Artificial Intelligence Enabled Metrology

Abstract

Methods and systems for implementing artificial intelligence enabled metrology are disclosed. An example method includes segmenting a first image of structure into one or more classes to form an at least partially segmented image, associating at least one class of the at least partially segmented image with a second image, and performing metrology on the second image based on the association with at least one class of the at least partially segmented image.

What is claimed is: 
     
         1 . A method comprising:
 segmenting a first image of structure into one or more classes to form an at least partially segmented image;   associating at least one class of the at least partially segmented image with a second image; and   performing metrology on the second image based on the association with at least one class of the at least partially segmented image.   
     
     
         2 . The method of  claim 1 , wherein associating at least one class of the at least partially segmented image with the second image includes associating on a pixel by pixel basis the at least one class of the segmented image with the second image. 
     
     
         3 . The method of  claim 2 , wherein the at least one class is a key points class that designates key features of structure included in the second image. 
     
     
         4 . The method of  claim 2 , wherein performing metrology on the second image based on the association of at least one class of the at least partially segmented image includes placing an edge finder on the second image based on the location of the at least one class. 
     
     
         5 . The method of  claim 1 , wherein segmenting a first image into one or more classes includes classifying each pixel of the first image as belonging to one or more classes of a plurality of classes. 
     
     
         6 . The method of  claim 5 , wherein the plurality of classes comprises a structure body, a structure boundary, and key points, wherein the key points indicate key features of the structure for a basis of metrology. 
     
     
         7 . The method of  claim 5 , wherein classifying each pixel of the first image as belonging to one or more classes of a plurality of classes is performed by a single convolutional neural network. 
     
     
         8 . The method of  claim 5 , wherein classifying each pixel of the first image as belonging to one or more classes of a plurality of classes comprises:
 classifying the pixels of the input image into a key points class by a first convolutional neural network; and   classifying the pixels of the input image into a remainder of classes of the plurality of classes by a second convolutional neural network.   
     
     
         9 . The method of  claim 1 , wherein performing metrology on the second image based on the association of at least one class of the segmented image includes placing boundary locating analytics on the first image based on the location of the at least one class. 
     
     
         10 . The method of  claim 9 , wherein the boundary locating analytics is selected from one of an edge finder algorithm, an active contour algorithm, and an image recognition algorithm. 
     
     
         11 . The method of  claim 1 , wherein the first and second images are the same image. 
     
     
         12 . The method of  claim 1 , wherein the first and second images are separate, registered images of the same structure. 
     
     
         13 . A charged particle microscope system for performing metrology on obtained images, the system comprising:
 an imaging platform to obtain one or more images of part of a sample, each of the one or more images including structure;   a controller coupled to the imaging platform to at least perform metrology on the structure in at least one of the images, the controller, coupled to or including non-transitory, computer readable medium including code, that when executed by one or more cores, causes the controller to:
 segment a first image of the one or more images of structure into one or more classes to form a segmented image; 
 associate at least one class of the segmented image with a second image of the one or more images of the structure; and 
 perform metrology on the second image of the structure based on the association of at least one class of the segmented image. 
   
     
     
         14 . The system of  claim 13 , wherein the code, that when executed, causes the controller to associate at least one class of the segmented image with the second image further includes code that causes the controller to associate on a pixel by pixel basis the at last one class of the segmented image with the second image. 
     
     
         15 . The system of  claim 14 , wherein the at least one class is a key points class that designates key features of structure included in the first image. 
     
     
         16 . The system of  claim 13 , wherein the code, that when executed, causes the controller to segment the first image of structure into one or more classes further includes code that causes the controller to classify each pixel of the first image of the structure as belonging to one or more classes of a plurality of classes. 
     
     
         17 . The system of  claim 16 , wherein the plurality of classes comprises a structure body, a structure boundary, and key points, wherein the key points indicate key features of the structure for a basis of metrology. 
     
     
         18 . The system of  claim 16 , wherein the classification of the first image of the structure as belonging to one or more classes of a plurality of classes is performed by a convolutional neural network, the convolutional neural network either being executed by the controller or a separate computing device coupled to the system. 
     
     
         19 . The system of  claim 16 , wherein the code, that when executed, causes the controller to classify each pixel of the first image of the structure as belonging to one or more classes of a plurality of classes further includes code that, when executed, causes the controller to:
 classify the pixels of the first image of the structure into a key points class by a first convolutional neural network; and   classify the pixels of the first image of the structure into a remainder of classes of the plurality of classes by a second convolutional neural network.   
     
     
         20 . The system of  claim 13 , wherein the code, that when executed, causes the controller to perform metrology on the second image of the structure based on the association of at least one class of the segmented image further includes code that causes the controller to place edge finders on the second image based on the location of the at least one class. 
     
     
         21 . The system of  claim 20 , wherein the code, that when executed, causes the controller to place edge finders on the second image based on the location of the at least one class further includes code that causes the controller to establish an area on the second image of the structure based on the location of the at least one class, and further includes code to analyze the second image of the structure inside the area to determine a boundary of the structure within the area. 
     
     
         22 . The system of  claim 21 , wherein the determined boundary forms an anchor point for measuring at least a portion of the structure. 
     
     
         23 . The system of  claim 13 , wherein the first and second images are the same image. 
     
     
         24 . The system of  claim 13 , wherein the first and second images are separate, registered images.