Title :
Recognition of handwritten characters with a multi-expert system
Author :
Rahman, A.F.R. ; Fairhurst, M.C.
Author_Institution :
Electron. Eng. Labs., Kent Univ., Canterbury, UK
Abstract :
A new multi-expert handwritten classification system has been introduced. It is shown that an intelligent combination of decisions taken by multiple experts can greatly enhance the final classification performance. A logical structure for the formation of a practical multi-expert hierarchical structure implementing multiple decision combination is presented and its performance is evaluated on both numeral and alpha-numeric handwritten character datasets
Keywords :
expert systems; image classification; optical character recognition; alphanumeric handwritten character datasets; handwriting classification; handwritten character recognition; multi-expert system; numeral handwritten character datasets;
Conference_Titel :
Handwriting Analysis and Recognition - A European Perspective, IEE Workshop on
Conference_Location :
London
DOI :
10.1049/ic:19960926
