Method and system for identifying defects in a radiographic image of a scanned object

1. A method for processing a radiographic image of a scanned object, the method comprising:

acquiring radiographic image data corresponding to a scanned object;

identifying one or more regions of interest in the radiographic image data corresponding to the scanned object by filtering the radiographic image data corresponding to the scanned object through an image-processing filter to identify the one or more regions of interest;

generating a noise-filtered radiographic image corresponding to the scanned object, based on the filtered radiographic image data by classifying one or more image pixels comprising the filtered radiographic image data based on a variance level associated with one or more of the image pixels; and

performing an image-contrast comparison of the radiographic image data corresponding to the scanned object and one or more reference radiographic images, to identify one or more defects in the radiographic image data corresponding to the scanned object.

2. The method of claim 1 , wherein the scanned object comprises at least one of cast aluminum components, turbine blades and cast metal equipment parts.

3. The method of claim 1 , wherein the image-processing filter is a median filter.

4. The method of claim 1 , further comprising generating a filtered radiographic image comprising one or more of the regions of interest.

5. The method of claim 1 , wherein the one or more regions of interest comprise at least one of noise, defects, edges and part structures comprising the radiographic image data corresponding to the scanned object.

6. The method of claim 1 , wherein performing the image-contrast comparison to identify one or more defective regions of interest in the radiographic image data comprising the scanned object comprises performing a comparison of an image-contrast intensity level of one or more regions comprising one or more noise-filtered reference radiographic images and an image-contrast intensity level of one or more regions comprising the noise-filtered radiographic image.

7. The method of claim 6 , further comprising performing a multi-resolution filtering of the one or more defective regions of interest comprising the radiographic image data corresponding to the scanned object.

8. The method of claim 7 , wherein performing the multi-resolution filtering of the one or more defective regions of interest comprises applying one or more localized image processing filters over the one or more defective regions of interest to identify one or more defects in the radiographic image data corresponding to the scanned object.

9. A radiographic inspection system comprising:

an imaging system configured to acquire radiographic image data corresponding to a scanned object; and

a computer system configured to be in signal communication with the imaging system, wherein the computer system comprises:

a memory configured to store the radiographic image data corresponding to the scanned object and one or more radiographic reference images corresponding to one or more reference objects;

a processor configured to:

process the radiographic image data and the one or more radiographic reference images;

identify one or more regions of interest in the radiographic image data corresponding to the scanned object by filtering the radiographic image data corresponding to the scanned object through an image-processing filter to identify the one or more regions of interest;

generate a noise-filtered radiographic image corresponding to the scanned object, based on the filtered radiographic image data by classifying one or more image pixels comprising the filtered radiographic image data based on a variance level associated with one or more of the image pixels; and

perform an image-contrast comparison of the radiographic image data corresponding to the scanned object and the one or more reference radiographic images to identify one or more defects in the radiographic image data corresponding to the scanned object; and

a display device configured to display the one or more defects in the radiographic image data corresponding to the scanned object.

10. The system of claim 9 , wherein the scanned object comprises at least one of cast aluminum components, turbine blades and cast metal equipment parts.

11. The system of claim 9 , wherein the processor is configured to generate a filtered radiographic image comprising one or more of the one or more regions of interest.

12. The system of claim 9 , wherein the one or more regions of interest comprise at least one of noise, defects, edges and part structures comprising the radiographic image data corresponding to the scanned object.

13. The system of claim 9 , wherein the processor is configured to perform the image-contrast comparison to identify one or more defective regions of interest in the radiographic image data comprising the scanned object based on a comparison of an image-contrast intensity level of one or more regions comprising one or more noise-filtered reference radiographic images and an image-contrast intensity level of one or more regions comprising the noise-filtered radiographic image.

14. The system of claim 13 , wherein the processor is further configured to perform a multi-resolution filtering of the one or more defective regions of interest by applying one or more localized image processing filters over the one or more defective regions of interest, to identify the one or more defects in the radiographic image data corresponding to the scanned object.

15. A method for processing a radiographic image of a scanned object, the method comprising:

acquiring radiographic image data corresponding to a scanned object;

identifying one or more regions of interest in the radiographic image data corresponding to the scanned object by filtering the radiographic image data corresponding to the scanned object through an image-processing filter to identify the one or more regions of interest;

generating a noise-filtered radiographic image corresponding to the scanned object, based on the filtered radiographic image data; and

performing an image-contrast comparison of the radiographic image data corresponding to the scanned object and one or more reference radiographic images, to identify one or more defects in the radiographic image data corresponding to the scanned object by performing a comparison of an image-contrast intensity level of one or more regions comprising one or more noise-filtered reference radiographic images and an image-contrast intensity level of one or more regions comprising the noise-filtered radiographic image.

16. The method of claim 15 , wherein the image-processing filter is a median filter.

17. The method of claim 15 , further comprising generating a filtered radiographic image comprising one or more of the regions of interest.

18. The method of claim 15 , wherein the one or more regions of interest comprise at least one of noise, defects, edges and part structures comprising the radiographic image data corresponding to the scanned object.

19. The method of claim 15 , further comprising performing a multi-resolution filtering of the one or more defective regions of interest comprising the radiographic image data corresponding to the scanned object.

20. The method of claim 19 , wherein performing the multi-resolution filtering of the one or more defective regions of interest comprises applying one or more localized image processing filters over the one or more defective regions of interest to identify one or more defects in the radiographic image data corresponding to the scanned object.