Automatic defect classification

Abstract

A method for automatic defect classification, the method may include acquiring, by a first camera, at least one first image of at least one area of an object; processing the at least one first image to detect a group of suspected defects within the at least one area; performing a first classification process for initially classifying the group of suspected defects; determining whether a completion of a classification of the first subgroup of the suspected defects requires additional information from a second camera; when determining that the first subgroup of the suspected defects requires additional information from the second camera then: acquiring second images, by the second camera while applying image acquisition parameters of the second camera, to provide the additional information; and performing the second classification process for classifying the first subgroup of suspected defects.

1 . A method for automatic defect classification, the method comprises:
 acquiring, by a first camera, at least one first image of at least one area of an object;   processing the at least one first image to detect a group of suspected defects within the at least one area;   performing a first classification process for initially classifying the group of suspected defects;   determining whether a completion of a classification of the first subgroup of the suspected defects requires additional information from a second camera;   wherein the determining is responsive to:   (a) a criticality of the suspected defects;   (b) an accuracy of the first classification process; and   (c) difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process; wherein the reliability is reflected by a success rate, a false alarm rate and false positive rate;   when determining that the first subgroup of the suspected defects requires additional information from the second camera then:
 acquiring second images, by the second camera while applying image acquisition parameters of the second camera, to provide the additional information; and 
 performing the second classification process for classifying the first subgroup of suspected defects. 
   
     
     
         2 . The method according to  claim 1  comprising acquiring the second images without acquiring images of suspected defects that do not belong to the first subgroup of suspected defects. 
     
     
         3 . The method according to  claim 1  wherein a throughput of the first camera exceeds a throughput of the second camera. 
     
     
         4 . The method according to  claim 1  wherein a resolution of the first camera is coarser than resolution of the second camera. 
     
     
         5 . The method according to  claim 1  wherein the first camera is a black and white camera and the second camera is selected out of an infrared camera, a near infrared camera and a three dimension profiler. 
     
     
         6 . The method according to  claim 1  comprising maintaining the wafer on a chuck during the acquiring of the at least one first image, during the acquiring of the second images, and between the acquiring of the at least one first image and the acquiring of the second images. 
     
     
         7 . The method according to  claim 1  wherein the second images are of the first group of the suspected defects. 
     
     
         8 . The method according to  claim 1  wherein the second images are of items that differ from the first group of the suspected defects. 
     
     
         9 . The method according to  claim 1  wherein the determining is executed without human intervention. 
     
     
         10 . A non-transitory computer program product that stores instructions that once executed by a computerized system cause the computerized system to execute the steps of:
 acquiring, by a first camera, at least one first image of at least one area of an object;   processing the at least one first image to detect a group of suspected defects within the at least one area;   performing a first classification process for initially classifying the group of suspected defects;   determining whether a completion of a classification of the first subgroup of the suspected defects requires additional information from a second camera;   wherein the determining is responsive to:   (a) a criticality of the suspected defects;   (b) an accuracy of the first classification process; and   (c) difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process; wherein the reliability is reflected by a success rate, a false alarm rate and false positive rate;   when determining that the first subgroup of the suspected defects requires additional information from the second camera then:
 acquiring second images, by the second camera while applying image acquisition parameters of the second camera, to provide the additional information; and 
 performing the second classification process for classifying the first subgroup of suspected defects The non-transitory computer readable medium according to  claim 12  that stores instructions for acquiring the second images without acquiring images of suspected defects that do not belong to the first subgroup of suspected defects. 
   
     
     
         11 . The non-transitory computer readable medium according to  claim 10  wherein a throughput of the first camera exceeds a throughput of the second camera. 
     
     
         12 . The non-transitory computer readable medium according to  claim 10  wherein a resolution of the first camera is coarser than resolution of the second camera. 
     
     
         13 . The non-transitory computer readable medium according to  claim 10  wherein the first camera is a black and white camera and the second camera is selected out of an infrared camera, a near infrared camera and a three dimension profiler. 
     
     
         14 . The non-transitory computer readable medium according to  claim 10  that stores instructions for maintaining the wafer on a chuck during the acquiring of the at least one first image, during the acquiring of the second images, and between the acquiring of the at least one first image and the acquiring of the second images. 
     
     
         15 . The non-transitory computer readable medium according to  claim 10  wherein the second images are of the first group of the suspected defects. 
     
     
         16 . The non-transitory computer readable medium according to  claim 10  wherein the second images are of items that differ from the first group of the suspected defects. 
     
     
         17 . The non-transitory computer readable medium according to  claim 10  wherein the determining is executed without human intervention. 
     
     
         18 . The non-transitory computer readable medium according to  claim 10  wherein the determining is responsive to difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process. 
     
     
         19 . A system for automatic defect classification, the system comprises:
 a first camera that is constructed and arranged to acquire at least one first image of at least one area of an object;   a second camera;   at least one processor that is constructed and arranged to (i) process the at least one first image to detect a group of suspected defects within the at least one area; (ii) perform a first classification process for initially classifying the group of suspected defects; and (iii) determine whether a completion of a classification of the first subgroup of the suspected defects requires additional information from a second camera;   wherein the determining is responsive to:   (a) a criticality of the suspected defects;   (b) an accuracy of the first classification process;   (c) difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process; wherein the reliability is reflected by a success rate, a false alarm rate and false positive rate;   when determining that the first subgroup of the suspected defects requires additional information from the second camera then:   acquiring second images, by the second camera while applying image acquisition parameters of the second camera, to provide the additional information; and   performing a second classification process for classifying the first subgroup of suspected defects.