System and method for automatic optical data entry

• US 5,237,628 A
• Filed: 06/03/1991
• Issued: 08/17/1993
• Est. Priority Date: 06/03/1991
• Status: Expired due to Term

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: NYNEX Corp. (Verizon Communications Inc.)
• Inventors: Levitan, Arthur C.
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): Fox, David
• Application Number:
  US07/709,499
• Time in Patent Office: 806 Days
• Field of Search: 382/61, 382/57, 382/40, 382/1, 235/375, 235/376, 235/454, 235/470
• US Class Current: 382/175
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields

Abstract

A system and method for automatically processing machine printed forms which are filled out by hand are disclosed. The inventive system and method eliminate the use of a manual data entry step. Typically each form has one or more fields, each field having a machine printed field identifier such as the words "name" or "social security number" and the corresponding information which is filled in by hand. A scanner or other device forms a digital image of each form. An optical recognition engine searches the digital image of each form through use of an algorithm which can recognize machine printed but not handwritten characters to locate the fields in the digital image by locating the machine printed field identifiers. An offline handwritten character recognition algorithm is then utilized to recognize the handwritten characters in each individual field. Symbolic information corresponding to the recognized handwritten characters is then stored in a database in a memory.

Claims

1. An electronic data processing system for processing large numbers of machine printed forms containing one or more fields, each field having a machine printed human intelligible field identifier which describes to a person information to be written into the field, and one or more handwritten characters written in response to the corresponding machine printed field identifier, said electronic data processing system comprising:

generating means for generating a digital image of each of said forms, and

an optical recognition engine comprising a first optical recognizer capable of recognizing machine printed characters but not handwritten characters for searching the digital image of each form to identify the locations of a selected one or more of said fields by recognizing only said human intelligible machine printed field identifiers, and a second optical recognizer capable of recognizing handwritten characters for recognizing the handwritten characters in the fields located by said first optical recognizer in said digital image of each form,

wherein said optical recognition engine uses only the same human intelligible field identifiers, which describe to a person information to be written into corresponding fields, for locating said fields containing handwritten characters without using any additional machine printed field identifiers.

2. The system of claim 1 wherein said generating means comprises a scanner.

3. The system of claim 1 wherein said generating means comprises a fax machine located remotely from said optical recognition engine.

4. The system of claim 1 wherein said optical recognition engine is formed by a general purpose computer.

5. The system of claim 1 wherein said second optical recognizer comprises a finder for locating handwritten material in said fields, a segmenter for identifying the location of character boundaries in said handwritten material, and a recognizer for recognizing individual handwritten characters.

6. A method for processing large numbers of machine printed forms containing one or more fields, each field having a machine printed human intelligible field identifier which describes to humans information to be written into the field and one or more handwritten characters written in response to the corresponding field identifier, said method comprising the steps of:

electroncially generating a digital image of each of said forms to be processed,

utilizing an optical recognition engine to execute an optical character recognition algorithm which recognizes machine printed characters but not handwritten characters, searching the digital image of each of said forms to locate said fields by recognizing said human intelligible machine printed field identifiers,

utilizing said optical recognition engine to execute a handwritten character recognition algorithm for recognizing handwritten characters contained in said located fields, and for outputting symbolic information representative of said recognized handwritten characters, and

storing said symbolic information in a memory,

wherein said optical recognition engine uses only the same human intelligible machine printed field identifiers, which describe to a person information to be written into corresponding fields, for locating said fields containing handwritten characters, without using any additional machine printed field identifiers.

7. The method of claim 6 wherein said optical recognition engine is formed by a general purpose computer.

8. The method of claim 6 wherein said algorithm which can recognize machine printed but not handwritten characters is a template matching algorithm.

9. The method of claim 6 wherein said offline handwritten character recognition algorithm comprises the steps of finding handwritten material in said fields, segmenting the handwritten material by locating character boundaries, and recognizing individual characters.

10. The method of claim 6 wherein said handwritten character recognition algorithm can recognize only a subset of said handwritten characters and wherein said method comprises the step of comparing said recognized handwritten characters with a database to determine the unrecognized handwritten characters.

11. The method of claim 10 wherein said subset of handwritten character comprises numbers.

12. An electronic data processing system for processing machine printed forms containing one or more fields, each field having a machine printed human intelligible field identifier which describes to a person information to be written into the field, and one or more handwritten characters written in response to the corresponding machine printed field identifier, said electronic data processing system comprising:

digitizing means for generating a digital image of each of said forms,

first optical recognition means which can recognize machine printed but not handwritten characters for searching the digital image of each form to find the location of selected ones of said fields by recognizing said machine printed human intelligible field identifiers, and

second optical recognition means which can recognize handwritten characters for recognizing the handwritten characters contained in the fields located by the first optical recognition means,

wherein said first optical recognition means uses only the same human intelligible field identifiers, which describe to a person information to be written into corresponding fields, for locating said fields containing handwritten characters without using any additional machine printed field identifiers.