Method for verifying an intended address by OCR percentage address matching

• US 7,539,326 B2
• Filed: 12/23/2005
• Issued: 05/26/2009
• Est. Priority Date: 12/23/2005
• Status: Expired due to Fees

• Current Assignee: DMT Solutions Global Corporation
• Original Assignee: Pitney Bowes Incorporated (Böwe Systec AG)
• Inventors: Eremita, Joseph, Ruck, Adrian
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): Bitar; Nancy
• Application Number:
  US11/318,230
• Publication Number:
  US 20070147659A1
• Time in Patent Office: 1,250 Days
• Field of Search: 382/101, 382/161, 382/225, 382/226, 382/228, 382/230, 382/231, 382/311, 382/197, 382/203, 382/184, 382/174, 382/175, 382/190, 707/3, 707/6, 707/200, 705/30, 705/401, 235/492, 209/584
• US Class Current: 382/101
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

An OCR percentage matching algorithm achieves a significant reduction in false mismatches accounting for combinations of unprocessed spaces, missing characters, extra characters and character substitution errors during the OCR scanning processing and allows for a specified percentage of the OCR character scan rather the entire OCR character scan to be the same as the expected character string to declare a match.

Claims

1. A method of verifying that an intended addressee on a mailpiece matches a valid addressee in a mail processing apparatus using an OCR system by comparing an OCR character string scan of the intended addressee to an expected character string of the corresponding valid addressee, the method comprising the steps of:

(a) removing spaces in the expected character string;

(b) searching for each character of a scanned OCR character string in the characters of the expected character string from left to right starting with a first character in the expected character string until that scanned OCR character is located;

(c) repeating the searching step for a second subsequent character of the scanned OCR character string in the characters of the expected character string starting from a location of a last previously located character in the expected character string or if an end of the expected character string is reached without locating the second subsequent character, repeating the searching step for a third subsequent character of the scanned OCR character string from the location of a most recent previously located character in the expected character string;

(d) repeating step (c) for each next subsequent character of the scanned OCR character string until a percentage of located OCR scanned characters in a correct order matching correspondingly positioned characters in the expected character string exceeds a pre-determined threshold percentage; and

(e) declaring a match between the intended addressee and the valid addressee upon reaching the pre-determined threshold percentage;

whereby further character comparison is stopped.

2. The method as defined in claim 1 further including a step of defining the expected character string as a small character string when a number of characters in the expected character string does not exceed a pre-determined number of characters.

3. The method as defined in claim 2 wherein the number of characters defining a small string is six characters.

4. The method as defined in claim 1 further including a step of setting the pre-determined threshold percentage value.

5. The method as defined in claim 2 wherein the step of searching for each character of the scanned OCR character string further comprises searching a scanned OCR character string having missing characters.

6. The method as defined in claim 1 wherein the step of searching for each character of the scanned OCR character string further comprises searching a scanned OCR character string having extra characters.

7. The method as defined in claim 1 wherein the step of searching for each character of the scanned OCR character string further comprises searching a scanned OCR character string having substitution and untrained characters.

8. The method as defined in claim 1 wherein the step of searching for each character of the scanned OCR character string further comprises searching a scanned OCR character string having substitution and extra characters.