Image processing apparatus, method, and recording medium for reducing noise in an image

1. An image processing apparatus comprising:

a low-frequency component extraction unit for extracting a first low-frequency component from first image data;

a noise reduction unit for obtaining a second low-frequency component by applying a noise reduction filter to either the first low-frequency component or data obtained by processing the first low-frequency component;

a high-frequency component extraction unit for extracting a first high-frequency component from the first images data and either one of the second low-frequency component and data obtained by processing the second low-frequency component, and the first image data;

a high-frequency component tuning unit for obtaining a second high-frequency component by tuning the first high-frequency component to reduce amplitude of the first high-frequency component; and

an image synthesis unit for obtaining second image data by combining either one of the second low-frequency component and the data obtained by processing the second low-frequency component with the second high-frequency component.

2. The apparatus of claim 1 , further comprising:

a scale-down unit for scaling down the first low-frequency component; and

a scale-up unit for scaling up the second low-frequency component,

wherein the noise reduction unit obtains a second low-frequency component by applying a noise reduction filter to the scaled-down first low-frequency component,

the high-frequency component extraction unit extracts the first high-frequency component from the scaled-up second low-frequency component and the first image data, and

the image synthesis unit obtains second image data by combining the scaled-up second low-frequency component and the second high-frequency component.

3. The apparatus of claim 1 , wherein the low-frequency component extraction unit comprises a low-pass filter.

4. The apparatus of claim 1 , wherein the noise reduction unit comprises a bilateral filter.

5. The apparatus of claim 1 , wherein the high-frequency component extraction unit obtains the first high-frequency component by using the difference between the first image data and the second low-frequency component.

6. The apparatus of claim 2 , wherein the high-frequency component extraction unit obtains the first high-frequency component by using the difference between the first image data and the scaled-up second low-frequency component.

7. An image processing method comprising:

extracting a first low-frequency component from first image data;

obtaining a second low-frequency component by applying a noise reduction filter to the first low-frequency component;

obtaining a first high-frequency component from the first image data and the second low-frequency component;

obtaining a second high-frequency component by tuning the first high-frequency component to reduce amplitude of the first high-frequency component; and

obtaining second image data by combining the second low-frequency component with the second high-frequency component.

8. The method of claim 7 , wherein a low-pass filter is used in the extracting of the first low-frequency component.

9. The method of claim 7 , a bilateral filter is used in the obtaining of the second low-frequency component.

10. The method of claim 7 , wherein the obtaining of the first high-frequency component comprises obtaining the first high-frequency component by using the difference between the first image data and the second low-frequency component.

11. A computer readable medium having recorded thereon a program for controlling a computer to perform the following operations:

extract a first low-frequency component from first image data;

obtain a second low-frequency component by applying a noise reduction filter to the first low-frequency component;

obtain a first high-frequency component from the first image data and the second low-frequency component;

obtain a second high-frequency component by tuning the first high-frequency component to reduce amplitude of the first high-frequency component; and

obtain second image data by combining the second low-frequency component with the second high-frequency component.

12. An image processing method comprising:

extracting a first low-frequency component from first image data;

scaling down the first low-frequency component;

obtaining a second low-frequency component by applying a noise reduction filter to the scaled-down first low-frequency component;

scaling up the second low-frequency component;

obtaining a first high-frequency component from the first image data and the scaled-up second low-frequency component;

obtaining a second high-frequency component by tuning the first high-frequency component; and

obtaining second image data by combining the scaled-up second low-frequency component with the second high-frequency component.

13. The method of claim 12 , wherein a low-pass filter is used in the extracting of the first low-frequency component.

14. The method of claim 12 , wherein a bilateral filter is used in the obtaining of the second low-frequency component.

15. The method of claim 12 , wherein the obtaining of the first high-frequency component comprises obtaining the first high-frequency component by using the difference between the first image data and the scaled-up second low-frequency component.

16. The method of claim 12 , wherein the obtaining of the second high-frequency component comprises obtaining the second high-frequency component by tuning the first high-frequency component to reduce amplitude of the first high-frequency component.

17. A computer readable medium having recorded thereon a computer program for controlling a computer to perform the following operations:

extract a first low-frequency component from first image data;

scale down the first low-frequency component;

obtain a second low-frequency component by applying a noise reduction filter to the scaled-down first low-frequency component;

scale up the second low-frequency component;

obtain a first high-frequency component from the first image data and the scaled-up second low-frequency component;

obtain a second high-frequency component by tuning the first high-frequency component; and

obtain second image data by combining the scaled-up second low-frequency component with the second high-frequency component.

18. A computer readable medium of claim 17 , wherein the obtaining of the first high-frequency component comprises obtaining the first high-frequency component by using the difference between the first image data and the scaled-up second low-frequency component.