Performance Evaluation Methodology for Historical Document Image Binarization

Document image binarization is of great importance in the document image analysis and recognition pipeline since it affects further stages of the recognition process. The evaluation of a binarization method aids in studying its algorithmic behavior, as well as verifying its effectiveness, by providi...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on image processing Vol. 22; no. 2; pp. 595 - 609
Main Authors Ntirogiannis, K., Gatos, B., Pratikakis, I.
Format Journal Article
LanguageEnglish
Published New York, NY IEEE 01.02.2013
Institute of Electrical and Electronics Engineers
Subjects
Algorithms
Applied sciences
Artificial Intelligence
Document image binarization
Documentation - methods
Exact sciences and technology
ground truth
Handwriting
Humans
Image processing
Image Processing, Computer-Assisted - methods
Information, signal and communications theory
Loss measurement
Noise measurement
Optical character recognition software
Pattern Recognition, Automated - methods
performance evaluation
Printing
PSNR
Reproducibility of Results
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Telecommunications and information theory
Weight measurement
Performance evaluation
Document image binarization
ground truth
Image processing
Background noise
Printed document
False alarm rate
Document image processing
Image analysis
Weighting
Binary image
Metric
Manuscript character
Online AccessGet full text

Cover

More Information
Summary:Document image binarization is of great importance in the document image analysis and recognition pipeline since it affects further stages of the recognition process. The evaluation of a binarization method aids in studying its algorithmic behavior, as well as verifying its effectiveness, by providing qualitative and quantitative indication of its performance. This paper addresses a pixel-based binarization evaluation methodology for historical handwritten/machine-printed document images. In the proposed evaluation scheme, the recall and precision evaluation measures are properly modified using a weighting scheme that diminishes any potential evaluation bias. Additional performance metrics of the proposed evaluation scheme consist of the percentage rates of broken and missed text, false alarms, background noise, character enlargement, and merging. Several experiments conducted in comparison with other pixel-based evaluation measures demonstrate the validity of the proposed evaluation scheme.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2012.2219550