Vol. 6 No. 2 (2025)

Standard Journal Issues

Handwritten Recognition of Telugu Characters Using Various Pretrained Convolutional Neural Networks

Published 2025-09-16

  • Mukkoti Vishnu Vardhan
    • ,
  • E Jayakiran Reddy
    • ,
  • N Srinivas Reddy
    • ,
  • Dheeraj Joshi
    • ,
  • Shaik Hujefa Ayyub
    • ,
  • Vishal Pratap Mahajan
    • ,
  • Nishat Afshan Ansari

Mukkoti Vishnu Vardhan
Department of AI&ML, Sri Vasavi Engineering College, Tadepalligudem, Andhra Pradesh, India

E Jayakiran Reddy
Department of Mechanical Engineering, Sreenidhi Institute of science and Technology, Hyderabad, India

N Srinivas Reddy
Department of Mechanical Engineering, Vardhaman College of Engineering, Shamshabad, Hyderabad, Telangana, India

Dheeraj Joshi
Department of Mechanical Engineering, Vardhaman College of Engineering, Shamshabad, Hyderabad, Telangana, India

Shaik Hujefa Ayyub
R. C. Patel College of Engineering & Polytechnic, Shirpur, Dhule, Maharashtra, India

Vishal Pratap Mahajan
R. C. Patel College of Engineering & Polytechnic, Shirpur, Dhule, Maharashtra, India

Nishat Afshan Ansari
Department of Computer Science Engineering, IIIT Nagpur, Maharastra, India

Abstract

Telugu handwritten character recognition has seen significant advancements in recent years, particularly in the context of deep learning models such as Convolutional Neural Networks (CNNs). However, recognizing handwritten digits and scripts in multilingual settings, especially in a diverse country like India, presents unique challenges due to the variance in handwriting styles and the complexity of regional scripts. The proposed system addresses the challenges of diverse handwriting styles by leveraging the power of CNNs for automated handwriting recognition. Our first contribution is collecting the Telugu characters dataset. A larger dataset of 33,496 handwritten Telugu characters was collected from schoolchildren and adults of varying ages. We collected a larger corpus of 33,496 locally handwritten Telugu characters to study script variability. The experiments in this paper evaluate six vowels (1,200 images) from the public Kaggle set, serving as a focused benchmark; the larger corpus will be used in follow-up work and released separately. This project presents a deep learning-based approach to recognize handwritten Telugu vowels. To ensure optimal recognition performance, five Convolutional Neural Network (CNN) architectures LeNet, VGG16, ResNet50, DenseNet, and AlexNet were selected and evaluated for the task of Telugu character recognition. These models were rigorously trained, and the Adam optimizer is used to optimize the parameters. These models are evaluated, and their performance is compared. From the analysis, it is found that the VGG16 model showed the best results with a high accuracy of 98.14%.

Keywords

Handwritten recognition, Telugu vowels, Convolutional Neural Networks (CNN), Data augmentation, Deep learning models, Pretrained CNN models

PDF

References

  1. Murthy, P. V. R., & Prasad, C. G. V. N. (2019). Recognition of online handwritten Telugu letters for different domains and organizations. Journal of Critical Reviews, 6, 33–40.
  2. Anupama, A., Valli, K. V., & Satya, K. G. (2018). A deep learning approach to recognize handwritten Telugu characters using convolutional neural networks. International Journal of Information Systems & Management Science, 1(2).
  3. Bharadwaj, A. R., Venugopal, A., SuryaKiran, C., & Nageswara Rao, M. V. (2019). Telugu text extraction and recognition using convolutional and recurrent neural networks. International Journal of Engineering and Advanced Technology (IJEAT), 8, 1449–1451.
  4. Revathi, B., Prasad, M. V. D., & Naveen Kishore, G. (2024). Performance comparison of various CNN models for recognition of handwritten Telugu text. Journal of Electrical Systems, 20(7s), 3607–3619.
  5. Soujanya, B., Chittineni, S., Sitamahalakshmi, T., & Srinivas, G. (2022). A CNN based approach for handwritten character identification of Telugu Guninthalu using various optimizers. International Journal of Advanced Computer Science and Applications, 13(4). https://doi.org/10.14569/ijacsa.2022.0130482
  6. Aarthi, R., Varma, M., Vaishnavi, J. S., Prashanth, N. V. S., & Srikar, G. T. (2021). Performance analysis of Telugu characters using deep learning networks. In Lecture Notes in Electrical Engineering (pp. 311–322). Springer. https://doi.org/10.1007/978-981-15-9019-1_28
  7. Karapu, B. M., A. G. L., Elappila, M., & M. B. N. (2024). Handwritten Telugu character recognition using machine learning. In Proceedings of the 2024 International Conference on Data, Communication and Technology (pp. 1–6). IEEE. https://doi.org/10.1109/icdcot61034.2024.10515646
  8. Soujanya, B., & Sitamahalakshmi, T. (2020). Optimization with Adam and RMSprop in convolution neural network (CNN): A case study for Telugu handwritten characters. International Journal of Emerging Trends in Engineering Research, 8(9), 5116–5121. https://doi.org/10.30534/ijeter/2020/38892020
  9. Ashlin, G. S., Mohammed, Z., Sai, P., Raju, A. V., & Negi, A. (2023). A novel approach to recognize handwritten Telugu words using character level CNN. In 2023 4th International Conference for Emerging Technology (INCET) (pp. 1–5). IEEE. https://doi.org/10.1109/incet57972.2023.10170305
  10. Kalpana, B., & Hanmandlu, M. (2023). Offline handwritten basic Telugu optical character recognition (OCR) using convolution neural networks (CNN). In 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 1195–1200). IEEE.
  11. Reddy, J. M., & Reddy, A. V. (2019). Recognition of handwritten characters using deep convolutional neural network. International Journal of Innovative Technology and Exploring Engineering, 8(6S4), 314–317. https://doi.org/10.35940/ijitee.f1064.0486s419
  12. Wasalwar, Y. P., Bagga, K. S., Rao, P. B., & Dongre, S. (2023). Handwritten character recognition of Telugu characters. In 2022 IEEE 7th International Conference for Convergence in Technology (I2CT). IEEE. https://doi.org/10.1109/i2ct57861.2023.10126377
  13. Prathima, C., & Muppalaneni, N. B. (2021). Deep learning approach for prediction of handwritten Telugu vowels. In Smart Innovation, Systems and Technologies (pp. 367–374). Springer. https://doi.org/10.1007/978-981-33-4443-3_35
  14. Ganji, T., Velpuru, M. S., & Dugyala, R. (2021). Multi-variant handwritten Telugu character recognition using transfer learning. IOP Conference Series: Materials Science and Engineering, 1042, 012026. https://doi.org/10.1088/1757-899x/1042/1/012026
  15. Koteswararao, D., & Hedge, N. P. (2025). In-depth analysis and challenges of handwritten Telugu character recognition with an improved CNN model for solutions. In Raju, K. S., Senkerik, R., Kumar, T. K., Sellathurai, M., & Naresh Kumar, V. (Eds.), Intelligent Computing and Communication. ICICC 2024. Lecture Notes in Networks and Systems (Vol. 1241). Springer. https://doi.org/10.1007/978-981-96-1267-3_8
  16. Muppalaneni, N. B. (2020). Handwritten Telugu compound character prediction using convolutional neural networks. In 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE). IEEE. https://doi.org/10.1109/ic-ETITE47903.2020.349
  17. Devi, D. S., & Bindu, C. S. (2021). CNN architectures to recognize handwritten Telugu characters. In Satapathy, S. C., Bhateja, V., Favorskaya, M. N., & Adilakshmi, T. (Eds.), Smart Computing Techniques and Applications. Smart Innovation, Systems and Technologies (Vol. 225). Springer. https://doi.org/10.1007/978-981-16-0878-0_23
  18. Kakarla, S. (2020). Telugu 6 vowel dataset. Kaggle. https://www.kaggle.com/datasets/syamkakarla/telugu-6-vowel-dataset
  19. Rao, B. V. S., Rao, K. S., Thatha, V. N., Vamsi, B., Rao, J. N., & Ganiya, R. K. (2024). Unicode-powered handwritten Telugu-to-English character recognition and translation system using deep learning. International Journal of Intelligent Systems and Applications in Engineering, 12(10s), 515–525
  20. Pragada, P., & Rao, D. C. H. (2025). Automated LSTM based deep learning model for handwritten Telugu answer script analysis. Communications on Applied Nonlinear Analysis, 32(8s)
  21. Isaac, L. D., Manoj, N., Sukumar, M. E., & Srinivasan, M. (2025). Handwritten text recognition. AIP Conference Proceedings, 3279(1), 020050. https://doi.org/10.1063/5.0262895
  22. Inuganti, S., & Rajeshwara Rao, R. (2022). Recognition of online handwritten Telugu strokes by detected dominant points using curvature estimation. International Journal of Data Analysis Techniques and Strategies, 14(2), 140–158. https://doi.org/10.1504/IJDATS.2022.124754.
  23. Agyenta, C., & Justice. (2022). Skin lesion classification based on convolutional neural networks. Journal of Applied Science and Technology Trends, 3(1), 21–26. https://doi.org/10.38094/jastt301121.

Downloads

Download data is not yet available.

Similar Articles

31-40 of 65

You may also start an advanced similarity search for this article.