A2iA Check Reader: a family of bank check recognition systems

Author

Gorski, N. ; Anisimov, V. ; Augustin, E. ; Baret, O. ; Price, D. ; Simon, J.-C.

Author_Institution

Ai2A, Paris, France

fYear

1999

fDate

20-22 Sep 1999

Firstpage

523

Lastpage

526

Abstract

The paper presents new A2iA bank check recognition systems designed to process handwritten and/or printed checks issued in France, UK or USA. All the systems have identical architecture and design principles. However, each of them contains a country-specific part and is trained with country-specific data. Each system performs location, extraction, segmentation and recognition of courtesy and legal amounts in a document image, as well as deciding whether to accept or reject the check. The recognition rate is 80-90%. In the production mode, the check acceptance rate is 60-75%, with the misread rate corresponding to that of a human operator (close to 1%)

Keywords

cheque processing; document image processing; handwritten character recognition; A2iA Check Reader; A2iA bank check recognition systems; France; UK; USA; architecture; check acceptance rate; check rejection; country-specific data training; country-specific part; courtesy amounts; decision making; design principles; document image; extraction; handwritten check processing; legal amounts; location; misread rate; printed check processing; recognition rate; segmentation; Automation; Data mining; Handwriting recognition; Humans; Image recognition; Image segmentation; Law; Legal factors; Process design; Production;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on

Conference_Location

Bangalore

Print_ISBN

0-7695-0318-7

Type

conf

DOI

10.1109/ICDAR.1999.791840

Filename

791840