Method of defect detection on a specimen and system thereof

A computerized method of defect detection on a specimen, the method performed by a processing unit operatively connected to an examination tool, the processing unit comprising a memory and a processor operatively coupled thereto, the method comprising:

• performing partitioning for each portion of one or more portions of a first die of a specimen, wherein the partitioning for a given portion of the one or more portions is performed based on at least one of:
• i) image data characterizing the given portion, thereby giving rise to a plurality of regions in image space, and ii) design data characterizing the given portion, thereby giving rise to a plurality of regions in design space;
• receiving, from the examination tool, in runtime, one or more noise maps indicative of noise distribution on one or more second images captured for one or more portions of a second die of the specimen, the first die and the second die characterized by same design data;
• and
• performing segmentation for each of the one or more noise maps in runtime, wherein the segmentation for a given noise map of the one or more noise maps is performed by:
• calculating a score for each region of the plurality of regions, wherein the given noise map is aligned with the plurality of regions and each region thereof is associated with noise data aligned therein, and wherein the score for a given region of the plurality of regions is calculated at least based on the noise data associated therewith;
• and
• associating each region with one segmentation label of a predefined set of segmentation labels indicative of different noise levels based on the calculated score, thereby obtaining a set of segments each corresponding to one or more regions associated with the same segmentation label;
• wherein the set of segments are usable for defect detection on the specimen based on the given noise map.

A non-transitory computer readable storage medium tangibly embodying a program of instructions that, when executed by a computer, cause the computer to perform a method of defect detection on a specimen, the method comprising:

• performing partitioning for each portion of one or more portions of a first die of the specimen, wherein the partitioning for a given portion of the one or more portions is performed based on at least one of:
• i) image data characterizing the given portion, thereby giving rise to a plurality of regions in image space, and ii) design data characterizing the given portion, thereby giving rise to a plurality of regions in design space;
• receiving, in runtime, one or more noise maps indicative of noise distribution on one or more second images captured for one or more portions of a second die of the specimen, the first die and the second die characterized by the same design data;
• and
• performing segmentation for each of the one or more noise maps in runtime, wherein the segmentation for a given noise map of the one or more noise maps is performed by:
• calculating a score for each region of the plurality of regions, wherein the given noise map is aligned with the plurality of regions and each region thereof is associated with noise data aligned therein, and wherein the score for a given region of the plurality of regions is calculated at least based on the noise data associated therewith;
• and
• associating each region with one segmentation label of a predefined set of segmentation labels indicative of different noise levels based on the calculated score, thereby obtaining a set of segments each corresponding to one or more regions associated with the same segmentation label;
• wherein the set of segments are usable for the defect detection on the specimen based on the given noise map.