Graham Kendall
Various Images

Professor Graham Kendall

Professor Graham Kendall is the Provost and CEO of The University of Nottingham Malaysia Campus (UNMC). He is also a Pro-Vice Chancellor of the University of Nottingham.

He is a Director of MyResearch Sdn Bhd, Crops for the Future Sdn Bhd. and Nottingham Green Technologies Sdn Bhd. He is a Fellow of the British Computer Society (FBCS) and a Fellow of the Operational Research Society (FORS).

He has published over 230 peer reviewed papers. He is an Associate Editor of 10 journals and the Editor-in-Chief of the IEEE Transactions of Computational Intelligence and AI in Games.

News

I have published a number of papers on Cutting and Packing
http://bit.ly/dQPw7T
The hunt for MH370
http://bit.ly/1DXRLbu

Latest Blog Post

Snooker: Celebrating 40 years at the Crucible

Random Blog Post

EURO 2009 Conference

Publication(s)

Scheduling English Football Fixtures over the Holiday Period Using Hyper-heuristics
http://bit.ly/eeIVyB
The importance of a piece difference feature to Blondie24
http://bit.ly/1a2Ns0W
Learning versus Evolution in Iterated Prisoner's Dilemma
http://bit.ly/eWgsgR
Barriers to implementation of IT in educational institutions
http://bit.ly/1zUkd8s

Graham Kendall: Details of Requested Publication


Citation

Ibrahim, Z; Isa, D; Rajkumar, R and Kendall, G Document Zone Classification for Technical Document Images Using Artificial Neural Network and Support Vector Machines. In Second International Conference on the Applications of Digital Information and Web Technologies, pages 345-350, 2009.


Abstract

Artificial Neural Networks (ANN) are a classic pattern classifier and widely applicable to various problems and are relatively easy to use. Three of the most popular ANNs are Multilayer Perceptron (MLP) with Backpropagation learning algorithm, Self Organizing Map (SOM) and Recurrent Neural Network (RNN). Support Vector Machines (SVM) have gained great interest in the last few years in pattern recognition. Thus, this research compares the recognition performance of text and non-text images (text, table, figure and graph) from technical document images based on the pixel intensity of various zones between BPNN, SOM, RNN and SVM. Symmetrical and non-symmetrical zoning algorithms were compared as input. 400 different datasets have been tested and the experiments indicate that SVM classification is superior to the other three classifiers. The experiments also indicate that the combination of symmetrical and non-symmetrical zoning design is better than non-symmetrical or symmetrical zoning only.


pdf

You can download the pdf of this publication from here


doi

The doi for this publication is 10.1109/ICADIWT.2009.5273957 You can link directly to the original paper, via the doi, from here

What is a doi?: A doi (Document Object Identifier) is a unique identifier for sicientific papers (and occasionally other material). This provides direct access to the location where the original article is published using the URL http://dx.doi/org/xxxx (replacing xxx with the doi). See http://dx.doi.org/ for more information



URL

This pubication does not have a URL associated with it.

The URL is only provided if there is additional information that might be useful. For example, where the entry is a book chapter, the URL might link to the book itself.


Bibtex

@INPROCEEDINGS{iirk2009, author = {Z. Ibrahim and D. Isa and R. Rajkumar and G. Kendall},
title = {Document Zone Classification for Technical Document Images Using Artificial Neural Network and Support Vector Machines},
booktitle = {Second International Conference on the Applications of Digital Information and Web Technologies},
year = {2009},
pages = {345--350},
abstract = {Artificial Neural Networks (ANN) are a classic pattern classifier and widely applicable to various problems and are relatively easy to use. Three of the most popular ANNs are Multilayer Perceptron (MLP) with Backpropagation learning algorithm, Self Organizing Map (SOM) and Recurrent Neural Network (RNN). Support Vector Machines (SVM) have gained great interest in the last few years in pattern recognition. Thus, this research compares the recognition performance of text and non-text images (text, table, figure and graph) from technical document images based on the pixel intensity of various zones between BPNN, SOM, RNN and SVM. Symmetrical and non-symmetrical zoning algorithms were compared as input. 400 different datasets have been tested and the experiments indicate that SVM classification is superior to the other three classifiers. The experiments also indicate that the combination of symmetrical and non-symmetrical zoning design is better than non-symmetrical or symmetrical zoning only.},
doi = {10.1109/ICADIWT.2009.5273957},
owner = {gxk},
timestamp = {2011.12.08},
webpdf = {http://www.graham-kendall.com/papers/iirk2009.pdf} }