Region classification of film non-uniformity based on processing of substrate images
A method of classification of a film non-uniformity on a substrate includes obtaining a color image of a substrate with the color image comprising a plurality of color channels, obtaining a standard color for the color image of the substrate, for each respective pixel along a path in the color image determining a difference vector between the a color of the respective pixel and the standard color to generate a sequence of difference vectors, sorting the pixels along the path into a plurality of regions including at least one normal region and at least one abnormal region based on the sequence of difference vectors, and classifying the at least one abnormal region as overpolished or underpolished based on at least one difference vector of a pixel at a boundary between the abnormal region and an adjacent normal region.
1. A non-transitory computer readable medium comprising a computer program to classify a film non-uniformity on a substrate, the computer program including instructions to cause one or more computers to:
obtain a color image of a substrate, the color image comprising a plurality of color channels;
obtain a uniform color value for the color image of the substrate;
for each respective pixel along a path in the color image, determine a difference vector between a color of the respective pixel and the uniform color value to generate a sequence of difference vectors; and
classify the pixels along the path as normal or abnormal based on the sequence of difference vectors;
group the pixels into one or more regions in response to the pixels being identified as normal or abnormal; and
classify a region having abnormal pixels as overpolished or underpolished based on at least one difference vector using only a pixel at a boundary between the region having abnormal pixels and an adjacent region having normal pixels and not a pixel that is not at the boundary.
2. The computer readable medium of claim 1 , comprising instructions to classify the region having abnormal pixels as overpolished or underpolished based on a multiplicity of difference vectors for each of a multiplicity of successive pixels along the path at the boundary.
3. The computer readable medium of claim 2 , wherein the multiplicity of successive pixels is no more than 5 pixels.
4. The computer readable medium of claim 2 , comprising instructions to classify the region having abnormal pixels as overpolished or underpolished based on each of the multiplicity of difference vectors meeting a criterion.
5. The computer readable medium of claim 2 , wherein the instructions to classify the region having abnormal pixels as overpolished or underpolished include instructions to calculate a factor based on a ratio of difference values in two color channels.
6. The computer readable medium of claim 5 , wherein the instructions to calculate the factor include instructions to calculate a sum of a first ratio of difference values in a first two color channels and a second ratio of difference values in a second two color channels.
7. The computer readable medium of claim 5 , wherein the instructions to classify the region having abnormal pixels as overpolished or underpolished regions include instructions to compare the factor to at least a first threshold value.
8. The computer readable medium of claim 7 , comprising instructions to classify the region having abnormal pixels as underpolished in response to determining that the factor exceeds the first threshold value.
9. The computer readable medium of claim 7 , comprising instructions to classify the region having abnormal pixels as overpolished in response to determining that the factor does not exceed a second threshold value, the second threshold value being different than the first threshold value.
10. The computer readable medium of claim 6 , wherein the first two color channels are green and red and the second two color channels are blue and red.
11. The computer readable medium of claim 1 , comprising instructions to determine a severity of the region having abnormal pixels based on the multiplicity of the difference vectors.
12. The computer readable medium of claim 11 , wherein determining the severity comprises determining a minimum bounding region containing the difference vectors for the pixels in the region having abnormal pixels in a color space at least two of the color channels, and comparing an area of the bounding region to a third threshold value, the third threshold value.
13. The computer readable medium of claim 12 , wherein the minimum bounding region comprises a rectangle.
14. A method of classification of a film non-uniformity on a substrate, comprising:
obtaining a color image of a substrate, the color image comprising a plurality of color channels;
obtaining a uniform color value for the color image of the substrate;
for each respective pixel along a path in the color image, determining a difference vector between a color of the respective pixel and the uniform color value to generate a sequence of difference vectors;
grouping the pixels along the path into a plurality of regions including at least one normal region and at least one abnormal region based on the sequence of difference vectors; and
classifying the at least one abnormal region as overpolished or underpolished based on at least one difference vector using only a pixel at a boundary between the region having abnormal pixels and an adjacent region having normal pixels and not a pixel that is not at the boundary.
15. The method of claim 14 , wherein obtaining the color image includes scanning the substrate with an in-line metrology system including a line-scan imager.
16. A polishing system, comprising:
a polisher to polish a substrate;
an in-line metrology system to obtain to color image of a substrate, the color image comprising a plurality of color channels; and
a controller configured to
receive obtain the color image from the in-line metrology system,
obtaining a uniform color value for the color image of the substrate,
for each respective pixel along a path in the color image, determine a difference vector between a color of the respective pixel and the uniform color value to generate a sequence of difference vectors,
classify the pixels along the path as normal or abnormal based on the sequence of difference vectors,
group the pixels into one or more regions in response to the pixels being identified as normal or abnormal,
classify a region having abnormal pixels as overpolished or underpolished based on at least one difference vector using only a pixel at a boundary between the region having abnormal pixels and an adjacent region having normal pixels and not a pixel that is not at the boundary, and
adjust a polishing parameter of the polisher for a region having pixels identified as abnormal based on the region being classified as overpolished or underpolished.
17. The polishing system of claim 16 , wherein the controller is configured to classify the region as overpolished or underpolished based a multiplicity of difference vectors for each of a multiplicity of successive pixels along the path at the boundary.
18. The polishing system of claim 17 , wherein the controller is configure to classify the region as overpolished or underpolished based on each of the multiplicity of difference vectors meeting a criterion.
19. The polishing system of claim 16 , wherein the controller is configured to determine a severity of the region having abnormal pixels based on the multiplicity of the difference vectors.
20. The polishing system of claim 19 , wherein the controller is configured to determine the severity by determining a minimum bounding region containing the difference vectors for the pixels in the region having abnormal pixels in a color space at least two of the color channels, and comparing an area of the bounding region to a fifth threshold value.