Image processing device, image processing method, and program

1. An image processing device, comprising:

one or more processors configured to:

detect a first region in a certain color from an input image;

calculate a feature amount related to luminance of the input image;

execute noise removal on the input image based on a result obtained by detecting the first region in the certain color, and the feature amount,

reduce the input image;

execute a first filter process on the reduced input image;

enlarge the input image, filtered by use of the first filter process, to a size of the input image before reduction;

execute a second filter process on the input image;

synthesize, the enlarged input image with the input image filtered by use of the second filter process, by use of a first synthesizing coefficient decided based on the result obtained by detection of the first region in the certain color, and the feature amount; and

synthesize, the input image synthesized by use of the first synthesizing coefficient with the input image, by use of a second synthesis coefficient decided based on the result obtained based on detection of the first region in the certain color and the feature amount.

2. The image processing device according to claim 1 , wherein the one or more processors are further configured to execute the noise removal having a noise removal effect on the first region in the certain color, the noise removal effect being stronger than a noise removal effect of the noise removal to be executed on a second region.

3. The image processing device according to claim 1 , wherein the one or more processors are further configured to execute the noise removal having a noise removal effect on a border of the first region in the certain color, the noise removal effect on the border of the first region being weaker than a noise removal effect of the noise removal to be executed on a second region.

4. The image processing device according to claim 1 , wherein the certain color is an achromatic color.

5. The image processing device according to claim 1 , wherein the one or more processors are further configured to calculate the feature amount based on edge detection.

6. The image processing device according to claim 5 , wherein the one or more processors are further configured to calculate a flatness degree of luminance of the first region as the feature amount, the flatness degree being calculated as a reciprocal of edge strength of the first region.

7. The image processing device according to claim 6 , wherein the one or more processors are further configured to execute the noise removal having a noise removal effect on the first region, the noise removal effect being stronger than a noise removal effect of the noise removal to be executed on a second region, the first region having the flatness degree of luminance greater than or equal to a threshold.

8. The image processing device according to claim 1 , wherein the one or more processors are further configured to:

calculate border information indicating typicality of a border of the first region in the certain color based on the result obtained by detecting the first region in the certain color, and

execute the noise removal on the input image by use of at least any one of processes different from each other based on the border information and the feature amount.

9. The image processing device according to claim 8 , wherein the processes different from each other have different ranges of the first region on the input image, the first region being used for noise removal.

10. The image processing device according to claim 8 , wherein the one or more processors are further configured to:

supply the input image for at least one of the reduction or the second filter process based on the border information and the feature amount.

11. An image processing method, comprising:

detecting a first region in a certain color from an input image;

calculating a feature amount related to luminance of the input image;

executing noise removal on the input image based on a result obtained by detecting the first region in the certain color, and the feature amount,

reducing the input image and executing a first filter process on the reduced input image;

enlarging the input image, filtered using the first filter process, to a size of the input image before reduction;

executing a second filter process on the input image;

synthesizing the enlarged input image with the input image filtered using the second filter process, by using a first synthesizing coefficient decided based on the result obtained by detecting the first region in the certain color, and the feature amount; and

synthesizing the input image synthesized using the first synthesizing coefficient with the input image, by using a second synthesis coefficient decided based on the result obtained by detecting the first region in the certain color and the feature amount.

12. A non-transitory computer-readable medium having stored thereon, computer-executable instructions for causing a computer to execute operations, comprising:

detecting a first region in a certain color from an input image;

calculating a feature amount related to luminance of the input image;

executing noise removal on the input image based on a result obtained by detecting the first region in the certain color, and the feature amount,

reducing the input image and executing a first filter process on the reduced input image;

enlarging the input image, filtered using the first filter process, to a size of the input image before reduction;

executing a second filter process on the input image;

synthesizing the enlarged input image with the input image filtered using the second filter process, by using a first synthesizing coefficient decided based on the result obtained by detecting the first region in the certain color, and the feature amount; and

synthesizing the input image synthesized using the first synthesizing coefficient with the input image, by using a second synthesis coefficient decided based on the result obtained by detecting the first region in the certain color and the feature amount.