# US 2017/0287128 A1 · Adaptive Local Threshold and Color Filtering > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0287128 A1 - Document ID: US20170287128A1 - Status: Published application - Kind: A1 - Application number: 15/624,649 - Filed: 2017-06-15 - Published: 2017-10-05 - Earliest claimed: 2013-08-08 - Assignees: KLA-Tencor Corporation - Applicants: KLA-Tencor Corporation - Inventors: Junqing Huang; Hucheng Lee; Kenong Wu; Lisheng Gao - Web page: https://patentgrep.com/patent/US20170287128A1 ## CPC - G06T 7/0008: {checking presence/absence} - G06T 7/0006: {using a design-rule based approach} - G06T 7/90: Determination of colour characteristics - G06T 2207/10024: Color image - G06T 2207/20024: Filtering details - G06T 2207/20076: Probabilistic image processing - G06T 2207/30148: Semiconductor; IC; Wafer - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Methods and systems for detecting defects on a wafer using adaptive local thresholding and color filtering are provided. One method includes determining local statistics of pixels in output for a wafer generated using an inspection system, determining which of the pixels are outliers based on the local statistics, and comparing the outliers to the pixels surrounding the outliers to identify the outliers that do not belong to a cluster of outliers as defect candidates, The method also includes determining a value for a difference in color between the pixels of the defect candidates and the pixels surrounding the defect candidates. The method further includes identifying the defect candidates that have a value for the difference in color greater than or equal to a predetermined value as nuisance defects and the defect candidates that have a value for the difference in color less than the predetermined value as real defects, ## Claims ### Claim 1 A system configured to detect defects on a wafer, comprising: an optical subsystem configured to direct light to a wafer and detect light from the wafer to thereby generate output for the wafer; and a computer subsystem configured for: to determining local statistics of pixels in the output for the wafer; determining which of the pixels are outliers based on the local statistics; comparing the outliers to the pixels surrounding the outliers to identify the outliers that do not belong to a cluster of outliers as defect candidates and to further identify the outliers that belong to a cluster of outliers as local color nuisances; determining a value for a difference in color between the pixels of the defect candidates and the pixels surrounding the defect candidates; identifying the defect candidates that have a value for the difference in the color that is greater than or equal to a predetermined value as nuisance defects; and identifying the defect candidates that have a value for the difference in the color that is less than the predetermined value as real defects. ### Claim 2 (depends on 1) The system of claim 1, wherein the output for which the local statistics are determined comprises output generated with multiple angles of incidence. ### Claim 3 (depends on 1) The system of claim 1, wherein the output for which the local statistics are determined comprises output generated with multiple channels of the optical subsystem. ### Claim 4 (depends on 1) The system of claim 1, wherein the output for which the local statistics are determined comprises output responsive to specularly reflected light from the wafer and output responsive to scattered light from the wafer. ### Claim 5 (depends on 1) The system of claim 1, wherein the local statistics comprise one or more local statistics of difference values for the pixels. ### Claim 6 (depends on 1) The system of claim 1, wherein the local statistics comprise one or more local statistics of difference values for the pixels, and wherein the difference values are determined by subtracting a characteristic of the pixels in the output for a reference structure on the wafer from the characteristic of their corresponding pixels in the output for a test structure on the wafer. ### Claim 7 (depends on 1) The system of claim 1, wherein the local statistics comprise one or more local statistics of difference values for the pixels, and Wherein the difference values are determined based on intensity of the pixels. ### Claim 8 (depends on 1) The system of claim 1, wherein the local statistics are determined across fewer than all of the pixels in a frame image of the output. ### Claim 9 (depends on 1) The system of claim 1, wherein determining which of the pixels are the outliers comprises determining a local threshold for one pixel based on its local statistics, comparing a value of the local statistics for the one pixel to the local threshold, and determining if the one pixel is an outlier if the value of the local statistics for the one pixel is greater than the local threshold. ### Claim 10 (depends on 1) The system of claim 1, wherein the local statistics of the pixels comprise a local two-dimensional scatter plot. ### Claim 11 (depends on 1) The system of claim 1, wherein determining which of the pixels are outliers is performed based on the local statistics in combination with a local two-dimensional scatter plot generated for the pixels. ### Claim 12 (depends on 1) The system of claim 1, wherein determining the local statistics, determining which of the pixels are the outliers, and comparing the outliers are performed in a detecting phase of inspection of the wafer. ### Claim 13 (depends on 1) The system of claim 1, wherein determining the value for the difference in the color, identifying the defect candidates as the nuisance defects, and identifying the defect candidates as the real defects are performed in a filtering phase of inspection of the wafer. ### Claim 14 (depends on 13) The system of claim 13, wherein the filtering phase does not comprise identifying the nuisance defects and the real defects based on energy parameters of the defect candidates. ### Claim 15 (depends on 13) The system of claim 13, wherein the filtering phase does not comprise identifying the nuisance defects and the real defects based on size of the defect candidates. ### Claim 16 (depends on 1) The system of claim 1, wherein the computer subsystem is further configured for eliminating one or more of the defect candidates prior to determining the value for the difference in the color based on one or more characteristics of the pixels of the defect candidates. ### Claim 17 (depends on 16) The system of claim 16, wherein the one or more characteristics of the pixels comprise polarity. ### Claim 18 (depends on 1) The system of claim 1, wherein the wafer has one or more local process variations that result in one or more local differences in color. ### Claim 19 (depends on 1) The system of claim 1, wherein the wafer has one or more local process variations that span an area on the wafer that is smaller than an area of the wafer corresponding to a frame image in the output. ### Claim 20 (depends on 1) The system of claim 1, wherein the wafer has one or more global process variations that result in one or more global differences in color from other wafers of the same type at the same point in a tabrication process as the wafer. ### Claim 21 A computer-implemented method for detecting defects on a wafer, comprising: determining local statistics of pixels in output for a wafer generated using an inspection system; determining which of the pixels are outliers based on the local statistics; comparing the outliers to the pixels surrounding the outliers to identify the outliers that do not belong to a cluster of outliers as defect candidates and to further identify the outliers that belong to a cluster of outliers as local color nuisances; determining a value for a difference in color between the pixels of the defect candidates and the pixels surrounding the defect candidates; identifying the defect candidates that have a value for the difference in the color that is greater than or equal to a predetermined value as nuisance defects; and identifying the defect candidates that have a value for the difference in the color that is less than the predetermined value as real defects, wherein determining the local statistics, determining which of the pixels are the outliers, comparing the outliers, determining the value for the difference in the color, identifying the defect candidates as the nuisance defects, and identifying the defect candidates as the real defects are performed by a computer system. ### Claim 22 A non-transitory computer-readable medium, storing program instructions executable on a computer system for performing a computer-implemented method for detecting defects on a wafer, wherein the computer-implemented method comprises: determining local statistics of pixels in output for a wafer generated using an inspection system; determining which of the pixels are outliers based on the local statistics; comparing the outliers to the pixels surrounding the outliers to identify the outliers that do not belong to a cluster of outliers as defect candidates and to further identify the outliers that belong to a cluster of outliers as local color nuisances; determining a value for a difference in color between the pixels of the defect candidates and the pixels surrounding the defect candidates; identifying the defect candidates that have a value for the difference in the color that is greater than or equal to a predetermined value as nuisance defects; and identifying the defect candidates that have a value for the difference in the color that is less than the predetermined value as real defects.