# US 2018/0025485 A1 · Facilitating anomaly detection for a product having a pattern > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0025485 A1 - Document ID: US20180025485A1 - Status: Published application - Kind: A1 - Application number: 15/219,099 - Filed: 2016-07-25 - Published: 2018-01-25 - Earliest claimed: 2016-07-25 - Assignees: PT Papertech Inc. - Applicants: PT Papertech Inc. - Inventors: Juha REUNANEN - Web page: https://patentgrep.com/patent/US20180025485A1 ## CPC - G06T 7/0008: {checking presence/absence} - G06F 18/28: Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries - G06T 7/0004: {Industrial image inspection} - G06T 7/001: {using an image reference approach} - G06V 10/30: Noise filtering - G06V 10/443: {by matching or filtering} - G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching} - G06F 18/22: Matching criteria, e.g. proximity measures - G06T 2207/10004: Still image; Photographic image - G06T 2207/10024: Color image - G06T 2207/20076: Probabilistic image processing - G06T 2207/30124: Fabrics; Textile; Paper - G06T 2207/30161: Wood; Lumber - G06V 2201/06: Recognition of objects for industrial automation - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for facilitating detection of at least one anomaly in a representation of a product having a pattern is provided. The method involves causing at least one processor to receive image data representing the product during processing, identify from the image data generally similar images representing respective instances of a repeated aspect of the pattern, each of the images including image element values, generate a set of corresponding image element values including an image element value from each image, identify at least one image element value from the set of corresponding image element values to be excluded from a subset of the set of corresponding image element values, generate at least one criterion based on the subset, and cause the at least one criterion to be used to facilitate identification of the at least one anomaly. Other methods, apparatuses, systems, and computer readable media are also provided. ## Claims ### Claim 1 A method for facilitating detection of at least one anomaly in a representation of a product having a pattern, the method comprising: causing at least one processor to receive image data representing the product during processing of the product; causing the at least one processor to identify from the image data generally similar images representing respective instances of a repeated aspect of the pattern, each of the images including image element values; causing the at least one processor to generate a set of corresponding image element values, said set including an image element value from each of the images; causing the at least one processor to identify at least one image element value from the set of corresponding image element values to be excluded from a subset of the set of corresponding image element values; causing the at least one processor to generate at least one criterion based on the subset of the set of corresponding image element values; and causing the at least one processor to cause the at least one criterion to be used to facilitate identification of the at least one anomaly. ### Claim 2 (depends on 1) The method of claim 1 wherein causing the at least one processor to cause the at least one criterion to be used to facilitate identification of the at least one anomaly comprises: causing the at least one processor to receive image data representing a subject image representing at least a portion of an instance of the repeated aspect of the pattern; causing the at least one processor to apply the at least one criterion to a subject image element value of the subject image, the subject image element value corresponding to the subset of corresponding image element values. ### Claim 3 (depends on 2) The method of claim 2 wherein causing the at least one processor to generate the at least one criterion comprises causing the at least one processor to determine an upper limit value from the subset of the set of corresponding image element values and wherein causing the at least one processor to apply the at least one criterion comprises causing the at least one processor to compare the subject image element value to the upper limit value. ### Claim 4 (depends on 2) The method of claim 2 wherein causing the at least one processor to generate the at least one criterion comprises causing the at least one processor to determine a lower limit value from the subset of the set of corresponding image element values and wherein causing the at least one processor to apply the at least one criterion comprises causing the at least one processor to compare the subject image element value to the lower limit value. ### Claim 5 (depends on 2) The method of claim 2 wherein causing the at least one processor to generate the at least one criterion comprises causing the at least one processor to determine an upper limit value and a lower limit value from the subset of the set of corresponding image element values and wherein causing the at least one processor to apply the at least one criterion comprises causing the at least one processor to compare the subject image element value to the upper limit value and the lower limit value. ### Claim 6 (depends on 5) The method of claim 5 wherein causing the at least one processor to determine the upper limit value and the lower limit value comprises causing the at least one processor to set the upper limit value and the lower limit value to a greatest value and a lowest value respectively of the subset of the set of corresponding image element values. ### Claim 7 (depends on 5) The method of claim 5 wherein causing the at least one processor to determine the upper limit value and the lower limit value comprises causing the at least one processor to determine a standard deviation and a mean from the subset of the set of corresponding image element values and to derive the upper limit value and the lower limit value from the standard deviation and the mean. ### Claim 8 (depends on 5) The method of claim 5 wherein causing the at least one processor to cause the at least one criterion to be used to facilitate identification of the at least one anomaly comprises: causing the at least one processor to determine whether the subject image element value is greater than the upper limit or less than the lower limit; causing the at least one processor to, if the subject image element value is greater than the upper limit or less than the lower limit: generate a new image element value derived from the subject image element value and at least one of the upper limit and the lower limit; and generate a new image including the new image element value for inspection. ### Claim 9 (depends on 8) The method of claim 8 wherein causing the at least one processor to cause the at least one criterion to be used to facilitate identification of the at least one anomaly comprises causing the at least one processor to, if the subject image element value is not greater than the upper limit or less than the lower limit, generate the new image to include a neutral image element value. ### Claim 10 (depends on 8) The method of claim 8 further comprising causing the at least one processor to transmit signals representing the new image to an anomaly detector. ### Claim 11 (depends on 8) The method of claim 8 further comprising causing the at least one processor to inspect the new image to determine whether the new image element value is anomalous. ### Claim 12 (depends on 1) The method of claim 1 further comprising causing the at least one processor to produce signals for causing at least one display to display a representation of the at least one anomaly to a user. ### Claim 13 (depends on 1) The method of claim 1 wherein causing the at least one processor to identify the at least one image element value to be excluded from the subset comprises causing the at least one processor to identify at least one extreme image element value as the at least one image element value to be excluded. ### Claim 14 (depends on 13) The method of claim 13 wherein the set of corresponding image element values comprise pixel values and wherein causing the at least one processor to identify the at least one extreme image element value to be excluded comprises causing the at least one processor to identify at least one lowest pixel value of the pixel values to be excluded and at least one greatest pixel value of the pixel values to be excluded. ### Claim 15 (depends on 14) The method of claim 14 wherein causing the at least one processor to identify the at least one lowest pixel value and the at least one greatest pixel value comprises causing the at least one processor to identify a first percentage of the pixel values having lowest values as the at least one lowest pixel value and to identify a second percentage of the pixel values having greatest values as the at least one greatest pixel value. ### Claim 16 (depends on 15) The method of claim 15 wherein the first and second percentages are each between about 5% and about 15%. ### Claim 17 A system for facilitating detection of at least one anomaly in a representation of a product having a pattern, the system comprising: means for receiving image data representing the product during processing of the product; means for identifying from the image data generally similar images representing respective instances of a repeated aspect of the pattern, each of the images including image element values; means for generating a set of corresponding image element values, said set including an image element value from each of the images; means for identifying at least one image element value from the set of corresponding image element values to be excluded from a subset of the set of corresponding image element values; means for generating at least one criterion based on the subset of the set of corresponding image element values; and means for causing the at least one criterion to be used to facilitate identification of the at least one anomaly. ### Claim at position 18 18-32. (canceled) ### Claim 33 An apparatus for facilitating detection of at least one anomaly in a representation of a product having a pattern, the apparatus comprising at least one processor configured to: receive image data representing the product during processing of the product; identify from the image data generally similar images representing respective instances of a repeated aspect of the pattern, each of the images including image element values; generate a set of corresponding image element values, said set including an image element value from each of the images; identify at least one image element value from the set of corresponding image element values to be excluded from a subset of the set of corresponding image element values; generate at least one criterion based on the subset of the set of corresponding image element values; and cause the at least one criterion to be used to facilitate identification of the at least one anomaly. ### Claim 34 (depends on 33) The apparatus of claim 33 wherein the at least one processor is configured to: receive image data representing a subject image representing at least a portion of an instance of the repeated aspect of the pattern; apply the at least one criterion to a subject image element value of the subject image, the subject image element value corresponding to the subset of corresponding image element values. ### Claim 35 (depends on 34) The apparatus of claim 34 wherein the at least one processor is configured to: determine an upper limit value from the subset of the set of corresponding image element values; and compare the subject image element value to the upper limit value. ### Claim 36 (depends on 34) The apparatus of claim 34 wherein the at least one processor is configured to: determine a lower limit value from the subset of the set of corresponding image element values; and compare the subject image element value to the lower limit value. ### Claim 37 (depends on 34) The apparatus of claim 34 wherein the at least one processor is configured to: determine an upper limit value and a lower limit value from the subset of the set of corresponding image element values; and compare the subject image element value to the upper limit value and the lower limit value. ### Claim 38 (depends on 37) The apparatus of claim 37 wherein the at least one processor is configured to set the upper limit value and the lower limit value to a greatest value and a lowest value respectively of the subset of the set of corresponding image element values. ### Claim 39 (depends on 37) The apparatus of claim 37 wherein the at least one processor is configured to determine a standard deviation and a mean from the subset of the set of corresponding image element values and to derive the upper limit value and the lower limit value from the standard deviation and the mean. ### Claim 40 (depends on 37) The apparatus of claim 37 wherein the at least one processor is configured to: determine whether the subject image element value is greater than the upper limit or less than the lower limit; if the subject image element value is greater than the upper limit or less than the lower limit: generate a new image element value derived from the subject image element value and at least one of the upper limit and the lower limit; and generate a new image including the new image element value for inspection. ### Claim 41 (depends on 40) The apparatus of claim 40 wherein the at least one processor is configured to, if the subject image element value is not greater than the upper limit or less than the lower limit, generate the new image to include a neutral image element value. ### Claim 42 (depends on 40) The apparatus of claim 40 wherein the at least one processor is configured to transmit signals representing the new image to an anomaly detector. ### Claim 43 (depends on 40) The apparatus of claim 40 wherein the at least one processor is configured to inspect the new image to determine whether the new image element value is anomalous. ### Claim 44 (depends on 33) The apparatus of claim 33 further comprising at least one display and wherein the at least one processor is configured to produce signals for causing the at least one display to display a representation of the at least one anomaly to a user. ### Claim 45 (depends on 33) The apparatus of claim 33 wherein the at least one processor is configured to identify at least one extreme image element value as the at least one image element value to be excluded. ### Claim 46 (depends on 45) The apparatus of claim 45 wherein the set of corresponding image element values comprise pixel values and wherein the at least one processor is configured to identify at least one lowest pixel value of the pixel values to be excluded and at least one greatest pixel value of the pixel values to be excluded. ### Claim 47 (depends on 46) The apparatus of claim 46 wherein the at least one processor is configured to identify a first percentage of the pixel values having lowest values as the at least one lowest pixel value and to identify a second percentage of the pixel values having greatest values as the at least one greatest pixel value. ### Claim 48 (depends on 47) The apparatus of claim 47 wherein the first and second percentages are each between about 5% and about 15%. ### Claim 49 A computer readable medium having stored thereon codes which, when executed by at least one processor, cause the at least one processor to: receive image data representing the product during processing of the product; identify from the image data generally similar images representing respective instances of a repeated aspect of the pattern, each of the images including image element values; generate a set of corresponding image element values, said set including an image element value from each of the images; identify at least one image element value from the set of corresponding image element values to be excluded from a subset of the set of corresponding image element values; generate at least one criterion based on the subset of the set of corresponding image element values; and cause the at least one criterion to be used to facilitate identification of the at least one anomaly.