Share Email Print

Proceedings Paper

Binary image filtering under noise distribution constraints
Author(s): Octavian Valeriu Sarca; Jaakko T. Astola
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The most general filtering methods for binary images are binary increasing or non-increasing filters. The amount of memory used by both methods during training rises exponentially with the window size. Also, both methods need training sets whose size rises exponentially with the number of the window elements. This limits the size of the window to maximum 5 by 5 pixels. In this paper we search for a suboptimal filter which can be implemented for larger window sizes. Applying certain constraints to the noise distribution, the conditional expectation is decomposed into noise dependent and original image dependent components. The resulting filter can be trained with the original image to learn the ideal patterns, while the noise properties can be extracted by both modeling or training on a reasonable training set. The amount of memory used by the new filter is proportional to a finite power of window size. It is shown that the new filter is a generalization of weighted order statistic filter.

Paper Details

Date Published: 25 March 1996
PDF: 10 pages
Proc. SPIE 2662, Nonlinear Image Processing VII, (25 March 1996); doi: 10.1117/12.235838
Show Author Affiliations
Octavian Valeriu Sarca, Tampere Univ. of Technology (Finland)
Jaakko T. Astola, Tampere Univ. of Technology (Finland)

Published in SPIE Proceedings Vol. 2662:
Nonlinear Image Processing VII
Edward R. Dougherty; Jaakko T. Astola; Harold G. Longbotham, Editor(s)

© SPIE. Terms of Use
Back to Top