Abstract
A seven-year-old child can identify characters with far greater accuracy than the leading OCR systems. Through many examples, we have seen the variety of problems at the OCR frontier. No single technique can solve all of these problems; however, there are many ways to advance the state of the art. We discuss four approaches:
-
1.
Improved image processing.
-
2.
Adapting to the current document.
-
3.
Multi-character recognition.
-
4.
Increased use of linguistic context.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media New York
About this chapter
Cite this chapter
Rice, S.V., Nagy, G., Nartker, T.A. (1999). Conclusion. In: Optical Character Recognition. The Springer International Series in Engineering and Computer Science, vol 502. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5021-1_6
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5021-1_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7281-3
Online ISBN: 978-1-4615-5021-1
eBook Packages: Springer Book Archive