Method of validating a media item
View Patent ↗A technique for use in automatic validation of a media item involves accessing a template that comprises multiple one-class classifiers, each corresponding to one of multiple classes to which the media item might belong, and then applying each of the one-class classifiers to an image of the media item to generate a result set for each of the multiple classes. The result set for each media class is then analyzed to assess whether the media item belongs to that class.
1. A method for use in automatic validation of a sheet media item, a valid sheet media item having at least two classes, with at least two classes corresponding to two different orientations of the valid sheet media item upon presentation for validation, the method comprising:
storing in a digital memory a single template that comprises a single segmentation map for the valid media item that applies to both of said at least two classes corresponding to two different orientations, and at least two one-class classifiers for the valid sheet media item that work in conjunction with the single segmentation map, each one-class qualifier corresponding to one of the at least two classes corresponding to two different orientations;
accessing by a computer the single template;
applying by the computer each of the one-class classifiers to an image of the sheet media item to generate a result set for each of the multiple classes; and
for each of the multiple classes, analyzing by the computer the result set and assessing whether the sheet media item belongs to that class.
2. The method of claim 1 , further comprising concluding that the sheet media item belongs to none of the multiple classes and, in response, concluding that the sheet media item is not valid.
3. The method of claim 1 , further comprising concluding that the sheet media item belongs to one of the multiple classes and, in response, concluding that the sheet media item is valid.
4. The method of claim 1 , where the valid sheet media item has at least four classes are associated with each of four orientations in which the sheet media item can be inserted into an automated validation machine.
5. The method of claim 1 , where at least two further classes are associated with each of at least two production series in which the valid sheet media item has been produced.
6. The method of claim 1 , where the valid sheet media item is a bank note, and where the single template corresponds to a particular currency and a particular denomination to which the bank note belongs.
7. The method of claim 6 , where at least two classes are associated with each of two orientations in which a bank note of the particular currency and particular denomination can be inserted into an automatic validation machine.
8. The method of claim 1 , where each of two further classes are associated with a different production series in which a bank note of the particular currency and particular denomination has been produced.
9. The method of claim 1 , further comprising:
retrieving from the single template the single segmentation map for the valid sheet media item; and
applying the segmentation map to the image of the sheet media item to extract a feature set for the image.
10. The method of claim 9 , where applying each of the one-class classifiers to the image of the sheet media item includes applying each of the one-class classifiers to the feature set for the image to generate the result set for each of the at least two classes.
11. The method of claim 1 , where the single template comprises at least two one-class classifiers that each represents one of multiple feature clusters, where each of the multiple feature clusters is associated with one of the at least two classes to which the sheet media item might belong.
12. The method of claim 1 , where the sheet media item is a bank note.
13. The method of claim 1 wherein the single template comprises segments determined at least in part by clustering pixels utilizing measured intensity values of the pixels.
14. The method of claim 1 , wherein the segmentation map is created from images of valid sheet media items having all four possible orientations of presentation for validation.
15. The method of claim 1 wherein the valid media sheet item is a bank note, and the method further comprises:
receiving a bank note by an ATM; and
creating an image of the bank note.
16. The method of claim 15 further comprising:
analyzing the image to identify both the currency and denomination of the bank note.
17. The method of claim 16 further comprising:
utilizing the identified currency and denomination of the bank note to retrieve a single template from digital memory corresponding to the identified currency and denomination.