Paper
28 January 2008 Automatic removal of crossed-out handwritten text and the effect on writer verification and identification
Axel Brink, Harro van der Klauw, Lambert Schomaker
Author Affiliations +
Proceedings Volume 6815, Document Recognition and Retrieval XV; 68150A (2008) https://doi.org/10.1117/12.766466
Event: Electronic Imaging, 2008, San Jose, California, United States
Abstract
A method is presented for automatically identifying and removing crossed-out text in off-line handwriting. It classifies connected components by simply comparing two scalar features with thresholds. The performance is quantified based on manually labeled connected components of 250 pages of a forensic dataset. 47% of connected components consisting of crossed-out text can be removed automatically while 99% of the normal text components are preserved. The influence of automatically removing crossed-out text on writer verification and identification is also quantified. This influence is not significant.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Axel Brink, Harro van der Klauw, and Lambert Schomaker "Automatic removal of crossed-out handwritten text and the effect on writer verification and identification", Proc. SPIE 6815, Document Recognition and Retrieval XV, 68150A (28 January 2008); https://doi.org/10.1117/12.766466
Lens.org Logo
CITATIONS
Cited by 8 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Distance measurement

Forensic science

Computing systems

Copper

Data modeling

Artificial intelligence

Clouds

RELATED CONTENT

Handwriting individualization using distance and rarity
Proceedings of SPIE (January 23 2012)
Group discriminatory power of handwritten characters
Proceedings of SPIE (December 15 2003)
Shear invariant 3D model retrieval
Proceedings of SPIE (January 29 2007)

Back to Top