Defect detection
There may be provided a method for determining three dimensional (3D) defect information, the method may include performing a two-dimensional (2D) inspection of an area of a wafer to generate 2D defect information related to defects of the area of the wafer; estimating 3D defect information regarding the defects of the area of the wafer, wherein the estimating is based on the 2D defect information related to defects of the area of the wafer, and a mapping between 2D defect information and 3D defect information, wherein the mapping is generated using a supervised deep learning machine process.
1. A method for determining three dimensional (3D) defect information, the method comprises:
performing a two-dimensional (2D) inspection of an area of a wafer to generate 2D defect information related to defects of the area of the wafer;
estimating 3D defect information regarding the defects of the area of the wafer, wherein the estimating is based on (a) the 2D defect information related to defects of the area of the wafer, and (b) a mapping between 2D defect information and 3D defect information, wherein the mapping is generated using a supervised deep learning machine process.
2. The method according to claim 1 , comprising generating the mapping.
3. The method according to claim 2 , wherein the generating of the mapping comprises:
performing a 2D inspection of at least a portion of at least one wafer, to provide 2D inspection results;
performing a 3D inspection of the at least portion of the at least one wafer, to provide 3D inspection results; and
performing a supervised deep learning machine process based on the 2D inspection results and on the 3D inspection results, to provide the mapping;
wherein the 2D inspection results are inputs to the supervised deep learning machine process; wherein the 3D inspection results are desired outputs of the supervised deep learning machine process.
4. The method according to claim 3 wherein the 2D inspection results are defect location and boundaries; and wherein the 3D inspection comprises measuring 3D information at area located between boundaries of the defects.
5. The method according to claim 4 wherein the 3D inspection results are height distributions of at least the defects.
6. The method according to claim 2 wherein the performing of the 2D inspection of the at least portion of the at least one wafer with infrared and visual light beams.
7. The method according to claim 2 comprising performing the 3D inspection only on defects identified in the 2D inspection results.
8. The method according to claim 2 wherein the 3D information results are provided at a height bin resolution.
9. The method according to claim 2 wherein the performing of the supervised deep learning machine process comprises selecting a machine learning process model that represents the mapping out of multiple machine learning process models generated during the performing of the supervised deep learning machine process.
10. The method according to claim 1 wherein the performing of the 2D inspection comprises using at least one sensor selected out of a charged-coupled device (CCD) sensor, an area cameras, an inner crack imaging (ICI) camera, a line camera, time delay and integration (TDI) sensor, a sensor that includes an array of sensing elements, a black and white camera, a color camera.
11. A non-transitory computer readable medium for determining three dimensional (3D) defect information, (Original) The non-transitory computer readable medium stores instructions for:
performing a two-dimensional (2D) inspection of an area of a wafer to generate 2D defect information related to defects of the area of the wafer;
estimating 3D defect information regarding the defects of the area of the wafer, wherein the estimating is based on (a) the 2D defect information related to defects of the area of the wafer, and (b) a mapping between 2D defect information and 3D defect information, wherein the mapping is generated using a supervised deep learning machine process.
12. The non-transitory computer readable medium according to claim 11 , comprising generating the mapping.
13. The non-transitory computer readable medium according to claim 12 , wherein the generating of the mapping comprises:
performing a 2D inspection of at least a portion of at least one wafer, to provide 2D inspection results;
performing a 3D inspection of the at least portion of the at least one wafer, to provide 3D inspection results; and
performing a supervised deep learning machine process based on the 2D inspection results and on the 3D inspection results, to provide the mapping;
wherein the 2D inspection results are inputs to the supervised deep learning machine process; wherein the 3D inspection results are desired outputs of the supervised deep learning machine process.
14. The non-transitory computer readable medium according to claim 13 wherein the 2D inspection results are defect location and boundaries; and wherein the 3D inspection comprises measuring 3D information at the boundaries of the defects.
15. The non-transitory computer readable medium according to claim 14 wherein the 3D inspection results are height distributions of at least the boundaries of the defects.
16. The non-transitory computer readable medium according to claim 12 wherein the performing of the 2D inspection of the at least portion of the at least one wafer with infrared and visual light beams.
17. The non-transitory computer readable medium according to claim 12 comprising performing the 3D inspection only on defects identified in the 2D inspection results.
18. The non-transitory computer readable medium according to claim 12 wherein the 3D information results are provided at a height bin resolution.
19. The non-transitory computer readable medium according to claim 12 wherein the performing of the supervised deep learning machine process comprises selecting a machine learning process model that represents the mapping out of multiple machine learning process models generated during the performing of the supervised deep learning machine process.
20. An inspection system for determining three dimensional (3D) defect information, the inspection system comprises: a two-dimensional (2D) inspection unit that is configured to perform a 2D inspection of an area of a wafer to generate 2D defect information related to defects of the area of the wafer; a processor that is configured to estimate 3D defect information regarding the defects of the area of the wafer, wherein the estimating is based on (a) the 2D defect information related to defects of the area of the wafer, and (b) a mapping between 2D defect information and 3D defect information, wherein the mapping is generated using a supervised deep learning machine process.
21. The method according to claim 1 wherein the performing of the 2D inspection is executed without height measurement.
22. The non-transitory computer readable medium according to claim 12 wherein the performing of the 2D inspection is executed without height measurement.
23. The inspection system according to claim 20 wherein the 2D inspection unit is configured to perform the 2D inspection of the area of the wafer without height measurement.