Restoration of archival documents using a wavelet technique
- 10 December 2002
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 24 (10) , 1399-1404
- https://doi.org/10.1109/tpami.2002.1039211
Abstract
This paper addresses a problem of restoring handwritten archival documents by recovering their contents from the interfering handwriting on the reverse side caused by the seeping of ink. We present a novel method that works by first matching both sides of a document such that the interfering strokes are mapped with the corresponding strokes originating from the reverse side. This facilitates the identification of the foreground and interfering strokes. A wavelet reconstruction process then iteratively enhances the foreground strokes and smears the interfering strokes so as to strengthen the discriminating capability of an improved Canny edge detector against the interfering strokes. The method has been shown to restore the documents effectively with average precision and recall rates for foreground text extraction at 84 percent and 96 percent, respectively.Keywords
This publication has 19 references indexed in Scilit:
- Threshold selection for wavelet shrinkage of noisy dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A noise attribute thresholding method for document image binarizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A new wavelet-based approach to sharpening and smoothing of images in Besov spaces with applications to deblurringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- On the evaluation of document analysis components by recall, precision, and accuracyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A wavelet approach to extracting contours of document imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Multiscale segmentation of unstructured document pages using soft decision integrationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Character extraction from documents using wavelet maximaPublished by SPIE-Intl Soc Optical Eng ,1996
- De-noising by soft-thresholdingIEEE Transactions on Information Theory, 1995
- Contrast enhancement of medical images using multiscale edge representationOptical Engineering, 1994
- Characterization of signals from multiscale edgesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992