Document processing system control using document feature analysis for identification

A method of controlling mail processing equipment of a mail processing system used to process one document of a plurality of documents, the one having minutiae extracted from an electronic file associated with the document, the method comprising the following steps:

• processing a printed representation of the document on mail processing equipment, the processing including at least capturing of an image of the printed representation of the document;
• extracting image minutiae from the captured image;
• comparing the image minutiae with the minutiae for positively identifying the document;
• and
• utilizing control data associated with the document to control operation of the mail processing equipment in response to positively identifying the document, wherein:
• the minutiae and the image minutiae are a plurality of document characteristics, the plurality of document characteristics are selected from a combination of two or more of font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document,
• the document characteristics individually are insufficient to uniquely identify the document from a second document, but the combination of the two or more document characteristics are sufficient to uniquely identify the one document from the second document, and
• the mail processing system is either an inserter system or sorter system.

A method of controlling a mail processing system comprising:

• defining a super set of minutiae associated with each of a plurality of documents prior to processing on mail processing equipment of the mail processing system, the super set of minutiae including a plurality of minutiae candidates associated with each document which, in combination, provide positive identification of each document;
• generating a document minutiae database for storing the plurality of minutiae candidates extracted from an electronic file;
• obtaining control data associated with each document by matching the stored minutiae candidates for each document with image minutiae obtained from an image post-print representation of each document loaded on the mail processing equipment, and
• applying the control data to control the operation of the mail processing equipment, wherein:
• the stored minutiae and the image minutiae are a plurality of document characteristics, the plurality of document characteristics are selected from a combination of two or more of font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document, the document characteristics individually are insufficient to uniquely identify one of the plurality of documents from a second document, but the combination of the two or more document characteristics are sufficient to uniquely identify the one document from the second document, and
• the mail processing system is either an inserter system or sorter system.

A method of performing a quality check of a previously identified document (“document”) including a plurality of pages, the method comprising steps of:

• capturing an image of a printed representation of the document processed on mail processing equipment of a mail processing system selected from an inserter or sorter system, the image including image minutiae for one or more pages of the document;
• comparing minutiae associated with at least one page of the document which is subsequent to a first page of the document with associated image minutiae;
• verifying that the at least one page of the document is part of the document;
• and
• processing the document based on a result of the verifying step, wherein:
• the minutiae extracted from an electronic file and the image minutiae are a plurality of document characteristics, the plurality of document characteristics are selected from a combination of two or more or font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document, the document characteristics individually are insufficient to uniquely identify the document, but the combination of the two or more document characteristics are sufficient to uniquely identify the document.