Neural Computing for Online Arabic Handwriting Character Recognition using Hard Stroke Features Mining

TL;DR

This paper presents an improved online Arabic handwriting recognition method that extracts critical stroke features, reduces token redundancy, and achieves high accuracy using a multilayer perceptron classifier.

Contribution

It introduces a novel stroke feature extraction technique and token minimization approach for enhanced Arabic character recognition accuracy.

Findings

Achieved 98.6% recognition accuracy on OHASD dataset.

Reduced token redundancy improves recognition efficiency.

Method outperforms some existing recognition techniques.

Abstract

Online Arabic cursive character recognition is still a big challenge due to the existing complexities including Arabic cursive script styles, writing speed, writer mood and so forth. Due to these unavoidable constraints, the accuracy of online Arabic character's recognition is still low and retain space for improvement. In this research, an enhanced method of detecting the desired critical points from vertical and horizontal direction-length of handwriting stroke features of online Arabic script recognition is proposed. Each extracted stroke feature divides every isolated character into some meaningful pattern known as tokens. A minimum feature set is extracted from these tokens for classification of characters using a multilayer perceptron with a back-propagation learning algorithm and modified sigmoid function-based activation function. In this work, two milestones are achieved; firstly, attain a fixed number of tokens, secondly, minimize the number of the most repetitive tokens. For experiments, handwritten Arabic characters are selected from the OHASD benchmark dataset to test and evaluate the proposed method. The proposed method achieves an average accuracy of 98.6% comparable in state of art character recognition techniques.