Document image defect models and their uses
- 30 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The accuracy of today's document recognition algorithmsfalls abruptly when image quality degradeseven slightly. In an effort to surmount this barrier, researchershave in recent years intensified their study ofexplicit, quantitative, parameterized models of the imagedefects that occur during printing and scanning.I review the recent literature and discuss the formthese models might take. I give a preview of a largepublic--domain database of character images, labeledwith ground--truth...Keywords
This publication has 7 references indexed in Scilit:
- Global and local document degradation modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Perfect metricsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning classification treesStatistics and Computing, 1992
- Document Image Defect ModelsPublished by Springer Nature ,1992
- The first census optical character recognition system conferencePublished by National Institute of Standards and Technology (NIST) ,1992
- Large Tree Classifier with Heuristic Search and Global TrainingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- Decision tree design using a probabilistic model (Corresp.)IEEE Transactions on Information Theory, 1984