Method and system for defect detection
A system, method and computer program product for defect detection, the method includes: (i) retrieving a second pixel of a second image that corresponds to a tested pixel of a first image of the object; wherein the first and second images were obtained using different acquisition methods; (ii) searching a third pixel of the second image such that a neighborhood of the second pixel is similar to a neighborhood of the third pixel; (iii) retrieving a fourth pixel of the first image that corresponds to the third pixel; and (iv) comparing between the tested pixel and the fourth pixel.
1. A method for defect detection, the method comprising:
retrieving a second pixel of a second image of an object that corresponds to a tested pixel of a first image of the object; wherein the first and second images were obtained using different acquisition methods;
searching a golden matching pixel of a second golden image such that a neighborhood of the golden matching pixel is similar to a neighborhood of the second pixel;
retrieving a corresponding golden pixel of a first golden image that corresponds to the golden matching pixel;
comparing between the tested pixel and the corresponding golden pixel; and
identifying defects in the object based on the comparison,
wherein each respective golden matching pixel and golden pixel of a golden image is a pixel of an image representing a defect-free object.
2. The method according to claim 1 further comprising repeating the searching for multiple tested pixels and generating statistics representative of a number of pixels found during the searching.
3. A non-transitory computer readable medium having computer readable code for defect detection embodied therein, the computer-readable code comprising instructions for:
retrieving a second pixel of a second image of an object that corresponds to a tested pixel of a first image of the object; wherein the first and second images were obtained using different acquisition methods;
searching a golden matching pixel of a second golden image such that a neighborhood of the golden matching pixel is similar to a neighborhood of the second pixel;
retrieving a corresponding golden pixel of a first golden image that corresponds to the golden matching pixel;
comparing between the tested pixel and the corresponding golden pixel; and identifying defects in the object based on the comparison,
wherein each respective golden matching pixel and golden pixel of a golden image is a pixel of an image representing a defect-free object.
4. The computer readable medium of claim 3 wherein the computer-readable code comprises instructions for: searching for multiple pixels of the second image that have neighborhoods that match a neighborhood of the second pixel.
5. The computer readable medium of claim 4 wherein the computer-readable code comprises instructions for: repeating the searching for multiple tested pixels and generating statistics representative of a number of pixels found during the searching.
6. The computer readable medium of claim 3 wherein the computer-readable code comprises instructions for: generating a synthetic image by replacing tested pixels by reference pixels.
7. A system for defect detection, the system comprising: a memory unit adapted to store information representative of neighborhoods of pixels within a first image of an object and within a second image of the object; and a processor, adapted to: retrieve a second pixel of a second image of the object that corresponds to a tested pixel of a first image of the object; wherein the first and second images were obtained using different acquisition methods;
search a golden matching pixel of a second golden image such that a neighborhood of the golden matching pixel is similar to a neighborhood of the second pixel; retrieve a corresponding golden pixel of a first golden image that corresponds to the golden matching pixel; and compare between the tested pixel and the corresponding golden pixel, wherein each respective golden matching pixel and golden pixel of a golden image is a pixel of an image representing a defect-free object.
8. The system according to claim 7 wherein the processor is adapted to search for multiple pixels of the second image that have neighborhoods that match a neighborhood of the second pixel.
9. The system according to claim 8 wherein the processor is adapted to repeat the searching for multiple tested pixels and generate statistics representative of a number of pixels found during the searching.
10. The system according to claim 7 wherein the processor is adapted to identify defects in the object based on the comparison.