Boosting OCR Classifier by Optimal Edge Noise Filtering
Chapter
Abstract
The problem of Optical Character Recognition (OCR) can be solved by set operators implemented as programs for a Morphological Machine (MMach). In this paper, we present two techniques to boost such programs: (1) Anchoring and (2) Edge Noise Filtering by Stamp. The power of these techniques is demonstrated by some impressive experimental results.
Key words
Morphological Machines OCR Edge Noise Filtering Set OperatorsPreview
Unable to display preview. Download preview PDF.
References
- 1.J. Serra. Image Analysis and Mathematical Morphology. Academic Press, New York, 1982.MATHGoogle Scholar
- 2.G. J. F. Banon and J. Barrera. Minimal representation for translation invariant set mappings by Mathematical Morphology. SIAM J. Appl. Math., V. 51, pp. 1782–1798, 1991.CrossRefMathSciNetMATHGoogle Scholar
- 3.J. Barrera and G. J. F. Banon. Expressiveness of the Morphological Language. In Image Algebra and Morphological Image Processing III, V. 1769 of SPIE Proceedings, pp. 264–275, San Diego, CA, 1992.Google Scholar
- 4.J. Barrera, E. R. Dougherty, and N. S. Tomita. Automatic programming of binary morphological machines by design of statistically optimal operators in the context of computational learning theory. Electronic Imaging, 6(1):54–67, January 1997.CrossRefGoogle Scholar
- 5.J. Barrera and R. Terada and F. S. C. da Silva and N. S. Tomita Automatic programming of morphological machines for OCR. In Mathematical Morphology and its Applications to Image and Signal Processing, pages 385, 392, Atlanta, GA, May 1996, ISMM, Kluwer Academic PublishersGoogle Scholar
- 6.J. Barrera and R. Terada and R. A. Lotufo and N. S. T. Hirata and R. Hirata Jr. and F. A. Zampirolli. An OCR based on Mathematical Morphology. In Nonlinear Image Processing IX, V. 3304 of SPIE, pages 197–208, San Jose, CA, January 1998.Google Scholar
- 7.J. Barrera and G. P. Salas. Set operations on collections of closed intervals and their applications to the automatic programming of morphological machines In Electronic Imaging, 5(3):335–352, July 1996.Google Scholar
- 8.J. Goutsias. Morphological analysis of discrete random shapes. Journal of Mathematical Image and Vision, V. 2, pp. 193–215, 1992.MathSciNetMATHGoogle Scholar
- 9.E. R. Dougherty, Y. Zhang and Y. Chen. Optimal Iterative Increasing Binary Morphological Filters. Optical Engineering, V. 35,N. 12, pp. 3495–3507, December 1996.CrossRefGoogle Scholar
Copyright information
© Kluwer Academic/Plenum Publishers 2002