Abstract: There is provided a system and method of defect examination on a semiconductor specimen. The method comprises obtaining an input image indicative of difference between an inspection image of the specimen and a corresponding reference image; and processing the input image using a trained machine learning (ML) system, to generate an output image representative of a defect map indicative of distribution of defect of interest (DOI) candidates in the input image. The ML system comprises a plurality of ML models operatively connected therebetween and previously trained together to perform defect detection on the input image based on Fourier transform. The output image is usable for further defect examination.

Abstract: In an example, two images of a printed calibration image are acquired using two measurement devices. The measurement devices are offset along an axis so that the two images correspond to two portions of the printed calibration image overlapping along the axis. The printed calibration image comprises a pattern extending across the printed calibration image in the direction of the axis, the pattern defining a shape so that in each image, a portion of the pattern appears as different from a straight line parallel to the axis. The two images are aligned using the two portions of pattern.

Abstract: In an example, two images of a printed calibration image are acquired using two measurement devices. The measurement devices are offset along an axis so that the two images correspond to two portions of the printed calibration image overlapping along the axis. The printed calibration image comprises a pattern extending across the printed calibration image in the direction of the axis, the pattern defining a shape so that in each image, a portion of the pattern appears as different from a straight line parallel to the axis. The two images are aligned using the two portions of pattern.