A segmentation-free approach to OCR
- 2 January 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 190-196
- https://doi.org/10.1109/acv.1992.240312
Abstract
When confronted with degraded images of text, however, the performance of many commercial OCR systems deteriorates severely. This occurs because all these systems rely on a segmentation step that is prone to error in the presence of image noise and printing artifacts. The authors present a novel OCR approach that overcomes this problem by eliminating the segmentation step altogether. This approach is based on the concept and techniques of occluded object recognition. To achieve high efficiency as well as robustness, they incorporate the notions of indexing and voting, and tailor them to the problem of OCR. Preliminary experimental results are given Author(s) Chen, C.H. Inf., Telecommun. & Autom. Div., SRI Int., Menlo Park, CA, USA DeCurtins, J.L.Keywords
This publication has 6 references indexed in Scilit:
- Geometric Hashing: A General And Efficient Model-based Recognition SchemePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Feature-utility measures for automatic vision programmingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reading cursive handwriting by alignment of letter prototypesInternational Journal of Computer Vision, 1990
- Object recognition and localization via pose clusteringComputer Vision, Graphics, and Image Processing, 1987
- Research on Machine Recognition of Handprinted CharactersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- A two-step strategy for character recognition using geometrical momentsRadio and Electronic Engineer, 1975