Process and equipment for recognition of a pattern on an item presented

• US 6,373,982 B1
• Filed: 05/07/1999
• Issued: 04/16/2002
• Est. Priority Date: 05/07/1998
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Maier, Udo, Ruppert, Werner
• Primary Examiner(s): Au, Amelia M.
• Assistant Examiner(s): Dastouri, Mehrdad
• Application Number:
  US09/307,327
• Time in Patent Office: 1,075 Days
• Field of Search: 382/310, 382/311, 382/181, 382/182, 382/187, 382/224, 382/225, 382/229
• US Class Current: 382/187
• CPC Class Codes: G06V 10/98 Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
• CPC Class Codes: G06V 30/248 involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" G06V30/242 takes precedence

Abstract

Apparatus and method for improving recognition of patterns such as alphanumeric characters. A known recognition system is expanded to further include a complementary recognition system which is linked with the primary recognition system. An image that can not be positively recognized by the primary recognition system is passed on to the complementary recognition system and any characters not positively recognized by the complementary recognition are again passed on to a correction system. At the correction system, an operator classifies unrecognized characters which are then used to teach the complementary recognition system. Thus, the classified data of the correction system provide the training data for a continuous training process which is coupled with the correction system by a pattern adaptation system.

Claims

1. Apparatus for recognizing a pattern comprising:

a first pattern recognition system for recognizing a pattern with a first level of confidence;

a complementary pattern recognition system for recognizing with a second level of confidence, a pattern that cannot be recognized by the first pattern recognition system with the first level of confidence;

a correcting system for receiving manual pattern identification input when a pattern cannot be recognized by the complementary pattern recognition system with the second level of confidence;

a pattern adaptation system connected to the correction system for receiving pattern identification information from the correction system, the pattern adaptation system including;

a database for receiving information originating from input to the correction system, the database including;

means for storing patterns of characters to be recognized by the complementary recognition system; and

means for storing attribute information for each pattern to be recognized by the complementary recognition system, the means for storing attribute information including;

means for storing a master identification of a related stored pattern;

means for storing scanner resolution of a related stored pattern;

means for storing width and height of a character frame of a related stored pattern; and

means for storing a recognition-ID of a related stored pattern;

the pattern adaptation system providing adaptation of the pattern recognition information supplied to the complementary recognition system to improve the recognition level of confidence of the complementary recognition system.

2. Apparatus for recognizing a pattern comprising:

a first pattern recognition system for recognizing a pattern with a first level of confidence;

a complementary pattern recognition system for recognizing with a second level of confidence, a pattern that cannot be recognized by the first pattern recognition system with the first level of confidence;

a correcting system for receiving manual pattern identification input when a pattern cannot be recognized by the complementary pattern recognition system with the second level of confidence;

a pattern adaptation system connected to the correction system for receiving pattern identification information from the correction system, the pattern adaptation system including a database for receiving information originating from input to the correction system; and

means for determining that identification information for an adequate quantity of patterns has been collected; and

means for determining that a specific time has arrived for using the collected pattern identification information to adapt the pattern recognition information supplied to the complementary recognition system to improve the recognition level of confidence of the complementary recognition system.

3. Method of recognizing a pattern comprising the acts of:

recognizing a pattern in a primary recognition system with a first level of confidence;

recognizing in a complementary recognition system with a second level of confidence, a pattern that cannot be recognized by the primary pattern recognition system with the first level of confidence;

receiving manual pattern identification input at a correction station when a pattern cannot be recognized by the complementary pattern recognition system with the second level of confidence;

receiving pattern identification information at a pattern adaptation system from the correction system;

storing information originating from input to the correction system in a database including patterns of characters to be recognized by the complementary recognition system and for each pattern to be recognized by the complementary recognition system;

storing in the database, a master identification of a related stored pattern;

storing in the database, scanner resolution of a related stored pattern;

storing in the database, width and height of a character frame of a related stored pattern; and

storing in the database, a recognition-ID of a related stored pattern; and

then

adapting the pattern recognition information supplied to the complementary recognition system to improve the recognition level of confidence of the complementary recognition system.

4. Method of recognizing a pattern comprising the acts of:

recognizing a pattern in a primary recognition system with a first level of confidence;

recognizing in a complementary recognition system with a second level of confidence, a pattern that cannot be recognized by the primary pattern recognition system with the first level of confidence;

receiving manual pattern identification input at a correction station when a pattern cannot be recognized by the complementary pattern recognition system with the second level of confidence;

receiving pattern identification information at a pattern adaptation system from the correction system; and

determining when identification information for an adequate quantity of patterns has been collected; and

determining when a specific time has arrived for

adapting the pattern recognition information supplied to the complementary recognition system to improve the recognition level of confidence of the complementary recognition system.