Reading Modi Lipi: A Deep Learning Journey in Character Recognition.

Kanchan Varpe; Sachin Sakhare

doi:10.9781/ijimai.2024.09.002

Authors

Kanchan Varpe Vishwakarma University
Sachin Sakhare Vishwakarma University

DOI:

https://doi.org/10.9781/ijimai.2024.09.002

Keywords:

Deep Learning, Feature Extraction, Image Processing, InceptionNet V3, ResNet50, ResNet9

Abstract

Advancements in deep learning methodologies have played a significant role in the success of various character recognition processes. Character recognition refers to the technique of identifying either handwritten or printed characters from documents and their conversion into a form that can be read by machines. MODI script, an ancient Indian script, is categorized under the Devanagari script and holds historical significance. Despite its historical importance, there are only a few MODI translators available. Conversely, there exist a vast number of historical documents written in MODI that are yet to be deciphered. Recognizing characters in Indian language scripts poses many challenges due to the complex nature of the scripts and variations in individuals' writing styles. This paper provides an overview of the newest advancements in the Handwritten Optical Character Recognition (HWCR) methodology specifically designed for the MODI script. Utilization of residual networks and inception in image classification has gained popularity in recent times. In this paper the authors have implemented three techniques: ResNet9, ResNet50, and InceptionNet V3, trained specifically for handwritten MODI characters and vowels. The dataset used for training the models consists of handwritten MODI script images. The benchmark database from IEEE data port for handwritten MODI script is used to evaluate the performance. The dataset contains 46 classes, including 10 vowel classes and 36 consonant classes. Each class comprises 90 images, resulting in a total of 4140 images. The image size in the dataset is 227×227. The accuracy achieved by the trained models is as follows: 98.92% for ResNet9, 91.91% for ResNet50, and 86% for Inception Net V3. The obtained results have been compared with existing models and it is observed that the proposed model attained improved performance parameters and less training and validation losses in comparison to existing methods. There are several advantages of the proposed model in comparison to state of the art, namely minimal training and validation loss. In addition to this, the proposed approach improved generalization and robustness, and improved model scalability.

Downloads

Download data is not yet available.

References

V. Kanchan and S. Sakhare, “Review of Character Recognition Techniques for MODI Script,” Indian Journal of Science and Technology, vol. 16, no. 26, pp. 1935-1946, 2023. doi: 10.17485/IJST/v16i26.485.

K. Sadanand, L. Prashant, R. Ramesh and L. Pravin, “Impact of zoning on Zernike moments for handwritten MODI character recognition,” 2015 International Conference on Computer, Communication and Control (IC4), Indore, India, 2015, pp. 1-6, doi: 10.1109/IC4.2015.7375516.

S. Joseph and J. George, “Handwritten Character Recognition of MODI Script using Convolutional Neural Network Based Feature Extraction Method and Support Vector Machine Classifier,” 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP), Nanjing, China, 2020, pp. 32-36, doi: 10.1109/ICSIP49896.2020.9339435

A. Pandey, “Proposal to Encode North Indic Number Forms in ISO/IEC 10646,” 2007. [Online]. Available: https://api.semanticscholar.org/CorpusID:215863507

S. Joseph and J. George, “Feature Extraction and Classification Techniques of MODI Script Character Recognition,” Pertanika Journal of Science and Technology, vol. 27, pp. 1649-1669, 2019. Available: https://api.semanticscholar.org/CorpusID:260481222.

K. Sadanand, P. Borde, R. Ramesh, and P. Yannawar, “Offline MODI Character Recognition Using Complex Moments,” Procedia Computer Science, vol. 58, pp. 516-523, 2015, doi: 10.1016/j.procs.2015.08.067.

D. Besekar, “Recognition of numerals of MODI script using morphological approach,” International Referred Research Journal, ISSN 0974-2832, pp. 0974-2832, 2011

D. Besekar, “Special Approach for Recognition of Handwritten MODI Script’s Vowels,” in National Conference “MEDHA 2012”, vol. 1, no. 1, pp. 48-52, September 2012. [Online]. Available: /proceedings/medha/number1/8679-1023/.

D. Besekar and R. Ramteke, “Feature extraction algorithm for handwritten numerals recognition of MODI script using zoning-based approach,” International Journal of Systems, Algorithms and Applications, vol. 2, pp. 1-4, 2012

S. Ramteke and G. Katkar, “Recognition of Off-line Modi Script: A Structure Similarity Approach,” International Journal of Research in Engineering, IT and Social Science (IJREISS), vol. 2, no. 11, pp. 2250-0588 2013. [Online]. Available: https://api.semanticscholar.org/CorpusID:16802396

S. Kulkarni and P. Borde, “Analysis of orthogonal moments for recognition of handwritten MODI numerals,” VNSGU Journal of Science and Technology, vol. 4, pp. 36-43, Jul. 2015.

S. Anam and S. Gupta, “An approach for recognizing Modi Lipi using Ostu’s binarization algorithm and Kohenen neural network,” International Journal of Computer Applications, vol. 111, no. 2, pp. 29–34, Feb. 2015, doi: 10.5120/19511-1128.

M. Deshmukh, M. Patil, and S. Kolhe, “Off-line handwritten Modi numerals recognition using chain code,” in Proceedings of the Third International Symposium on Women in Computing and Informatics, Kochi, India, 2015, pp. 388–393, doi: 10.1145/2791405.2791419.

S. Chandure and V. Inamdar, “Performance analysis of handwritten Devnagari and MODI Character Recognition system,” 2016 International Conference on Computing, Analytics and Security Trends (CAST), Pune, India, 2016, pp. 513-516, doi: 10.1109/CAST.2016.7915022.

S. Gharde and R. Ramteke, “Recognition of characters in Indian MODI script,” 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC), Jalgaon, India, 2016, pp. 236-240, doi: 10.1109/ICGTSPICC.2016.7955304

R. Maurya and S. Maurya, “Recognition of a Medieval Indic-Modi Script using Empirically Determined Heuristics in Hybrid Feature Space,” International Journal of Computer Sciences and Engineering, vol. 6, no. 2, pp. 136-142, Feb. 2018, doi: 10.26438/ijcse/v6i2.136142.

S. Joseph, J. George, and S. Gaikwad, “Character Recognition of MODI Script Using Distance Classifier Algorithms,” in ICT Analysis and Applications, S. Fong, N. Dey, and A. Joshi, Eds. Singapore: Springer Singapore, 2020, pp. 105–113.

S. Joseph and J. George, “Handwritten Character Recognition of MODI Script using Convolutional Neural Network Based Feature Extraction Method and Support Vector Machine Classifier,” 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP), Nanjing, China, 2020, pp. 32-36, doi: 10.1109/ICSIP49896.2020.9339435

S. Sawant, A. Sharma, G. Suvarna, T. Tanna and S. Kulkarni, “Word Transcription of MODI Script to Devanagari Using Deep Neural Network,” 2020 3rd International Conference on Communication System, Computing and IT Applications (CSCITA), Mumbai, India, 2020, pp. 18-22, doi: 10.1109/CSCITA47329.2020.9137781

J. Solley and J. George, “Efficient Handwritten Character Recognition of MODI Script Using Wavelet Transform and SVD,” in Data Science and Security, D. S. Jat, S. Shukla, A. Unal, and D. K. Mishra, Eds. Singapore: Springer Singapore, 2021, pp. 227–233, doi: 10.1007/978-981-15-5309-7_24

S. Joseph, A. Datta, O. Anto, S. Philip, and J. George, “OCR System Framework for MODI Scripts using Data Augmentation and Convolutional Neural Network,” in Data Science and Security, D. S. Jat, S. Shukla, A. Unal, and D. K. Mishra, Eds. Singapore: Springer Singapore, 2021, pp. 201-209, doi: 10.1007/978-981-15-5309-7_21

P. Tamhankar, K. Masalkar, and S. R. Kolhe, “Character Recognition of Offline Handwritten Marathi Documents Written in MODI Script Using Deep Learning Convolutional Neural Network Model,” in Recent Trends in Image Processing and Pattern Recognition, K. C. Santosh and B. Gawali, Eds. Singapore: Springer Singapore, 2021, pp. 478–487, doi: 10.1007/978-981-16-0507-9_40

K. Mahajan and N. Tajne, “An Ancient Indian Handwritten Script Character Recognition by Using Deep Learning Algorithm,” EFFLATOUNIA: Multidisciplinary Journal, vol. 5, no. 2, pp. 123-134, Oct. 2021.

S. Chandure and V. Inamdar, “Handwritten MODI Character Recognition Using Transfer Learning with Discriminant Feature Analysis,” IETE Journal of Research, vol. 69, no. 5, pp. 2584-2594, 2023. doi: 10.1080/03772063.2021.1902867

S. Kulkarni and P. Yannawar, “Recognition of Partial Handwritten MODI Characters Using Zoning,” in Recent Trends in Image Processing and Pattern Recognition, K. C. Santosh and B. Gawali, Eds. Singapore: Springer Singapore, 2021, pp. 407–430, doi: 10.1007/978-981-16-0507-9_35.

J. Kondhare, V. Yaduvanshi, R. Patil, and R. Kaldate, “Recognition of Handwritten Modi Digits and Characters by Using Deep Learning Algorithm,” International Journal of Emerging Technologies and Innovative Research, vol. 9, no. 8, pp. 563-572, Aug. 2022. [Online]. Available: http://www.jetir.org/papers/JETIRFP06101.pdf.

M. Ekbote, A. Jadhav, and D. Ambawade, “Implementing a Hybrid Deep Learning Approach to Achieve Classic Handwritten Alphanumeric MODI Recognition,” International Journal of Engineering and Advanced Technology (IJEAT), vol. 12, no. 1, pp. 1-8, Oct. 2022, doi: 10.35940/ijeat.A3846.1012122.

V. Pawar, D. Wadkar, S. Kashid, P. Prakare, V. More, and Prof. S. A. Babar, “MODI Lipi Handwritten Character Recognition Using CNN and Data Augmentation Techniques,” International Research Journal of Engineering and Technology (IRJET), vol. 09, no. 06, pp. 2345-2351, Jun. 2022.

C. Chandankhede and R. Sachdeo, “Character Recognition using MODI script: Facts, Challenges and its future,” TEST Engineering and Management, vol. 83, pp. 25389–25395, 2020.

S. Jadhav, V. Inamdar, October 12, 2021, “Handwritten MODI Characters “, IEEE Dataport, doi: https://dx.doi.org/10.21227/z3gg-8b29.

K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 2818-2826, doi: 10.1109/CVPR.2016.308.