A multiexpert framework for character recognition: a novel application of Clifford networks

• Published in: IEEE transactions on neural networks Vol. 12; no. 1; pp. 101 - 112
• Main Authors: Rahman, A.F.R., Howells, W.G.J., Fairhurst, M.C.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2001
• Subjects: Algebra; Character recognition; Data analysis; Data mining; Data storage; Feature extraction; Handwriting recognition; Mathematical analysis; Memory; Multidimensional data; Multidimensional systems; Multilayer perceptrons; Networks; Neural networks; Recognition; Robustness
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/72.896799

A novel multiple-expert framework for recognition of handwritten characters is presented. The proposed framework is composed of multiple classifiers (experts) put together in such a manner as to enhance the recognition capability of the combined network compared to the best performing individual expert participating in the framework. Each of these experts has been derived from a novel neural structure in which the weight values are derived from Clifford algebra. A Clifford algebra is a mathematical paradigm capable of capturing the interdimensional dependencies found in multidimensional data. It offers a technique for concise data storage and processing by representing dependencies between the component dimensions of the data which is otherwise difficult to encode and hence is often employed in analyzing multidimensional data. Results achieved by the proposed multiple-expert framework demonstrates significant improvement over alternative techniques.