Detection of defects embedded in noise for inspection in semiconductor manufacturing
One embodiment relates to an apparatus for detecting defects on a manufactured substrate. The apparatus includes an imaging tool arranged to obtain image frames from the manufactured substrate. The apparatus further includes a data processing system which includes computer-readable code configured to compute features for pixels in an image frame and divide the pixels in the image frame into feature-defined groups of pixels. The computer-readable code is further configured to select a feature-defined group, and generate a multi-dimensional feature distribution for the selected feature-defined group. Another embodiment relates to a method of detecting defects from a test images frame and multiple reference image frames. Other embodiments, aspects, and features are also disclosed.
1. An apparatus for detecting defects on a manufactured substrate, the apparatus comprising:
an imaging tool arranged to obtain image frames from the manufactured substrate; and
a data processing system including a processor, memory and computer-readable code in said memory, the computer-readable code being configured to
compute features for pixels in an image frame;
separate pixels in the image frame that have values of the features within specified ranges of values from other pixels in the image frame such that the separated pixels form a feature-defined group of pixels;
generate a multi-dimensional feature distribution for only the pixels in the image frame belonging to the feature-defined group of pixels;
determine a normal cluster in the multi-dimensional feature distribution; and
detect outlier points in the multi-dimensional feature distribution which are outside the normal cluster.
2. The apparatus of claim 1 , wherein the computer-readable code is further configured to locate defective pixels associated with the outlier points.
3. The apparatus of claim 2 , wherein the computer-readable code is further configured to report the defective pixels.
4. The apparatus of claim 1 , wherein the features include reference features, and wherein a reference feature is a property associated with a pixel location on multiple reference images.
5. The apparatus of claim 4 , wherein the features further include test features, and wherein a test feature is derived from a pixel location on a test image and the multiple reference images.
6. The apparatus of claim 4 , wherein the property comprises a range of gray levels at the pixel location.
7. The apparatus of claim 4 , wherein the property includes information from a local range of pixels centered at the pixel location.
8. A method of detecting defects from a test image frame and multiple reference image frames, the method comprising:
imaging, by an imaging apparatus, a local area of a manufactured substrate held on a movable substrate holder to generate the test image frame; and
using a data processing system including a processor, memory and computer-readable code in said memory to perform steps including:
computing features for pixels in the test image frame and the multiple reference image frames;
separate pixels in the image frame that have values of the features within specified ranges of values from other pixels in the image frame such that the separated pixels form a feature-defined group of pixels;
generating a multi-dimensional feature distribution for only the pixels belonging to the feature-defined group of pixels;
determining a normal cluster in the multi-dimensional feature distribution; and
detecting outlier points in the multi-dimensional feature distribution which are outside the normal cluster.
9. The method of claim 8 further comprising:
locating defective pixels associated with the outlier points.
10. The method of claim 9 further comprising:
flagging the defective pixels.
11. The method of claim 8 , wherein the features include reference features, and wherein a reference feature is a property associated with a pixel location on the multiple reference image frames.
12. The method of claim 11 , wherein the features further include test features, and wherein a test feature is derived from a pixel location on a test image frame and the multiple reference image frames.
13. The method of claim 11 , wherein the property comprises a range of gray levels at the pixel location.
14. The method of claim 11 , wherein the property includes information from a local range of pixels centered at the pixel location.
15. A non-transitory tangible data storage medium storing computer-readable code configured to perform a method comprising:
computing features for pixels in the test and reference image frames;
using the features computed for the pixels in the test image frame and the multiple reference image frames to separate pixels belonging to a feature-defined group of pixels from other pixels that do not belong to the feature-defined group of pixels;
generating a multi-dimensional feature distribution for only the pixels belonging to the feature-defined group of pixels;
determining a normal cluster in the multi-dimensional feature distribution; and
detecting outlier points in the multi-dimensional feature distribution which are outside the normal cluster.
16. The non-transitory tangible data storage medium of claim 15 , wherein the method further comprises:
locating defective pixels associated with the outlier points; and
flagging the defective pixels.