Sreya Adhikary,
Arnab Das,
Sankhadip Chowdhury,
- Student, Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning), Institute of Engineering and Management, Kolkata, West Bengal, India
- Student, Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning), Institute of Engineering and Management, Kolkata, West Bengal, India
- Student, Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning), Institute of Engineering and Management, Kolkata, West Bengal, India
Abstract
This article provides detailed information about handwriting text recognition. Some human characteristics are unique to the individual. Writing is one of the scientifically proven habits that is different for everyone. Handwriting Text Recognition (HTR) is responsible for identifying written characters and converting them into digital text. HTR is an intensively researched area, but improvements can still be made in accuracy and efficiency. Digitization of manuscripts is very useful in today’s world because it allows information to be easily accessed anytime and anywhere. Digitized books can be used for commercial purposes and are safer and more environmentally friendly than textbooks. This review will highlight the various applications made so far in this field along with their advantages, limitations, and realities. Considering the amount of data collected in the human industry, optical character recognition (OCR) of data is very useful. Optical recognition is a scientific method that can transform various types of data or images into identifiable, editable and searchable data. Over the years, researchers have used AI/machine learning tools to automatically analyze written and printed documents to convert them into electronic documents. The purpose of this article is to conduct an extensive investigation of the various deep convolutional neural networks that can provide improved accuracy for offline cursive handwriting recognition for English language. The research methodology with the following five different phases such as acquiring the data, pre-processing, feature extraction, classification and finally the evaluation and model enhancement was applied for this study.
Keywords: OCR, HTR, Deep Learning, CNN, Digitization
[This article belongs to International Journal of Radio Frequency Innovations(ijrfi)]
References
- Bezerra, Zanchettin, C. and de Andrade, V. (2012). A MDRNN-SVM Hybrid Model for Cursive Offline Handwriting Recognition. Artificial Neural Networks and Machine Learning – ICANN 2012, pp.246-254.
- Khan, Sohail, A. Zahoora, U. and Qureshi, A. (2020). A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review.doi: 10.1007/s10462-020-09825-6
- Lee, and Verma, B., (2012) Binary segmentation algorithm for English cursive handwriting recognition. Pattern Recognition, 454, pp.1306–1317.
- Putra, E.W. and Supriana, I., (2015) Structural offline handwriting character recognition using levenshtein distance. Proceedings – 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015, August, pp.31–36.
- Rahman, and Verma, B., (2013) Effect of ensemble classifier composition on offline cursive character recognition. Information Processing and Management, 494, pp.852–864.
- Fitrianingsih, F., Madenda, S., Ernastuti, E., Widodo, S. and Rodiah, R., (2017) Cursive Handwriting Segmentation using Ideal Distance International Journal of Electrical and Computer Engineering (IJECE), 75, p.2863.
- Dasgupta, J., Bhattacharya, and Chanda, B., (2016) A holistic approach for Off-line handwritten cursive word recognition using directional feature based on Arnold transform. Pattern Recognition Letters, [online] 79, pp.73–79. Available at: http://dx.doi.org/10.1016/j.patrec.2016.05.017.
- Birnberg, G., (2011) A Proposed Framework for Behavioral. 231, pp.1–43.
- Hepzi, L., I.Muthumani and S.Selvabharathi, (2017) English Cursive Hand written Character Recognition. 117, pp.57–63.
- Yann LeCun, Leon Bottou, Yoshua Bengio, H., (1998) A B7CEDGF HIB7PRQTSUDGQICWVYX HIB edCdSISIXvg5r ` CdQTw XvefCdS. PROC. of The IEEE. [online] Available at: http://ieeexplore.ieee.org/document/726791/#full-text-section.
- Gonzalez, F., (2012) Handbook of approximation algorithms and metaheuristics. Handbook of Approximation Algorithms and Metaheuristics, pp.1– 1432.
- Simonyan, and Zisserman, A., (2015) Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations, ICLR 2015 – Conference Track Proceedings, pp.1–14.
Volume | 02 |
Issue | 01 |
Received | May 31, 2024 |
Accepted | June 27, 2024 |
Published | July 30, 2024 |