System and method for line Mura detection with preprocessing
A system and method for identifying line Mura defects on a display. The system is configured to generate a filtered image by preprocessing an input image of a display using at least one filter. The system then identifies line Mura candidates by converting the filtered image to a binary image, counting line components along a slope in the binary image, and marking a potential candidate location when the line components along the slope exceed a line threshold. Image patches are then generated with the candidate locations at the center of each image patch. The image patches are then classified using a machine learning classifier.
1. A system for identifying Mura in a display, the system comprising:
a memory;
a processor configured to execute instructions stored on the memory that, when executed by the processor, cause the processor to:
generate a filtered image by preprocessing an input image of a display using at least one filter;
identify a line Mura candidate by:
converting the filtered image to a binary image;
counting line components along a slope in the binary image; and
marking a candidate location in response to the line components along the slope exceeding a line threshold;
generate an image patch with the candidate location at the center of the image patch; and
classify the image patch using a machine learning classifier.
2. The system of claim 1 , wherein the at least one filter comprises at least one of: a Gabor filter and a pyramid filter.
3. The system of claim 1 , wherein converting the filtered image to the binary image comprises:
determining an average image intensity and a standard deviation of the filtered image;
calculating a binary threshold based on the average image intensity and standard deviation; and
converting the filtered image to the binary image according to the binary threshold.
4. The system of claim 1 , wherein the line threshold is equal to 70% of total line components along the slope.
5. The system of claim 1 , wherein the image patch is generated using the input image.
6. The system of claim 1 , wherein the machine learning classifier comprises a support vector machine.
7. The system of claim 1 , wherein the instructions further cause the processor to extract a feature vector from the image patch, wherein the feature vector comprises at least one image moment.
8. The system of claim 1 , wherein the instructions further cause the processor to normalize the input image.
9. A method for identifying Mura in a display comprising:
generating a filtered image by preprocessing an input image of a display using at least one filter;
identifying a line Mura candidate, wherein identifying a line Mura candidate comprises:
converting the filtered image to a binary image;
counting line components along a slope in the binary image; and
marking a candidate location in response to the line components along the slope exceeding a line threshold;
generating an image patch with the candidate location at the center of the image patch; and
classifying the image patch using a machine learning classifier.
10. The method of claim 9 , wherein the at least one filter comprises a Gabor filter and a Gaussian pyramid filter.
11. The method of claim 9 , wherein converting the filtered image to the binary image comprises:
determining an average image intensity and a standard deviation of the filtered image;
calculating a binary threshold based on the average image intensity and standard deviation; and
converting the filtered image to the binary image according to the binary threshold.
12. The method of claim 9 , wherein the line threshold is equal to 70% of total line components along the slope.
13. The method of claim 9 , wherein the image patch is generated using the input image.
14. The method of claim 9 , wherein the machine learning classifier comprises a support vector machine.
15. The method of claim 9 , further comprising extracting a feature vector the image patch, wherein the features vector comprises at least one image moment.
16. A method for identifying Mura in a display comprising:
normalizing an input image of a display to a desired data range;
generating a filtered image by preprocessing the normalized input image using a Gabor filter and a Gaussian pyramid filter;
identifying a line Mura candidate, wherein identifying a line Mura candidate comprises:
converting the filtered image to a binary image according to a binary threshold;
counting line components along at least one slope in the binary image; and
marking a candidate location in response to the line components along the at least one slope exceeding a line threshold;
generating at least one image patch with the candidate location at the center of the image patch; and
classifying the at least one image patch using a machine learning classifier.
17. The method of claim 16 , wherein converting the filtered image to the binary image comprises:
determining an average image intensity and a standard deviation of the filtered image;
calculating the binary threshold based on the average image intensity and standard deviation; and
converting the filtered image to the binary image according to the binary threshold.
18. The method of claim 17 , wherein the binary threshold is equal to the average image intensity plus the standard deviation divided by 1.5.
19. The method of claim 16 , wherein the machine learning classifier comprises a support vector machine.
20. The method of claim 16 , further comprising extracting a feature vector the image patch, wherein the features vector comprises at least one image moment.