2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 14 , Issue 2 , PP: 26-42, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
Ashwini Patil 1 * , Puneet Dwivedi 2
Doi: https://doi.org/10.54216/FPA.140202
This study presents a hybrid recognition system for multi-class compound Marathi characters, which addresses the problem of handwritten Marathi character recognition. The methodology efficiently bridges the gap between feature extraction and classification by integrating a Convolutional Neural Network (CNN) and Support Vector Machine (SVM). The first step is gathering and preprocessing a wide range of handwritten Marathi compound characters that are written in different styles. Using conventional supervised learning methods, the CNN is trained on this dataset, paying special attention to data augmentation and validation in order to reduce overfitting. High-level features taken from the final fully connected layer of the CNN are fed into an SVM classifier in the next step. By using these features in its training, the SVM improves prediction accuracy. For multi-class classification, the one-vs-all method is used. The hybrid CNN-SVM algorithm demonstrates its effectiveness in the crucial phases of feature extraction and classification by identifying handwritten compound Marathi characters with remarkable accuracy. Evaluation metrics, such as accuracy, precision, recall, F1-score, and confusion matrix analysis, are employed in the process of evaluating the effectiveness of the model. This assessment is carried out on a different testing dataset, offering a thorough examination of the model's functionality. The proposed algorithm demonstrates its superior performance and potential for improved character recognition by achieving training accuracy of 98.60% and validation accuracy of 97.69%. The development of handwriting recognition systems has benefited greatly from this research, especially when it comes to intricate scripts like Marathi. The suggested hybrid algorithm shows encouraging outcomes and has a great deal of potential for use in document processing, natural language comprehension, and character recognition in languages that use the Marathi script. Subsequent efforts will centre on refining the model and investigating ensemble methods to increase the robustness and accuracy of recognition.
Character Recognition , Compound Marathi character , CNN-SVM algorithm , Convolutional Neural Networks (CNNs) , HCR , OCR.
[1] Momeni, Saleh & Baba Ali, Bagher. (2023). A Transformer-based Approach for Arabic Offline Handwritten Text Recognition.
[2] Ajmire, Prafulla & Warkhede, Shankar. (2018). An Analytical Study of Devanagari Script Recognition.
[3] Sachdeva, Juhee & Mittal, Sonu & Yean, Len. (2022). Handwritten Offline Devanagari Compound Character Recognition Using CNN. 10.1007/978-981-16-6289-8_18.
[4] Kale, Karbhari & Chavan, Shriniwas & Kazi, Majharoddin & Rode, Yogesh. (2013). Handwritten Devanagari Compound Character Recognition Using Legendre Moment: An Artificial Neural Network Approach. 10.1109/ISCBI.2013.62.
[5] Gupta, Piyush, et al. "Convolutional Neural Network based Handwritten Devanagari Character Recognition." 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE). IEEE, 2020.
[6] Rani, N. Shobha, et al. "Deep Learning Network Architecture based Kannada Handwritten Character Recognition." 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA). IEEE, 2020.
[7] Prof. Parvaneh Basaligheh. (2017). Design and Implementation of High Speed Vedic Multiplier in SPARTAN 3 FPGA Device. International Journal of New Practices in Management and Engineering, 6(01), 14 - 19. Retrieved from http://ijnpme.org/index.php/IJNPME/article/view/51
[8] Sahu, Anupama, and S. N. Mishra. "Odia Handwritten Character Recognition with Noise using Machine Learning." 2020 IEEE International Symposium on Sustainable Energy, Signal Processing and Cyber Security (iSSSC). IEEE, 2020.
[9] Gurav, Yash, et al. "Devanagari Handwritten Character Recognition using Convolutional Neural Networks." 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE). IEEE, 2020.
[10] Narang, Sonika Rani, Munish Kumar, and Manish Kumar Jindal."DeepNetDevanagari: a deep learning model for Devanagari ancient character recognition." Multimedia Tools and Applications 80.13 (2021): 20671-20686.
[11] Sarangi, D. P. K. (2022). Malicious Attacks Detection Using Trust Node Centric Weight Management Algorithm in Vehicular Platoon. Research Journal of Computer Systems and Engineering, 3(1), 56–61. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/42
[12] Inkeaw, Papangkorn, Piyachat Udomwong, and Jeerayut Chaijaruwanich. "Density based semi-automatic labeling on multi-feature representations for ground truth generation: Application to handwritten character recognition." Knowledge-Based Systems 220 (2021): 106953.
[13] Mane, Deepak T., Rushikesh Tapdiya, and Swati V. Shinde."Handwritten Marathi numeral recognition using stacked ensemble neural network." International Journal of Information Technology (2021): 1-7.
[14] Geetha, R., T. Thilagam, and T. Padmavathy. "Effective offline handwritten text recognition model based on a sequence-to-sequence approach with CNN–RNN networks." Neural Computing and Applications (2021): 1-12.
[15] Bhati, Gaurav Singh, and Akhil Ranjan Garg. "Handwritten Devanagari Character Recognition Using CNN with Transfer Learning." Congress on Intelligent Systems. Springer, Singapore, 2020.
[16] Jain, Mayank, et al. "Handwritten Digit Recognition Using CNN." 2021 International Conference on Innovative Practices in Technology and Management (ICIPTM). IEEE, 2021.
[17] Moore, B., Clark, R., Martinez, J., Rodriguez, A., & Rodriguez, L. Anomaly Detection in Internet of Things (IoT) Data Streams. Kuwait Journal of Machine Learning, 1(4). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/151
[18] Dokare, Indu, et al. "Recognition of Handwritten Devanagari Character using Convolutional Neural Network." 2021 3rd International Conference on Signal Processing and Communication (ICPSC). IEEE, 2021.
[19] Sharma, N.; Pal, U.; Kimura, F.; Pal, S. Recognition of offline handwritten Devanagari characters using quadratic classifier. In Computer Vision, Graphics and Image Processing; Springer: Berlin/Heidelberg, Germany, 2006; pp. 805–816.
[20] Hanmandlu, M.; Murthy, O.V.R.; Madasu, V.K. Fuzzy Model based recognition of handwritten Hindi characters. In Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications, Glenelg, Australia, 3–5 December 2007; pp. 454–461.
[21] Kumar, S. Performance comparison of features on Devanagari handprinted dataset. Int. J. Recent Trends 2009, 1, 33–37.
[22] Pal, U.; Sharma, N.; Wakabayashi, T.; Kimura, F. Offline handwritten character recognition of Devanagari script. In Proceedings of the Ninth International Conference on Document Analysis and Recognition, Curitiba, Parana, Brazil, 23–26 September 2007; Volume 1, pp. 496–500.
[23] P. Gupta, S. Deshmukh, S. Pandey, K. Tonge, V. Urkunde and S. Kide (2020), "Convolutional Neural Network based Handwritten Devanagari Character Recognition," 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), pp. 322-326, doi: 10.1109/ICSTCEE49637.2020.9277222.
[24] Narang, Sonika Rani, Munish Kumar, and Manish Kumar Jindal.(2021) "DeepNetDevanagari: a deep learning model for Devanagari ancient character recognition." Multimedia Tools and Applications 80.13:20671-20686.
[25] Dokare, Indu, et al.(2021) "Recognition of Handwritten Devanagari Character using Convolutional Neural Network." 2021 3rd International Conference on Signal Processing and Communication (ICPSC). IEEE.
[26] Deore, Shalaka Prasad, and Albert Pravin.(2020) "Devanagari Handwritten Character Recognition using fine-tuned Deep Convolutional Neural Network on trivial dataset." Sadhana 45.1: 1-13.
[27] Bhagat et al.(2020) "Devanagari Handwritten Character Recognition using Convolutional Neural Networks." 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE). IEEE.
[28] Chen L, Li S, Bai Q, Yang J, Jiang S, Miao Y. Review of Image Classification Algorithms Based on Convolutional Neural Networks. Remote Sensing. 2021; 13(22):4712.
[29] Yamashita, R., Nishio, M., Do, RKG et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging 9, (2018): 611–629.
[30] KC Santosh, Nibaran Das, Swarnendu Ghosh, "Chapter 2 - Deep learning: a review," In Primers in Biomedical Imaging Devices and Systems, Deep Learning Models for Medical Imaging, Academic Press, 2022, 29-63, ISBN 9780128235041
[31] Gholamalinezhad, H., & Khosravi, H. (2020). Pooling Methods in Deep Neural Networks, a Review. ArXiv, abs/2009.07485.
[32] Montesinos López, O.A., Montesinos López, A., Crossa, J. (2022). Fundamentals of Artificial Neural Networks and Deep Learning. In: Multivariate Statistical Machine Learning Methods for Genomic Prediction. Springer, Cham.
[33] Hassan, E., Shams, M.Y., Hikal, N.A. et al. The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study. Multimed Tools Appl 82, 16591–16633 (2023)
