Multiple line skew estimation of handwritten images of documents based on a visual perception approach

Authors:
Carlos A. B. Mello;Ángel Sánchez;George D. C. Cavalcanti
Affiliations:
Center of Informatics, Federal University of Pernambuco, Recife, PE, Brazil;Rey Juan Carlos University, Madrid, Spain;Center of Informatics, Federal University of Pernambuco, Recife, PE, Brazil
Venue:
CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part II
Year:
2011

Citing 15
Cited 0

Document image analysis

Document image analysis
A fast parallel algorithm for thinning digital patterns

Communications of the ACM
Analysis and interpretation of visual saliency for document functional labeling

International Journal on Document Analysis and Recognition
Digital Image Processing (3rd Edition)

Digital Image Processing (3rd Edition)
Separating Lines of Text in Free-Form Handwritten Historical Documents

DIAL '06 Proceedings of the Second International Conference on Document Image Analysis for Libraries
Estimation of skew angles for scanned documents based on piecewise covering by parallelograms

Pattern Recognition
Text line extraction from multi-skewed handwritten documents

Pattern Recognition
On Skew Estimation and Correction of Text

CGIV '07 Proceedings of the Computer Graphics, Imaging and Visualisation
Fast and Accurate Detection of Document Skew and Orientation

ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02
A Robust Document Skew Estimation Algorithm Using Mathematical Morphology

ICTAI '07 Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence - Volume 01
A rotation method for binary document images using DDA algorithm

Proceedings of the eighth ACM symposium on Document engineering
A Rule Based Approach for Skew Correction and Removal of Insignificant Data from Scanned Text Documents of Devanagari Script

SITIS '07 Proceedings of the 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System
Skew Estimation and Segmentation of Text Line in Video Frames

ISIP '08 Proceedings of the 2008 International Symposiums on Information Processing
Skew Estimation and Correction of Text Using Bounding Box

CGIV '08 Proceedings of the 2008 Fifth International Conference on Computer Graphics, Imaging and Visualisation
Fast and robust skew estimation of scanned documents through background area information

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces Viskew: a new algorithm to estimate the skew of text lines in digitized documents. The algorithm is based on a visual perception approach where transition maps and morphological operators simulate human visual perception of documents. The algorithm was tested in a set of 19,500 synthetic text line images and 400 images of documents with multiple skew angles. The skew angles for the synthetic dataset are known and our algorithm achieved the lowest mean square error in average when compared with two other algorithms.