# US 2015/0310268 A1 · Media item validation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2015/0310268 A1 - Document ID: US20150310268A1 - Status: Published application - Kind: A1 - Application number: 14/264,860 - Filed: 2014-04-29 - Published: 2015-10-29 - Earliest claimed: 2014-04-29 - Assignees: NCR Corporation - Applicants: NCR Corporation - Inventors: Chao He; Gary Ross - Web page: https://patentgrep.com/patent/US20150310268A1 ## CPC - G07D 7/2016: {using feature extraction, e.g. segmentation, edge detection or Hough-transformation} - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/24: Classification techniques - G06V 30/40: Document-oriented image-based pattern recognition - G06F 18/23: Clustering techniques - G06F 18/2413: based on distances to training or reference patterns - G06V 10/141: Control of illumination - G06V 10/143: Sensing or illuminating at different wavelengths - G07D: HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract The present invention provides a method of validating a media item, the method comprising receiving image data corresponding to a plurality of digital images of a media item to be validated, wherein each image is associated with a respective one of a plurality of different channels of an illumination source for illuminating the media item, selecting image data corresponding to two of the plurality of images, dividing a common parameter of the selected image data associated with corresponding locations of the two selected images to create ratio image data representing a ratio image for two different channels of the illumination source, extracting feature information associated with the ratio image, and classifying the extracted feature information with at least one classifier of a validation template to determine whether or not the media item is valid. A computer program and a Self-Service Terminal for validating a media item, such as a banknote, are also provided. ## Claims ### Claim 1 A method of validating a media item, the method comprising: receiving image data corresponding to a plurality of digital images of a media item to be validated, wherein each image is associated with a respective one of a plurality of different channels of an illumination source for illuminating the media item; selecting image data corresponding to two of the plurality of images; dividing a common parameter of the selected image data associated with corresponding locations of the two selected images to create ratio image data representing a ratio image for two different channels of the illumination source; extracting feature information associated with the ratio image; and classifying the extracted feature information with at least one classifier of a validation template to determine whether or not the media item is valid. ### Claim 2 (depends on 1) The method as claimed in claim 1, further comprising: segmenting the ratio image using a segmentation map of the validation template; extracting feature information from each segment; and classifying the extracted feature information from each segment with a corresponding segment classifier of the validation template. ### Claim 3 (depends on 1) The method as claimed in claim 1, further comprising: combining the extracted feature information from all segments; and classifying the combined extracted feature information from all segments with a classifier of the validation template. ### Claim 4 (depends on 3) The method as claimed in claim 3, further comprising: inputting the extracted feature information into one or more functions of the at least one classifier to produce an output; and comparing the output with at least one threshold parameter of the at least one classifier to determine whether or not the media item is valid. ### Claim 5 (depends on 1) The method as claimed in claim 1, wherein the at least one classifier is a one-class classifier. ### Claim 6 (depends on 1) The method as claimed in claim 1, wherein the validation template is selected from a plurality of validation templates responsive to a class of media item to be validated. ### Claim 7 (depends on 7) The method as claimed in claim 7, wherein the media item is a banknote and the class comprises currency, denomination, orientation and design series. ### Claim 8 (depends on 7) The method as claimed in claim 7, wherein each validation template is created on the basis of information about a set of training ratio images of a plurality of media items of the same class. ### Claim 9 (depends on 9) The method as claimed in claim 9, wherein the segmentation map of a corresponding validation template is created by using a clustering algorithm to cluster pixel locations of each corresponding ratio image of a selected channel using a plurality of media items of the same class. ### Claim 10 (depends on 9) The method as claimed in claim 9, wherein the segmentation map of a corresponding validation template is created by using a clustering algorithm to cluster pixel locations of each corresponding ratio image of all ratio channels together using a plurality of media items of the same class. ### Claim 11 (depends on 1) The method as claimed in claim 1, wherein a one of the at least two selected images is associated with a green channel or a blue channel of the illumination source, and a remainder one of the at least two selected images is associated with an infrared channel of the illumination source. ### Claim 12 (depends on 1) The method as claimed in claim 1, wherein the common parameter comprises luminous intensity. ### Claim 13 (depends on 1) The method as claimed in claim 1, further comprising: adjusting at least one property of the ratio image. ### Claim 14 A computer program comprising program instructions for validating a media item by the steps of: receiving image data corresponding to a plurality of digital images of a media item to be validated, wherein each image is associated with a respective one of a plurality of different channels of an illumination source for illuminating the media item; selecting image data corresponding to two of the plurality of images; dividing a common parameter of the selected image data associated with corresponding locations of the two selected images to create ratio image data representing a ratio image for two different channels of the illumination source; extracting feature information associated with the ratio image; and classifying the extracted feature information with at least one classifier of a validation template to determine whether or not the media item is valid. ### Claim 15 (depends on 14) A Self-Service Terminal (SST) comprising: at least one imaging device for capturing a plurality of digital images of a media item to be validated; and a computing device that executes the computer program as claimed in claim 14.