A systematic review of multilingual numeral recognition systems

Abstract

Multilingual numeral recognition systems in online-offline environments play an essential role in several applications like banking or financial transactions, educational sectors, hospitals, etc. Several approaches have been proposed and executed for multilingual numeral recognition for various languages. This study systematically reviews eighty-four articles on the current research on multilingual numeral recognition in offline and online environments. According to the screening criteria, 489 relevant studies were retrieved from standard databases, and only 84 studies were used for further analysis based on the insertion and elimination measures. Our study investigates and analyzes the earlier approaches, datasets developed and utilized, and machine and deep learning methods applied in multilingual numeral recognition across different languages and handwritings. It also provides possible applications and challenges for future studies. Our analysis shows that some datasets are available for scientific research, but comprehensive multilingual datasets and cross-lingual models for multilingual recognition systems are urgently needed. In addition, this review finds that convolutional neural networks (CNN) and support vector machines (SVM) are mainly applied methods in multilingual numeral recognition due to their high recognition accuracy. The findings of this review will provide valuable insights for researchers directing the development of multilingual datasets and robust and effective systems for offline and online multilingual numeral recognition for several multilingual applications.