Abstract
A lack of explicit quantitative models of imaging defects due to printing, optics, and digitization has retarded progress in some areas of document image analysis, including syntactic and structural approaches. Establishing the essential properties of such models, such as completeness (expressive power) and calibration (closeness of fit to actual image populations) remain open research problems. Work-in-progress towards a parameterized model of local imaging defects is described, together with a variety of motivating theoretical arguments and empirical evidence. A pseudo-random image generator implementing the model has been built. Applications of the generator are described, including a polyfont classifier for ASCII and a single-font classifier for a large alphabet (Tibetan U-Chen), both of which which were constructed with a minimum of manual effort. Image defect models and their associated generators permit a new kind of image database which is explicitly parameterized and indefinitely extensible, alleviating some drawbacks of existing databases.
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
H. S. Baird, “Feature Identification for Hybrid Structural/Statistical Pattern Classification,” Computer Vision, Graphics, & Image Processing 42, pp. 318–333, 1988.
H. S. Baird, “Global-to-Local Layout Analysis,” Proc. IAPR Workshop on Syntactic and Structural Pattern Recognition, Pont-a-Mousson, France, 12–14 September, 1988.
M. P. Ekstrom, Digital Image Processing Techniques, Academic Press (Orlando, 1984 ).
R. Fossey and P. Lofting, “The Typestyle Jockey: Putting the Horse Out Front in Devanagari and Tibetan,” Nordic Institute of Asian Studies Report, Copenhagen, pp. 5–30, 1990.
D. Lee, T. Pavlidis, and G. W. Wasilkowski, “A Note on the Trade-off between Sampling and Quantization in Signal Processing,” J. of Complexity, Vol. 3, pp. 359–371, 1987.
G. Marsaglia, “A Current View of Random Number Generators,” Keynote address, Computer Science and Statistics 16th Symp. on the Interface, Atlanta, March 1984.
W. F. Schreiber, Fundamentals of Electronic Imaging Systems, Springer Series Information Science 15, Springer-Verlag (Berlin, 1986 ).
Tshe bDang rNam rGyal, ed., Dag Yig Ma Nor Lam bZang (The Excellent Path to Wealth Dictionary). Lhasa: Mi Rigs dPe sKrun Khang (Humanity Publishing House), 1982.
N. Zeirler, “Primitive Trinomials Whose Degree is a Mersenne Exponent,” Inf. Control, 15, 1969.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Baird, H.S. (1992). Document Image Defect Models. In: Baird, H.S., Bunke, H., Yamamoto, K. (eds) Structured Document Image Analysis. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-77281-8_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-77281-8_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-77283-2
Online ISBN: 978-3-642-77281-8
eBook Packages: Springer Book Archive