 5 is an explanatory diagram showing a specific example of a function for calculating the adjustment strength. As shown in the figure, as the function for calculating the adjustment strength, the higher the graphic degree (closer to 1), the smaller the adjustment strength (adjustment strength close to 0) is obtained, and the lower the graphic degree (close to 0), the larger Any adjustment strength (adjustment strength close to 1) may be obtained. This is because image correction processing should be performed for natural images in order to obtain a preferable image quality, whereas graphic images should not be subjected to extra image correction processing as much as possible in order to correctly reflect the creation intention. Because it should.
[0032]
In this way, the graphic degree calculation unit 10 calculates the graphic degree of the image data to be processed, and further calculates the adjustment strength specified from the graphic degree. Then, the graphic degree calculation unit 10 notifies the adaptive correction amount calculation unit 20 of the calculation result of the adjustment strength.
[0033]
At this time, in the adaptive correction amount calculation unit 20, with respect to the image data to be processed, the histogram totaling unit 21 histograms the distribution of the brightness value, the saturation value, and the hue value, and the feature amount extraction unit 22 uses the histogram. The feature amount of the total result is extracted, and the correction amount calculation unit 23 calculates the lightness correction amount, the saturation correction amount, and the hue correction amount for the image data to be processed based on the feature amount. Further, a correction amount such as a contrast amount, a sharpness amount, and a memory color adjustment amount may be calculated. Note that the processing in the adaptive correction amount calculation unit 20 may be performed using a method similar to the conventional method (when determining the correction amount for a natural image after discrimination of a natural image / graphic image). Description is omitted.
[0034]
Therefore, when the calculation result of the adjustment strength is notified from the graphic degree calculation unit 10, the adaptive correction amount calculation unit 20 causes the graphic degree of the image data to be reflected in the correction amount for the image data to be processed. Therefore, using the notified adjustment strength, the correction amount adjustment unit 24 adjusts each correction amount calculated by the correction amount calculation unit 23 (S113). Specifically, the calculation “correction amount after adjustment” = “correction amount calculated by the correction amount calculation unit 23” × “adjustment intensity notified from the graphic degree calculation unit 10” is performed to calculate the correction amount calculation unit 23. The adjustment for each correction amount calculated by is performed. The correction amount after adjustment obtained in this way is a variable value within a predetermined range including 0 because the adjustment strength is in the range of 0 to 1. Therefore, the correction amount adjustment unit 24 determines the correction amount, which is a variable value within a predetermined range including 0, as any value based on the adjustment strength from the graphic degree calculation unit 10. I can say that.
[0035]
When the correction amount adjustment unit 24 determines the adjusted correction amount, the correction execution unit 30 performs lightness value correction and saturation value correction on the image data to be processed based on the adjusted correction amount. Correction and hue value correction are performed (S114). Therefore, if the correction amount determined by the correction amount adjustment unit 24 is 0, the correction execution unit 30 does not perform image correction processing on the image data. Note that the image correction processing performed by the correction execution unit 30 may be performed using a method similar to the conventional one.
[0036]
As described above, according to the image processing apparatus described in the present embodiment, the image processing program executed by the image processing apparatus, and the image processing method that is the execution result, the distribution frequency of the difference value between the pixels in the region of interest. By calculating the degree of smoothness of the gradation from the aggregation result and obtaining the graphic degree, and performing the image correction process on the image data to be processed using the correction amount reflecting the graphic degree, A preferable image is obtained. That is, the image correction process is uniformly performed without performing the determination process of whether the image is a natural image or a graphic image, but the graphic degree calculation result is reflected in the correction amount in the image correction process. Moreover, the correction amount is a variable value within a predetermined range including zero. Therefore, even when image correction processing is performed uniformly, for example, the graphic degree is Low About image data By adjusting with a large adjustment strength Large correction amount and graphic degree high For image data, it is possible to set the correction amount to 0 and substantially not perform image correction processing.
[0037]
Therefore, according to the present embodiment, instead of performing binary image discrimination such as a natural image / graphic image, for example, image correction processing is uniformly performed using a correction amount that varies continuously according to image characteristics. Thus, for example, it is possible to avoid the disadvantage that the correction result varies greatly depending on a slight difference in image characteristics. As a result, the image correction process can be optimized.
[0038]
In the present embodiment, the color conversion processing is performed on the image data, and the graphic degree is calculated from the total result of the difference value distribution frequencies of the brightness, hue, and saturation. It becomes easy to distinguish from a graphic image, and as a result, the image characteristics can be accurately reflected in the correction amount (image correction processing). Furthermore, the correction amount can be controlled with higher accuracy than when the graphic degree is calculated from only one of the parameters of brightness, hue, and saturation. When the aggregation results are obtained for the brightness, hue, and saturation parameters, the aggregation result of the parameter with the highest graphic degree is adopted, or the average of the aggregation results is taken as the graphic degree. May be calculated. However, it is not always necessary to use all these parameters as a basis. Needless to say, if the distribution frequency of the difference values for at least one parameter is aggregated, the image correction process can be made more appropriate than before.
[0039]
In the present embodiment, the difference value between the pixels having an interval of one pixel or more is calculated as the difference value between the pixels in the region of interest. This also makes it possible to improve control accuracy with respect to the correction amount.
[0040]
In the present embodiment, when the difference value between pixels exceeds the threshold th_edg, the difference value is not included in the aggregation of the distribution frequency, so that the edge portion on the image is effectively excluded. In this respect, it can be said that it is possible to improve the control accuracy with respect to the correction amount.
[0041]
In the present embodiment, in calculating the degree of graphics, importance is placed on the distribution frequency of an area having a small difference value, so that the difference in characteristics between the graphic image and the natural image is effectively utilized. This makes it easier to distinguish the image. Therefore, this also improves the control accuracy with respect to the correction amount.
[0042]
In the present embodiment, the case where the graphic degree is extracted as the feature amount related to the image data has been described as an example, but the present invention is not limited to this. That is, for example, even if natural image quality (natural image quality) is extracted as a feature amount or other feature amounts are extracted, a correction amount that is a variable value based on the extracted feature amount If any one of the values is determined and image correction processing is performed, continuous non-binary image correction processing can be realized.
[0043]
In addition, the difference value aggregation, the graphic degree calculation, the adjustment strength calculation, and the like described in the present embodiment are merely examples of the preferred embodiment of the present invention, and are not limited thereto. is there.
[0044]
【The invention's effect】
As described above, according to the image processing apparatus, the image processing method, and the image processing program of the present invention, the image type is not simply determined in a binary manner, but the natural image quality or the graphic image quality is considered. Thus, the correction amount for the image data can be continuously adjusted. Therefore, even if a high-performance computer environment, application software, etc. can be used to represent a natural image even in a graphic image, the inconvenience that the correction result differs greatly due to a slight difference in image characteristics can be avoided. Therefore, it is possible to appropriately perform the image correction process according to the image type.
[Brief description of the drawings]
FIG. 1 is a block diagram illustrating a schematic configuration example of an image processing apparatus according to the present invention.
FIG. 2 is a flowchart showing an example of a procedure of an image processing method according to the present invention.
FIGS. 3A and 3B are explanatory diagrams showing an outline of difference value calculation according to the present invention, FIG. 3A is a diagram illustrating an example thereof, and FIG. 3B is a diagram illustrating another example;
FIG. 4 is an explanatory diagram showing a specific example of a result of counting difference frequency distribution frequencies between a graphic image and a natural image according to the present invention.
FIG. 5 is an explanatory diagram showing a specific example of a function for calculating the adjustment intensity of the correction amount in the present invention.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Graphic degree calculation part, 11 ... Difference value calculation part, 12 ... Difference value frequency totalization part, 13 ... Feature-value extraction part, 20 ... Adaptive correction amount calculation part, 21 ... Histogram totalization part, 22 ... Feature-value extraction part, 23 ... Correction amount calculation unit, 24 ... Correction amount adjustment unit, 30 ... Correction execution unit

Claims (15)

Difference value calculation means for calculating a difference value between pixels around the target pixel for the image data to be processed;
Difference value frequency counting means for counting the distribution frequency of the difference values calculated by the difference value calculating means;
Feature quantity extraction means for extracting the feature quantity from the distribution frequency tabulated by the difference value frequency tabulation means;
Extracting feature values of the image data from the distribution of brightness values, saturation values, and hue values in the image data, and calculating brightness correction amount, saturation correction amount, and hue correction amount for the image data based on the feature amounts Correction amount calculating means to perform ,
Correction amount adjusting means for performing adjustment with adjustment strength reflecting the feature amount extracted by the feature amount extracting means with respect to the correction amount calculated by the correction amount calculating means;
An image processing apparatus comprising: a correction execution unit that performs an image correction process on the image data based on a correction amount after adjustment by the correction amount adjustment unit . The image processing according to claim 1, wherein the difference value calculating unit and the difference value frequency totaling unit calculate difference values and total distribution frequencies for each of brightness, hue, and saturation between pixels. apparatus. The image processing according to claim 1, wherein the difference value calculation unit calculates a difference value between pixels having an interval of one pixel or more as a difference value between pixels around the target pixel. apparatus. The difference value frequency aggregation means does not include the difference value in the distribution frequency aggregation when the difference value calculated by the difference value calculation means exceeds a predetermined threshold. 3. The image processing apparatus according to 3. The image processing apparatus according to claim 1, 2, 3, or 4, wherein the feature amount extraction unit attaches importance to a distribution frequency of a region having a small difference value when extracting the feature amount. An image processing method for performing predetermined image correction processing on image data to be processed,
A difference value calculating step of calculating a difference value between pixels around the target pixel for the image data;
A difference value frequency counting step for counting the distribution frequency of the difference values calculated in the difference value calculating step;
A feature amount extraction step for extracting the feature amount from the distribution frequency tabulated in the difference value frequency tabulation step;
Extracting feature values of the image data from the distribution of brightness values, saturation values, and hue values in the image data, and calculating brightness correction amount, saturation correction amount, and hue correction amount for the image data based on the feature amounts A correction amount calculating step,
A correction amount adjustment step of performing adjustment with an adjustment intensity reflecting the feature amount extracted in the feature amount extraction step with respect to the correction amount calculated in the correction amount calculation step;
An image processing method comprising: a correction execution step of performing an image correction process on the image data with the correction amount after the adjustment in the correction amount adjustment step . The image processing according to claim 6, wherein, in the difference value calculation step and the difference value frequency aggregation step, difference value calculation and distribution frequency aggregation are performed for each of brightness, hue, and saturation between pixels. Method. The image processing according to claim 6 or 7, wherein, in the difference value calculating step, a difference value between pixels having an interval of one pixel or more is calculated as a difference value between pixels around the target pixel. Method. In the difference value frequency aggregation step, if the difference value calculated in the difference value calculation step exceeds a predetermined threshold value, the difference value is not included in the distribution frequency aggregation. 8. The image processing method according to 8. The image processing apparatus according to claim 6, 7, 8, or 9, wherein the feature amount extraction step places importance on a distribution frequency of a region having a small difference value in extracting the feature amount. Computer
Difference value calculation means for calculating a difference value between pixels around the target pixel for the image data to be processed;
Difference value frequency counting means for counting the distribution frequency of the difference values calculated by the difference value calculating means;
Feature quantity extraction means for extracting the feature quantity from the distribution frequency tabulated by the difference value frequency tabulation means;
Extracting feature values of the image data from the distribution of brightness values, saturation values, and hue values in the image data, and calculating brightness correction amount, saturation correction amount, and hue correction amount for the image data based on the feature amounts Correction amount calculating means to perform ,
Correction amount adjusting means for performing adjustment with adjustment strength reflecting the feature amount extracted by the feature amount extracting means with respect to the correction amount calculated by the correction amount calculating means;
An image processing program that functions as a correction execution unit that performs an image correction process on the image data based on a correction amount adjusted by the correction amount adjusting unit . The image processing according to claim 11, wherein the difference value calculating unit and the difference value frequency totaling unit calculate a difference value and total a distribution frequency for each of brightness, hue, and saturation between pixels. program. The image processing according to claim 11 or 12, wherein the difference value calculation means calculates a difference value between pixels having an interval of one pixel or more as a difference value between pixels around the target pixel. program. The difference value frequency aggregation means does not include the difference value in the distribution frequency aggregation when the difference value calculated by the difference value calculation means exceeds a predetermined threshold value. 13. The image processing program according to 13. 15. The image processing program according to claim 11, 12, 13, or 14, wherein the feature amount extraction unit places importance on a distribution frequency of a region having a small difference value in extracting the feature amount.

Images