An Efficient Feature Extraction and Dimensionality Reduction Scheme for the Vitreous Arabic Numerals Recognition

摘要

In this paper, we present an on-line methodology for the Arabic Numeral Character recognition based on efficient feature extraction followed by a suitable feature vector dimensionality reduction scheme. We have designed a novel system for the recognition of vitreous digits. This new system aims at attaining a very high recognition rate and a very high reliability at the same time, in other words, achieving an excellent recognition performance of vitreous Arabic numeral character. Experiments conducted on the same or similar characters' feature extractions are shown with encouraging results: a high reliability of 83.5% with the first recognition, and a 98.62% correct recognition rate without rejection in the last cascade layer.