A Two-Stage System for Arabic Handwritten Digit Recognition Tested on a New Large Database.
Ezzat El‐Sherif, Sherif Abdelazeem · Artificial Intelligence and Pattern Recognition · 2007
In this paper, we introduce a new large Arabic Handwritten Digits dataBase (AHDBase). The AHDBase is composed of 60,000 digits for training and 10,000 digits for testing written by 700 persons of different ages and educational backgrounds. We also introduce a recognition system for Arabic handwritten digits with a recognition rate of 99.15 % and low recognition time. Our system is composed of two stages. The first stage is an Artificial Neural Network (ANN) fed with a short powerful feature vector for fast classification of non-ambiguous cases. First stage has a reject option to pass the ambiguous cases to the more powerful second stage. Second stage is slow yet powerful Support Vector Machine (SVM) fed with a large feature vector to classify the ambiguous cases rejected from first stage.