US 12,266,143 B2
Salient feature point based image alignment
Chaohong Wu, Fremont, CA (US); Songyang Yu, Milpitas, CA (US); and Premchandra M. Shankar, Fremont, CA (US)
Assigned to KLA Corporation, Milpitas, CA (US)
Filed by KLA Corporation, Milpitas, CA (US)
Filed on Feb. 21, 2022, as Appl. No. 17/676,772.
Claims priority of provisional application 63/173,502, filed on Apr. 12, 2021.
Prior Publication US 2022/0327796 A1, Oct. 13, 2022
Int. Cl. G06V 10/24 (2022.01); G06T 7/33 (2017.01); G06V 10/22 (2022.01)
CPC G06V 10/24 (2022.01) [G06T 7/337 (2017.01); G06V 10/22 (2022.01); G06T 2207/10061 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A system configured for image alignment, comprising:
an imaging subsystem configured to generate a test image of a specimen, wherein the imaging subsystem comprises an energy source configured to generate energy directed to the specimen by the imaging subsystem and a detector configured to detect energy from the specimen and to generate output responsive to the detected energy, wherein the imaging subsystem is further configured to generate the test image from the output generated by the detector, and wherein the specimen comprises a wafer or a reticle; and
a computer subsystem configured for:
selecting three or more salient feature points for use in test image to reference image alignment by applying a selected salient feature point detection method to at least a reference image generated for the specimen, wherein the selected three or more salient feature points are shift and rotation invariant because the selected salient feature point detection method is shift and rotation invariant;
detecting the three or more salient feature points in the test image and the reference image;
aligning the detected three or more salient feature points in the test image to the detected three or more salient feature points in the reference image;
aligning remaining portions of the test image to remaining portions of the reference image based on results of aligning the detected three or more salient feature points in the test image to the detected three or more salient feature points in the reference image; and
after aligning the remaining portions of the test image to the remaining portions of the reference image, detecting defects in the test image by subtracting the reference image from the test image.