Segmenting merged characters

Author

Bayer, T. ; Kressel, Ulrich ; Hammelsbeck, M.

Author_Institution

Res. Center Ulm, Daimler-Benz AG, Germany

fYear

1992

fDate

30 Aug-3 Sep 1992

Firstpage

346

Lastpage

349

Abstract

In optical character recognition (OCR) and document analysis many errors are not caused by inadequate classifier power, but by segmentation errors. Besides broken characters, merged characters constitute the major remaining problem. This paper presents an efficient method for segmenting merged characters. The algorithm combines a statistical adapted cut classifier and a search algorithm, which employs further experts for selecting the proper cut positions from a set of hypotheses. It is designed especially for proportional fonts and even succeeds, if the characters are in italics font style

Keywords

character sets; document image processing; image segmentation; optical character recognition; cut positions; document analysis; italics font; merged characters; optical character recognition; proportional fonts; search algorithm; segmentation errors; statistical adapted cut classifier; Character recognition; Decision trees; Error analysis; Information analysis; Information processing; Optical character recognition software; Pattern analysis; Spatial databases; Testing; Text analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on

Conference_Location

The Hague

Print_ISBN

0-8186-2915-0

Type

conf

DOI

10.1109/ICPR.1992.201789

Filename

201789