Classification of Non-native Handwritten Characters Using Convolutional Neural Network

TL;DR

This paper introduces a custom CNN model trained on a new dataset to improve the classification accuracy of non-native handwritten English characters, addressing variability in handwriting styles.

Contribution

The authors propose a tailored CNN architecture and a new dataset for non-native English handwriting recognition, achieving higher accuracy than existing models.

Findings

Proposed CNN achieves 97.04% accuracy on HIEC dataset.

Model outperforms state-of-the-art with a 4.38% relative improvement.

Ablation study identifies optimal hyperparameters for the CNN.

Abstract

The use of convolutional neural networks (CNNs) has accelerated the progress of handwritten character classification/recognition. Handwritten character recognition (HCR) has found applications in various domains, such as traffic signal detection, language translation, and document information extraction. However, the widespread use of existing HCR technology is yet to be seen as it does not provide reliable character recognition with outstanding accuracy. One of the reasons for unreliable HCR is that existing HCR methods do not take the handwriting styles of non-native writers into account. Hence, further improvement is needed to ensure the reliability and extensive deployment of character recognition technologies for critical tasks. In this work, the classification of English characters written by non-native users is performed by proposing a custom-tailored CNN model. We train this CNN with a new dataset called the handwritten isolated English character (HIEC) dataset. This dataset consists of 16,496 images collected from 260 persons. This paper also includes an ablation study of our CNN by adjusting hyperparameters to identify the best model for the HIEC dataset. The proposed model with five convolutional layers and one hidden layer outperforms state-of-the-art models in terms of character recognition accuracy and achieves an accuracy of $\mathbf{97.04}$%. Compared with the second-best model, the relative improvement of our model in terms of classification accuracy is $\mathbf{4.38}$%.