# US 10,504,693 B2 · Evaluating an object > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,504,693 B2 - Document ID: US10504693B2 - Status: Granted - Kind: B2 - Application number: 16/131,289 - Filed: 2018-09-14 - Published: 2019-03-21 - Granted: 2019-12-10 - Earliest claimed: 2017-09-18 - Assignees: Applied Materials Israel Ltd. - Applicants: Applied Materials Israel Ltd. - Inventors: Shay Attal; Shaul Cohen; Guy Maoz; Noam Zac; Mor Baram; Lee Moldovan; Ishai Schwarzband; Ron Katzir; Kfir Ben-Zikri; Doron Girmonsky - Web page: https://patentgrep.com/patent/US10504693B2 ## CPC - H01J 37/244: Detectors; Associated components or circuits therefor - G01B 15/02: for measuring thickness - G01B 15/04: for measuring contours or curvatures - H01J 37/222: {Image processing arrangements associated with the tube} - H01J 37/29: Reflection microscopes - G01B 2210/56: Measuring geometric parameters of semiconductor structures, e.g. profile, critical dimensions or trench depth - H01J 2237/24475: Scattered electron detectors - H01J 2237/24578: Spatial variables, e.g. position, distance - H01J 2237/24592: Inspection and quality control of devices - H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H) - G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS ## Abstract A method for evaluating an object, the method may include acquiring, by a charged particle beam system, an image of an area of a reference object, wherein the area includes multiple instances of a structure of interest, and the structure of interest is of a nanometric scale; determining multiple types of attributes from the image; reducing a number of the attributes to provide reduced attribute information; generating guidelines, based on the reduced attribute information and on reference data, for evaluating the reduced attribute information; and evaluating an actual object by implementing the guidelines. ## Claims ### Claim 1 A method for evaluating an object, the method comprising: acquiring, by a charged particle beam system, an image of an area of a reference object, wherein the area comprises multiple instances of a structure of interest, and the structure of interest is of a nanometric scale; determining multiple types of attributes from the image; reducing a number of the attributes to provide reduced attribute information; generating guidelines, based on the reduced attribute information and on reference data, for evaluating the reduced attribute information; and evaluating an actual object by implementing the guidelines. ### Claim 2 (depends on 1) The method according to claim 1, wherein a resolution of the image is at least one hundred times finer than a resolution of the reference data. ### Claim 3 (depends on 1) The method according to claim 1, wherein the image is a backscattered electron image of nanometric scale resolution. ### Claim 4 (depends on 3) The method according to claim 3, wherein acquiring the image comprises collecting backscattered electrons by a backscattered electron detector that has a radial angular coverage range of tens of degrees. ### Claim 5 (depends on 4) The method according to claim 4, wherein acquiring the image comprises rejecting secondary electrons by an energy filter that precedes the backscattered electron detector. ### Claim 6 (depends on 1) The method according to claim 1, wherein the multiple instances of the structure of interest are positioned in recesses having an aspect ratio that exceeds ten, and wherein acquiring the image comprises scanning the area with a charged particle beam having a focal plane at a height related to a height of the multiple instances of the structure of interest. ### Claim 7 (depends on 1) The method according to claim 1, wherein generating the guidelines comprises training a neural network to output data that approximates the reference data when fed with the reduced attribute information. ### Claim 8 (depends on 1) The method according to claim 1, wherein reducing the number of attributes comprises utilizing a neural network. ### Claim 9 (depends on 1) The method according to claim 1, wherein reducing the number of attributes comprises training a neural network to output data that approximates the reference data regarding a reference object when fed with the reduced attribute information about the reference object, while attempting to reduce the number of attributes that are taken into account during an approximation of the reference data. ### Claim 10 (depends on 9) The method according to claim 9, wherein training the neural network comprises calculating a cost function related to the number of attributes of the reduced attribute information that are taken into account during the approximation of the reference data. ### Claim 11 A nontransitory computer program product that stores instructions for evaluating an object, the instructions comprising the steps of: acquiring an image of an area of a reference object; wherein the area comprises multiple instances of a structure of interest, and the structure of interest is of a nanometric scale; determining multiple types of attributes from the image; reducing a number of the attributes to provide reduced attribute information; generating guidelines, based on the reduced attribute information and on reference data, for evaluating the reduced attribute information; and evaluating an actual object by implementing the guidelines. ### Claim 12 A method for measuring depths and/or heights of structures on a substrate, the method comprising: acquiring, by a charged particle beam system, a backscattered electron image of an area of a reference object, wherein the area comprises multiple instances of a structure of interest, the structure of interest is positioned in a recess having an aspect ratio that exceeds ten, and the structure of interest is of a nanometric scale; determining multiple types of attributes from the image; reducing a number of the attributes to provide reduced attribute information; generating guidelines, based on the reduced attribute information and on reference data, for evaluating the reduced attribute information, wherein generating the guidelines includes training a neural network to output data that approximates the reference data when fed with the reduced attribute information; and evaluating an actual object by implementing the guidelines. ### Claim 13 (depends on 12) The method according to claim 12, wherein a resolution of the image is at least one hundred times finer than a resolution of the reference data. ### Claim 14 (depends on 12) The method according to claim 12, wherein acquiring the backscattered electron image includes collecting backscattered electrons by a backscattered electron detector that has a radial angular coverage range of tens of degrees. ### Claim 15 (depends on 14) The method according to claim 14, wherein acquiring the backscattered electron image includes rejecting secondary electrons using an energy filter that precedes the backscattered electron detector.