Method and system for enhancing image quality
The present disclosure relates to image filtering techniques for enhancing image quality. In one embodiment, two filtering techniques are applied on an image. Firstly, an adaptive weighted median filtering operation is performed on an acquired low contrast image corrupted by impulsive noise. Subsequently, a guided image filtering on the image obtained from adaptive weighted median filtering operation to de-blur and enhance the contrast that ultimately assures to preserve the edges of the images. In addition, the image filtering for enhancing image quality is enhanced by several variations of data adaptive guided image filtering and adaptive window sizes for guided image filtering techniques.
1. A method for enhancing image quality using an image processing system, said method comprising acts of:
obtaining an image;
performing, by a median filtering module, an adaptive weighted median filtering operation on each pixel of the obtained image to output an intermediary image by removing impulse noise, wherein performing the adaptive weighted median filtering operation comprises:
selecting a pixel value of the obtained image;
forming a window using all adjacent pixels around the selected pixel value;
determining a pixel with maximum value and a pixel with minimum value in the window;
comparing value of the selected pixel with the minimum pixel value and the maximum pixel value;
increasing size of the window by including all pixels adjacent to the window until the selected pixel value is determined to be within minimum and maximum pixel value of the window; and
upon determining the selected pixel value to be within the minimum and the maximum pixel value, performing:
determining a median of the window of the obtained image;
determining weight of the median to obtain weighted median value; and
determining an intermediate image using the obtained weighted median value; and
performing, by a guided image filtering module, a guided image filtering operation on the intermediary image to output a final image with enhanced contrast and preserved edges of the image.
2. The method as claimed in claim 1 , wherein the adaptive weighted median filtering module and the guided image filtering module derive filter coefficients from the obtained image.
3. The method as claimed in claim 1 , wherein the adaptive weighted median filtering module derives filter coefficients from the obtained image and the guided image filtering module derives filter coefficients from the intermediary image.
4. The method as claimed in claim 2 , wherein the filter coefficients are calculated by using an offset value.
5. The method as claimed in claim 4 , wherein
the offset value is set as one of maximum pixel value of a selected window and median value of pixels of the selected window, upon determining mean removed guiding image pixel value to be positive;
the offset value is set as one of minimum pixel value of the selected window, median value of pixels of the selected window and zero, upon determining the mean removed guiding image pixel value to be negative;
the offset value is set as zero, upon determining the mean removed guiding image pixel value to be zero, wherein the mean removed guiding image pixel is difference between guiding image at a pixel value inside a selected window and mean pixel value inside the selected window.
6. The method as claimed in claim 5 , wherein size of the selected window is fixed.
7. The method as claimed in claim 5 , wherein size of the selected window is determined for each pixel value by steps comprising:
a. comparing the difference between variances of two consecutive odd size windows with a threshold value;
b. selecting the selected window size as larger window size of the two consecutive odd size windows upon determining the difference to be less than the threshold value; and
c. increasing size of the two consecutive odd size of windows by two and performing the steps a and b upon determining the difference to be greater than or equal to the threshold value.
8. The method as claimed in claim 7 , wherein the size of window is initially set as 3×3.
9. The method as claimed in claim 3 , wherein the filter coefficients are calculated by using an offset value.
10. A system for image quality enhancement comprising:
a median filtering module configured to perform adaptive weighted median filtering operation on each pixel of the image to output an intermediary image by removing impulse noise, said median filtering module is configured to:
select a pixel value of the obtained image;
form a window using all adjacent pixels around the selected pixel value;
determine a pixel with maximum value and a pixel with minimum value in the window;
compare value of the selected pixel with the minimum pixel value and the maximum pixel value;
increase size of the window by including all pixels adjacent to the window until the selected pixel value is determined to be within minimum and maximum pixel value of the window; and
upon determining the selected pixel value to be within the minimum and the maximum pixel value,
determine a median of the window of the obtained image;
determine weight of the median to obtain weighted median value; and
determine an intermediate image using the obtained weighted median value
an adaptive data selection module configured to generate filter coefficients; and
a guided image filtering module configured to filter the intermediary image using the generated filter coefficient and output a final image with enhanced contrast and preserved edges of the image.
11. The system as claimed in claim 10 , wherein the adaptive weighted median filtering module and the guided image filtering module derive the filter coefficients from the obtained image.
12. The system as claimed in claim 10 , wherein the adaptive weighted median filtering module derives filter coefficients from the obtained image and the guided image filtering module derives filter coefficients from the intermediary image.