24 March 2014 Form similarity via Levenshtein distance between ortho-filtered logarithmic ruling-gap ratios
Author Affiliations +
Abstract
Geometric invariants are combined with edit distance to compare the ruling configuration of noisy filled-out forms. It is shown that gap-ratios used as features capture most of the ruling information of even low-resolution and poorly scanned form images, and that the edit distance is tolerant of missed and spurious rulings. No preprocessing is required and the potentially time-consuming string operations are performed on a sparse representation of the detected rulings. Based on edit distance, 158 Arabic forms are classified into 15 groups with 89% accuracy. Since the method was developed for an application that precludes public dissemination of the data, it is illustrated on public-domain death certificates.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
George Nagy, Daniel Lopresti, "Form similarity via Levenshtein distance between ortho-filtered logarithmic ruling-gap ratios", Proc. SPIE 9021, Document Recognition and Retrieval XXI, 902106 (24 March 2014); doi: 10.1117/12.2041956; https://doi.org/10.1117/12.2041956
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Vehicle positioning using image processing
Proceedings of SPIE (March 30 2009)
Finding text in color images
Proceedings of SPIE (April 01 1998)
Colour processing in Runge space
Proceedings of SPIE (February 03 2011)

Back to Top