Abstract
Still today, bitonal images (black & white images without any shades in between – just black and white) of high quality are the precondition for trouble-free automatic text recognition (OCR). The challenge is to distinguish between relevant information and background information – at the same time, however, image processing may not create damage to character structures.Due to the high calculation amount and the necessity to use uncompressed images as source image for processing, mainly hardware-oriented image processing methods were used in the past, and they are widely in use still today.Due to the risen PC calculation power and by optimizing calculation steps, a method could be developed for dynamic thresholding of greyscale images that returns optimal results even from extremely difficult images; in the spring of 2003, it delivered about 600 images per minute (A4, 200dpi).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bartsch, H.S.: Taschenbuch Mathematische Formeln. ISBN 3 87144 239 9
Bronstein, I.N, Semendjajew, K.A.: Taschenbuch der Mathematik. ISBN 3 87144 492 8
CCITT, Red Book, Volume II, Fascicle VII.3, Terminal Equipment and Protocols for Telematic Services. ISBN 92-61-02291-X
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. ISBN 0201180758
Jähne, B.: Digitale Bildverarbeitung. ISBN 3540412603
Seul, M., Sammon, M.J., O’Gorman, L.: Practical Algorithms for Image Analysis: Descriptions, Examples, and Code. ISBN 0521660653
le Cun, Y., Bottou, L., Haffner, P., Howard, P.: DjVu: a compression method for distributing scanned documents in color over the internet. Color 6, IST (1998)
Specification of DjVu Image Compression Format Version of 1999-04-29 15:46 EDT Copyright (c), by AT&T (1999), http://www.djvuzone.org/techpapers/index.html#specs
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Woitha, D., Janich, D. (2004). Adaptive Threshold. In: Dengel, A., Junker, M., Weisbecker, A. (eds) Reading and Learning. Lecture Notes in Computer Science, vol 2956. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24642-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-540-24642-8_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21904-0
Online ISBN: 978-3-540-24642-8
eBook Packages: Springer Book Archive