Share Email Print

Proceedings Paper

Adaptive pre-OCR cleanup of grayscale document images
Author(s): Ilya Zavorin; Eugene Borovikov; Mark Turner; Luis Hernandez
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper describes new capabilities of ImageRefiner, an automatic image enhancement system based on machine learning (ML). ImageRefiner was initially designed as a pre-OCR cleanup filter for bitonal (black-and-white) document images. Using a single neural network, ImageRefiner learned which image enhancement transformations (filters) were best suited for a given document image and a given OCR engine, based on various image measurements (characteristics). The new release improves ImageRefiner in three major ways. First, to process grayscale document images, we have included three grayscale filters based on smart thresholding and noise filtering, as well as five image characteristics that are all byproducts of various thresholding techniques. Second, we have implemented additional ML algorithms, including a neural network ensemble and several "all-pairs" classifiers. Third, we have introduced a measure that evaluates overall performance of the system in terms of cumulative improvement of OCR accuracy. Our experiments indicate that OCR accuracy on enhanced grayscale images is higher than that of both the original grayscale images and the corresponding bitonal images obtained by scanning the same documents. We have noticed that the system's performance may suffer when document characteristics are correlated.

Paper Details

Date Published: 16 January 2006
PDF: 9 pages
Proc. SPIE 6067, Document Recognition and Retrieval XIII, 60670C (16 January 2006); doi: 10.1117/12.641753
Show Author Affiliations
Ilya Zavorin, CACI International Inc. (United States)
Eugene Borovikov, CACI International Inc. (United States)
Mark Turner, CACI International Inc. (United States)
Luis Hernandez, Army Research Lab. (United States)

Published in SPIE Proceedings Vol. 6067:
Document Recognition and Retrieval XIII
Kazem Taghva; Xiaofan Lin, Editor(s)

© SPIE. Terms of Use
Back to Top