Title :
Scanner-model-based document image improvement
Author :
Bern, M. ; Goldberg, David
Author_Institution :
Xerox Palo Alto Res. Center, CA, USA
Abstract :
We describe a method for improving scanned or faxed document images. Our method assumes a probabilistic model of the scanning process, and uses this model to cluster instances of the same letter and to compute super-resolved representatives of the clusters. The approach also enables Bayesian prior distributions and reversal of scanner distortions such as gain.
Keywords :
Bayes methods; document image processing; facsimile; image enhancement; image resolution; image scanners; pattern clustering; probability; Bayesian prior distribution; faxed document images; gain; probabilistic model; scanned document images; scanner distortions; scanner-model-based document image improvement; scanning process; super-resolved cluster representatives; Bayesian methods; Character recognition; Clustering algorithms; Degradation; Histograms; Image restoration; Image sensors; Optical character recognition software; Pixel; Sensor phenomena and characterization;
Conference_Titel :
Image Processing, 2000. Proceedings. 2000 International Conference on
Conference_Location :
Vancouver, BC, Canada
Print_ISBN :
0-7803-6297-7
DOI :
10.1109/ICIP.2000.899497
