Low-Level cursive word representation based on geometric decomposition

Authors:
Jian-xiong Dong;Adam Krzyżak;Ching Y. Suen;Dominique Ponson
Affiliations:
IMDS Software, Montréal, Québec;Department of Computer Science and Software Engineering, Concordia University, Montréal, Québec, Canada;Center for Pattern Recognition and Machine Intelligence, Concordia University, Montréal, Québec, Canada;IMDS Software, Montréal, Québec
Venue:
MLDM'05 Proceedings of the 4th international conference on Machine Learning and Data Mining in Pattern Recognition
Year:
2005

Citing 6
Cited 0

Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques

IEEE Transactions on Pattern Analysis and Machine Intelligence
Hidden Markov model based word recognition and its application to legal amount reading on French checks

Computer Vision and Image Understanding - Special issue on document image understanding and retrieval
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Role of Holistic Paradigms in Handwritten Word Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition of Cursive Roman Handwriting - Past, Present and Future

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

An efficient low-level word image representation plays a crucial role in general cursive word recognition. This paper proposes a novel representation scheme, where a word image can be represented as two sequences of feature vectors in two independent channels, which are extracted from vertical peak points on the upper external contour and at vertical minima on the lower external contour, respectively. A data-driven method based on support vector machine is applied to prune and group those extreme points. Our experimental results look promising and have indicated the potential of this low-level representation for complete cursive handwriting recognition.