Writer Trait Identification from Hindi Handwriting: A ‎Hybrid Framework Combining Traditional And Deep ‎Learning Models

  • Authors

    • Parul Garg Department of Computer Science & Engineering, Giani Zail Singh Campus, College of Engineering and Technolo-gy (GZSCCET) Maharaja Ranjit Singh Punjab Technical University, Bathinda, Punjab, India
    • Dr. Naresh Kumar Garg Department of Computer Science & Engineering, Giani Zail Singh Campus, College of Engineering and Technolo-gy (GZSCCET) Maharaja Ranjit Singh Punjab Technical University, Bathinda, Punjab, India
    https://doi.org/10.14419/bng5xf18

    Received date: July 15, 2025

    Accepted date: August 18, 2025

    Published date: August 27, 2025

  • Writer Identification; Devanagari; CNN; ML; Age; Gender; Anxiety

  • Abstract

    Handwriting offers a unique behavioral biometric that can reveal critical information about a writer's identity and psychological state. This ‎study presents a hybrid classification framework for writer identification using Hindi handwritten text, with a focus on predicting age group, ‎gender, and anxiety level. A custom dataset was constructed containing diverse handwriting samples enriched with demographic and emotional metadata. The proposed system integrates both handcrafted features (HOG, ORB, LBP, SURF) and deep features extracted using ‎EfficientNet, evaluated using standalone classifiers (KNN, SVM), a hybrid ensemble (SVM + KNN), and a custom Convolutional Neural ‎Network (CNN). The hybrid models showed significant improvement over traditional classifiers, demonstrating the effectiveness of combining multiple feature representations. The CNN model outperformed all others, achieving accuracies of 83.7% for age prediction, 86.7% ‎for gender classification, and 76.8% for anxiety estimation. These findings validate the proposed approach as a robust solution for handwriting-based personal trait identification and open new avenues for intelligent, language-specific biometric systems in real-world applications ‎such as forensics, education, and psychological assessment‎.

  • References

    1. Kumar S (2009), Performance Comparison of Features on Devanagari Hand-printed Dataset. Proceedings of the IEEE, 2009, pp. 1–5.
    2. Rajput G.G., Ummapure S.B. (2019), Script Identification from Handwritten Document Images Using LBP Technique at Block Level. 2019 Inter-national Conference on Data Science and Communication (IconDSC), pp. 1–6. https://doi.org/10.1109/IconDSC.2019.8816944.
    3. Patil A., Dwivedi P. (2024), Enhanced Recognition of Handwritten Marathi Compound Characters using CNN-SVM Hybrid Approach. Fusion: Practice and Applications, Vol. 4, No. 2. https://doi.org/10.54216/FPA.140202.
    4. D., P., Ashok A., Reddy H. (2023), Comparative Analysis of Handwritten Text Recognition using CNN and SVM. 2023 International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), pp. 1–5. https://doi.org/10.1109/ICDCECE57866.2023.10150890.
    5. Manocha S., Tewari P. (2021), Devanagari Handwritten Character Recognition using CNN as Feature Extractor. 2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), pp. 1–5. https://doi.org/10.1109/SMARTGENCON51891.2021.9645786.
    6. Elleuch M., Maalej R., Kherallah M. (2016), A New Design Based-SVM of the CNN Classifier Architecture with Dropout for Offline Arabic Handwritten Recognition. Procedia Computer Science, Vol. 85, pp. 1712–1723. https://doi.org/10.1016/j.procs.2016.05.512.
    7. Darmatasia, Fanany M.I. (2017), Handwriting Recognition on Form Document Using Convolutional Neural Network and Support Vector Machines (CNN-SVM). 2017 5th International Conference on Information and Communication Technology (ICoIC7), pp. 1–6. https://doi.org/10.1109/ICoICT.2017.8074699.
    8. Niu X. (2011), Fusions of CNN and SVM Classifiers for Recognizing Handwritten Characters. PhD Thesis, University of Hagen, Germany.
    9. Benaissa A., Bahri A., El Allaoui A., Salahddine M.A. (2023), Transformative Progress in Document Digitization: An In-Depth Exploration of Ma-chine and Deep Learning Models for Character Recognition. Data and Metadata, Vol. 2, No. 3. https://doi.org/10.56294/dm2023174.
    10. Ali A., M. S. (2019), Arabic Handwritten Character Recognition Using Machine Learning Approaches. 2019 Fifth International Conference on Im-age Information Processing (ICIIP), pp. 187–192. https://doi.org/10.1109/ICIIP47207.2019.8985839.
    11. Nugroho N.E.W., Harjoko A. (2021), Transliteration of Hiragana and Katakana Handwritten Characters Using CNN-SVM. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), Vol. 15, No. 3, pp. 237–248. https://doi.org/10.22146/ijccs.66062.
    12. Maitra D.S., Bhattacharya U., Parui S.K. (2015), CNN Based Common Approach to Handwritten Character Recognition of Multiple Scripts. 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1021–1025. https://doi.org/10.1109/ICDAR.2015.7333916.
    13. Singh R., Sethi M. (2024), Deep Learning for Handwritten Hindi Character Recognition: A CNN-Based Implementation. 2024 1st International Conference on Advances in Computing, Communication and Networking (ICAC2N), pp. 138–143. https://doi.org/10.1109/ICAC2N63387.2024.10895622.
    14. Wang Y., Yu P. (2019), Offline Handwritten New Tai Lue Characters Recognition Using CNN-SVM. 2019 IEEE 2nd International Conference on Electronic Information and Communication Technology (ICEICT), pp. 636–639. https://doi.org/10.1109/ICEICT.2019.8846292.
    15. Berrich Y., Guennoun Z. (2022), Handwritten Digit Recognition System based on CNN and SVM. Signal & Image Processing Trends, Vol. 12, No. 1, pp. 123–131. https://doi.org/10.5121/csit.2022.121701.
    16. Dong X., Yu Z., Cao W., Shi Y., Ma Q. (2020), A survey on ensemble learning. Frontiers of Computer Science, 14(2), 241–258. https://doi.org/10.1007/s11704-019-8208-z.
    17. Opitz D., Maclin R. (1999), Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11, 169–198. https://doi.org/10.1613/jair.614.
    18. Sagi O., Rokach L. (2018), Ensemble learning: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), e1249. https://doi.org/10.1002/widm.1249.
    19. Schwartz R., Dodge J., Smith N.A., Etzioni O. (2020), Green AI. Communications of the ACM, 63(12), 54–63. https://doi.org/10.1145/3381831.
    20. Bonawitz K., Eichner H., Grieskamp W., Huba D., Ingerman A., Ivanov V., Kiddon C., Konečny J., Mazzocchi S., McMahan H.B., et al. (2019), Towards federated learning at scale: System design. Proceedings of Machine Learning and Systems, 1, 374–388.
    21. Sze V., Chen Y.-H., Emer J., Suleiman A., Zhang Z. (2017), Hardware for machine learning: Challenges and opportunities. In 2017 IEEE Custom Integrated Circuits Conference (CICC), pp. 1–8. https://doi.org/10.1109/CICC.2017.7993626.
    22. Ganaie M.A., Hu M., Malik A., Tanveer M., Suganthan P. (2022), Ensemble deep learning: A review. Engineering Applications of Artificial Intelli-gence, 115, 105151. https://doi.org/10.1016/j.engappai.2022.105151.
    23. He S., Schomaker L. (2021), GR-RNN: Global-context residual recurrent neural networks for writer identification. Pattern Recognition, 117, 107975. https://doi.org/10.1016/j.patcog.2021.107975.
    24. Bruno A., Moroni D., Martinelli M. (2023), Efficient deep learning approach for olive disease classification. In 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 889–894. https://doi.org/10.15439/2023F4794.
    25. Liu Z., Li S., Wang G., Wu L., Tan C., Li S.Z. (2024), Harnessing hard mixed samples with decoupled regularizer. Advances in Neural Information Processing Systems, 36.
    26. Marti U.-V., Bunke H. (2002), The IAM-database: An English sentence database for offline handwriting recognition. International Journal on Document Analysis and Recognition, 5(1), 39–46. https://doi.org/10.1007/s100320200071.
    27. Schomaker L., Vuurpijl L. (2000), Forensic writer identification: A benchmark data set and a comparison of two systems. In Proceedings of the 9th International Workshop on Frontiers in Handwriting Recognition.
    28. Liu C.-L., Yin F., Wang D.-H., Wang Q.-F. (2011), CASIA online and offline Chinese handwriting databases. In 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 37–41. https://doi.org/10.1109/ICDAR.2011.14.
    29. Louloudis G., Stamatopoulos N., Gatos B. (2011), ICDAR 2011 writer identification contest. In 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 1475–1479. https://doi.org/10.1109/ICDAR.2011.295.
    30. Louloudis G., Gatos B., Stamatopoulos N., Papandreou A. (2013), ICDAR 2013 competition on writer identification. In 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1397–1401. https://doi.org/10.1109/ICDAR.2013.280.
    31. R. T. Mim, S. A. H. Chowdhury and A. N. Mugdho, "An Autoencoder-Based Approach of Automatic Writer Identification from Biscriptual Char-acters," 2024 2nd International Conference on Information and Communication Technology (ICICT), Dhaka, Bangladesh, 2024, pp. 189-193, https://doi.org/10.1109/ICICT64387.2024.10839686.
    32. Kale SD, Sukte C, Hirve S, Shinde SK, Buchade A & Sable N (2025), Deep Learning-Based Hybridized Bi-LSTM Model for Author Identifica-tion in the Marathi Language. Advances in Nonlinear Variational Inequalities. https://doi.org/10.52783/anvi.v28.3222.

  • Downloads

  • How to Cite

    Garg, P. ., & Garg, D. N. K. . (2025). Writer Trait Identification from Hindi Handwriting: A ‎Hybrid Framework Combining Traditional And Deep ‎Learning Models. International Journal of Basic and Applied Sciences, 14(4), 698-706. https://doi.org/10.14419/bng5xf18