Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A novel preprocessing method for hectography prints based on independent component analysis

 
: Kurbiel, Thomas; Konya, Iulio; Eickeler, Stefan

:
Postprint urn:nbn:de:0011-n-1926788 (4.7 MByte PDF)
MD5 Fingerprint: 54150446497dac13df39ac6d9fa572ef
© 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 27.1.2012


International Association for Pattern Recognition -IAPR-, Technical Committee on Graphics Recognition; International Association for Pattern Recognition -IAPR-, Technical Committee on Reading Systems:
International Conference on Document Analysis and Recognition, ICDAR 2011. Vol.2 : Beijing, China, 18 - 21 September 2011; proceedings
Piscataway/NJ: IEEE, 2011
ISBN: 978-0-7695-4520-2 (Online)
ISBN: 978-1-4577-1350-7 (Print)
S.1145-1149
International Conference on Document Analysis and Recognition (ICDAR) <11, 2011, Beijing>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()
independent component analysis; hectography; image enhancement; extraction; OCR

Abstract
Archives and cultural facilities consists of vast spectra of different document classes, many of which are not encountered today anymore. The digitization therefore calls for image enhancement and preprocessing solutions so far not required and hence unsolved. A prominent document class in this context is hectography, which was a inexpensive printing and duplication method, widely used throughout the 20th century. The major challenge with hectography is poor contrast on the one side and multiple degradation effects on the other side.In this paper a novel preprocessing method for hectography duplicates is proposed which leads to better Optical Character Recognition (OCR) results compared to traditional methods that operate on grayscale images. The proposed method is based on the model confo rm with the independent component analysis. The problem of unwanted Gaussian noise components is considered as well.

: http://publica.fraunhofer.de/dokumente/N-192678.html