23 March 1994 Self-correcting 100-font classifier
Author Affiliations +
Abstract
We have developed a practical scheme to take advantage of local typeface homogeneity to improve the accuracy of a character classifier. Given a polyfont classifier which is capable of recognizing any of 100 typefaces moderately well, our method allows it to specialize itself automatically to the single -- but otherwise unknown -- typeface it is reading. Essentially, the classifier retrains itself after examining some of the images, guided at first by the preset classification boundaries of the given classifier, and later by the behavior of the retrained classifier. Experimental trials on 6.4 M pseudo-randomly distorted images show that the method improves on 95 of the 100 typefaces. It reduces the error rate by a factor of 2.5, averaged over 100 typefaces, when applied to an alphabet of 80 ASCII characters printed at ten point and digitized at 300 pixels/inch. This self-correcting method complements, and does not hinder, other methods for improving OCR accuracy, such as linguistic contextual analysis.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Henry S. Baird, Henry S. Baird, George Nagy, George Nagy, } "Self-correcting 100-font classifier", Proc. SPIE 2181, Document Recognition, (23 March 1994); doi: 10.1117/12.171098; https://doi.org/10.1117/12.171098
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Optimal policy for labeling training samples
Proceedings of SPIE (February 04 2013)
Toward quantifying the amount of style in a dataset
Proceedings of SPIE (January 16 2006)
Approximate k-nearest neighbor method
Proceedings of SPIE (September 01 1993)
Capacity of feedforward networks with shared weights
Proceedings of SPIE (July 01 1992)

Back to Top