Language independent skew estimation technique based on Gaussian mixture models: a case study on South Indian scripts

Authors:
V. N. Manjunath Aradhya;Ashok Rao;G. Hemantha Kumar
Affiliations:
Dept of Studies in Computer Science, University of Mysore, Mysore, India;Dept of Electronics and Communication, S.J. College of Engineering, Mysore, India;Dept of Studies in Computer Science, University of Mysore, Mysore, India
Venue:
PReMI'07 Proceedings of the 2nd international conference on Pattern recognition and machine intelligence
Year:
2007

Citing 10
Cited 1

Automated entry system for printed documents

Pattern Recognition
Skew correction of document images using interline cross-correlation

CVGIP: Graphical Models and Image Processing
An improved document skew angle estimation technique

Pattern Recognition Letters
Digital Document Processing

Digital Document Processing
Digital Image Processing

Digital Image Processing
Skew detection and correction in document images based on straight-line fitting

Pattern Recognition Letters
A nearest-neighbor chain based approach to skew estimation in document images

Pattern Recognition Letters
A new algorithm for skew detection and correction

Pattern Recognition Letters
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Text line extraction from multi-skewed handwritten documents

Pattern Recognition

Document skew estimation: an approach based on wavelets

Proceedings of the 2011 International Conference on Communication, Computing & Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

During document scanning, skew is inevitably introduced into the incoming document image. Presence of additional modified characters, which get plugged in as extensions and remain as disjointed protrusions of a main character is really challenging in estimating inclination in skewed documents made up of texts in south Indian languages (Kannada, Telugu, Tamil and Malayalam). In this paper, we present a novel script independent (for south Indian) skew estimation technique based on Gaussian Mixture Models (GMM). The Expectation-Maximization (EM) algorithm is used to learn the mixture of Gaussians. Subsequently the cluster means are subjected to moments to estimate the skew angle. Experiments on printed and handwritten documents corrupted by noise is done. Our method shows significantly improved performance as compared to other existing methods.