Browse Prior Art Database

Universal Image Recognition Reader/Sorter Control System

IP.com Disclosure Number: IPCOM000037466D
Original Publication Date: 1989-Feb-01
Included in the Prior Art Database: 2005-Jan-29
Document File: 1 page(s) / 11K

Publishing Venue

IBM

Related People

Dinan, RF: AUTHOR [+2]

Abstract

Disclosed is a Reader/Sorter system in which known hardware/software image capture and analysis technologies are used to control document sorting based on recognition of any desired characteristics of the document image.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 100% of the total text.

Page 1 of 1

Universal Image Recognition Reader/Sorter Control System

Disclosed is a Reader/Sorter system in which known hardware/software image capture and analysis technologies are used to control document sorting based on recognition of any desired characteristics of the document image.

This embodiment is based on analysis of a captured image of the entire document face (and/or back). This permits unlimited flexibility in establishing the form of the image criteria which determine the sort destination. This system is universal in that it is independent of document size and is readily adaptable to recognize image characteristics ranging from simple character fonts to complex morphologies. This is a complete break with present restrictive systems in which only certain character fonts in limited areas of the document may be used.

This system can be initialized by using directly programmed criteria or with a master document that, through Artificial Intelligence Learning, sets the criteria for the processing of subsequent documents. This mode of operation permits processing of documents that contain information of a non-standard nature.

It is apparent that this system has the inherent capability to sort unlimited variations of information formats including portraits, artwork, symbols, currency, tickets, etc.

Disclosed anonymously.

1