Deciphering Excellence: Comparative Study of Deep Learning Models in Handwriting Recognition
Keywords:
Convolutional Neural Network, Deep Learning, Handwritten Character Recognition, Optical Character Recognition, Pattern Recognition, Recurrent Neural NetworkAbstract
In the digital age, handwritten character recognition (HCR) is a vital technique that makes handwritten text easier to read and use by converting it into a machine-encoded format. Handwritten words, symbols, or characters can be automatically recognized and interpreted using HCR. The main objective of HCR is to transform handwritten text into machine-encoded text and make it readable and usable in digital formats. This technology falls under the category of optical character recognition (OCR), which is a broad term that includes handwritten and printed text recognition. This paper presents an efficient HCR model that makes use of Deep Convolutional Neural Networks (DCNN) with variable filters and feature fusion. The model's performance is gauged using a handcrafted dataset, and comparative analysis is conducted with CNN+ Bi-LSTM and CNN+ Bi-GRU models. The suggested Deep CNN with Variable Filters and Feature Fusion Model surpasses the other models with an accuracy of 98.86%. The findings underscore the effectiveness of merging sequential and convolutional modelling approaches and stress the need for complex architectures to achieve the best accuracy possible in HCR challenges. This study advances the field and emphasizes the importance of technological innovation in enhancing data input techniques across businesses, digitizing manuscripts, and protecting cultural heritage.
Downloads
References
Srihari, S. N., Cha, S. H., Arora, H., & Lee, S. (2002). Individuality of handwriting. Journal of forensic sciences, 47(4), 856-872.
Pal, A., & Singh, D. (2010). Handwritten English character recognition using neural network. International Journal of Computer Science & Communication, 1(2), 141-144.
OAM, P. W., & Crew, G. (2018). The future of handwriting. TEXT, 22(Special 52), 1 10.
Pal, U., Jayadevan, R., & Sharma, N. (2012). Handwriting recognition in indian regional scripts: a survey of offline techniques. ACM Transactions on Asian Language Information Processing (TALIP), 11(1), 1-35.
Chaudhuri, A., Mandaviya, K., Badelia, P., K Ghosh, S., Chaudhuri, A., Mandaviya, K., ... & Ghosh, S. K. (2017). Optical character recognition systems (pp. 9-41). Springer International Publishing.
Aparna, K. H., Subramanian, V., Kasirajan, M., Prakash, G. V., Chakravarthy, V. S., & Madhvanath, S. (2004, October). Online handwriting recognition for Tamil. In Ninth international workshop on frontiers in handwriting recognition (pp. 438-443). IEEE.
Chatterji, B. N. (1986). Feature extraction methods for character recognition. IETE Technical Review, 3(1), 9-22.
Graves, A., & Schmidhuber, J. (2008). Offline handwriting recognition with multidimensional recurrent neural networks. Advances in neural information processing systems, 21.
Gupta, A., Srivastava, M., & Mahanta, C. (2011, December). Offline handwritten character recognition using neural network. In 2011 IEEE International Conference on Computer Applications and Industrial Electronics (ICCAIE) (pp. 102-107). IEEE.
Maitra, D. S., Bhattacharya, U., & Parui, S. K. (2015, August). CNN based common approach to handwritten character recognition of multiple scripts. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (pp. 1021-1025). IEEE.
Nishide, S., Okuno, H. G., Ogata, T., & Tani, J. (2011, October). Handwriting prediction-based character recognition using recurrent neural network. In 2011 IEEE International Conference on Systems, Man, and Cybernetics (pp. 2549-2554). IEEE.
Pashine, S., Dixit, R., & Kushwah, R. (2021). Handwritten digit recognition using machine and deep learning algorithms. arXiv preprint arXiv:2106.12614.
Khandokar, I., Hasan, M., Ernawan, F., Islam, S., & Kabir, M. N. (2021, June). Handwritten character recognition using convolutional neural network. In Journal of Physics: Conference Series (Vol. 1918, No. 4, p. 042152). IOP Publishing.
KARAKAYA, R., & KAZAN, S. (2021). Handwritten digit recognition using machine learning. Sakarya university journal of science, 25(1), 65-71.
Nurseitov, D., Bostanbekov, K., Kanatov, M., Alimova, A., Abdallah, A., & Abdimanap, G. (2021). Classification of handwritten names of cities and handwritten text recognition using various deep learning models. arXiv preprint arXiv:2102.04816.
Ahmed, R. M., Rashid, T. A., Fattah, P., Alsadoon, A., Bacanin, N., Mirjalili, S., ... & Chhabra, A. (2022). Kurdish Handwritten character recognition using deep learning techniques. Gene Expression Patterns, 46, 119278.
Hamdan, Y. B., & Sathesh, A. (2021). Construction of statistical SVM based recognition model for handwritten character recognition. Journal of Information Technology and Digital World, 3(2), 92-107.
Kusetogullari, H., Yavariabdi, A., Hall, J., & Lavesson, N. (2021). DIGITNET: A deep handwritten digit detection and recognition method using a new historical handwritten digit dataset. Big Data Research, 23, 100182.
Popli, R., Kansal, I., Garg, A., Goyal, N., & Garg, K. (2021). Classification and recognition of online hand-written alphabets using machine learning methods. In IOP Conference Series: Materials Science and Engineering (Vol. 1022, No. 1, p. 012111). IOP Publishing.
Zin, T. T., Thant, S., Pwint, M. Z., & Ogino, T. (2021). Handwritten character recognition on android for basic education using convolutional neural network. Electronics, 10(8), 904.
Gope, B., Pande, S., Karale, N., Dharmale, S., & Umekar, P. (2021). Handwritten digits identification using MNIST database via machine learning models. In IOP conference series: materials science and engineering (Vol. 1022, No. 1, p. 012108). IOP Publishing.
Chychkarov, Y., Serhiienko, A., Syrmamiikh, I., & Kargin, A. (2021). Handwritten Digits Recognition Using SVM, KNN, RF and Deep Learning Neural Networks. CMIS, 2864, 496-509.
Jabde, M., Patil, C., Mali, S., & Vibhute, A. (2022, August). Comparative Study of Machine Learning and Deep Learning Classifiers on Handwritten Numeral Recognition. In International Symposium on Intelligent Informatics (pp. 123-137). Singapore: Springer Nature Singapore.
Guo, H., Liu, Y., Yang, D., & Zhao, J. (2022). Offline handwritten Tai Le character recognition using ensemble deep learning. The Visual Computer, 38(11), 3897-3910.
Narang, S. R., Kumar, M., & Jindal, M. K. (2021). DeepNetDevanagari: a deep learning model for Devanagari ancient character recognition. Multimedia Tools and Applications, 80, 20671-20686.
Balaha, H. M., Ali, H. A., Youssef, E. K., Elsayed, A. E., Samak, R. A., Abdelhaleem, M. S., ... & Mohammed, M. M. (2021). Recognizing Arabic handwritten characters using deep learning and genetic algorithms. Multimedia Tools and Applications, 80, 32473-32509.
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., ... & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, 8, 1-74.
Scherer, Dominik, Andreas Muller, and Sven Behnke, “Evaluation of pooling ¨ operations in convolutional architectures for object recognition,” International Conference on Artificial Neural Networks, Springer, Berlin, Heidelberg, pp.92- 101, 2010.
Shamim, S. M., Miah, M. B. A., Sarker, A., Rana, M., & Al Jobair, A. (2018). Handwritten digit recognition using machine learning algorithms. Global Journal Of Computer Science And Technology, 18(1), 17-23.
Bora, M. B., Daimary, D., Amitab, K., & Kandar, D. (2020). Handwritten character recognition from images using CNN-ECOC. Procedia Computer Science, 167, 2403-2409.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
