Analyzing Different Techniques to Generate Image Datasets for MODI Script Handwritten Character Recognition
Keywords:
Data Augmentation, Handwritten Character Recognition, Image Datasets, Image Filtering, MODI Script, MODI LipiAbstract
Character recognition of MODI script is a proedure to recognize multifarious handwritten characters using distinct image documents. It is one of the oldest scripts utilized in Marathi language. Across Maharashtra India, Marathi Language is still a major spoken language. Applications like optical character recognition (OCR), handwriting analysis, and text extraction depend heavily on character recognition, which is a key task in computer vision and artificial intelligence (AI). Character recognition systems performance is strongly influenced by the caliber and variety of the training picture collection. This research is conducted to analyze distinct techniques to create the image dataset for MODI script handwritten character recognition. Furthermore, the significance of numerous datasets in handwritten character recognition, emphasizing the need for differences in writing styles of MODI script, typefaces, and backgrounds is examined. We explored the key methods to increase the variety of datasets utilizing multifarious approaches such as data augmentation, AI, and many others for Modi script handwritten character recognition. The intricacy of every data generation approach is also covered in the research, including assurance of data quality as well as preserving dataset, effectively. In this work, a new approach is proposed for the creation of a novel dataset of Handwritten MODI script character recognition. Further, there is proposed a framework rooted in enhanced recurrent neural network (RNN) and convolutional autoencoder-based framework for character recognition of the MODI lipi from handwritten documents. It was observed that our MODI lipi character recognition framework offers high accuracy in image analysis and takes less time in pre-processing the document images.
Downloads
References
S. Joseph and J. George, “Feature extraction and classification techniques of modi script character recognition,” Pertanika Journal of Science and Technology. 2019.
Savitri Jadhav and Vandana Inamdar, “Convolutional Neural Network and Histogram of Oriented Gradient Based Invariant Handwritten MODI Character Recognition,” Pattern Recognit. Image Anal., 2022, doi: 10.1134/S1054661822020109.
S. S. Gharde and R. J. Ramteke, “Recognition of characters in Indian MODI script,” in Proceedings - International Conference on Global Trends in Signal Processing, Information Computing and Communication, ICGTSPICC 2016, 2017. doi: 10.1109/ICGTSPICC.2016.7955304.
R. K. Maurya and S. R. Maurya, “Recognition of a Medieval Indic-Modi Script using Empirically Determined Heuristics in Hybrid Feature Space,” Int. J. Comput. Sci. Eng., 2018, doi: 10.26438/ijcse/v6i2.136142.
K. SadanandA., B. Prashant L., M. Ramesh R., and Y. Pravin L., “Review on Recent Advances in Automatic Handwritten MODI Script Recognition,” Int. J. Comput. Appl., 2015, doi: 10.5120/20257-2636.
S. Joseph and J. George, “Handwritten Character Recognition of MODI Script using Convolutional Neural Network Based Feature Extraction Method and Support Vector Machine Classifier,” in 2020 IEEE 5th International Conference on Signal and Image Processing, ICSIP 2020, 2020. doi: 10.1109/ICSIP49896.2020.9339435.
A. K. Sadanand, L. B. Prashant, R. M. Ramesh, and L. Y. Pravin, “Offline MODI Character Recognition Using Complex Moments,” in Procedia Computer Science, 2015. doi: 10.1016/j.procs.2015.08.067.
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 Lecture Notes in Networks and Systems, 2021. doi: 10.1007/978-981-15-5309-7_21.
R. Shah, M. K. Gupta, and A. Kumar, “Line Level Modi (Heritage script) OCR using Attention based Encoder-Decoder Architecture,” in Proceedings of the IEEE International Conference Image Information Processing, 2021. doi: 10.1109/ICIIP53038.2021.9702605.
S. Sawant, A. Sharma, G. Suvarna, T. Tanna, and S. Kulkarni, “Word Transcription of MODI Script to Devanagari Using Deep Neural Network,” in 2020 3rd International Conference on Communication Systems, Computing and IT Applications, CSCITA 2020 - Proceedings, 2020. doi: 10.1109/CSCITA47329.2020.9137781.
P. A. Tamhankar, K. D. Masalkar, and S. R. Kolhe, “Character Recognition of Offline Handwritten Marathi Documents Written in MODI Script Using Deep Learning Convolutional Neural Network Model,” in Communications in Computer and Information Science, 2021. doi: 10.1007/978-981-16-0507-9_40.
A. K. Sadanand, L. B. Prashant, R. M. Ramesh, and L. Y. Pravin, “Impact of zoning on Zernike moments for handwritten MODI character recognition,” in IEEE International Conference on Computer Communication and Control, IC4 2015, 2016. doi: 10.1109/IC4.2015.7375516.
P. S. Chidrawar and V. Dhamdhere, “A Systematic Review on MODI Script Character Recognition,” 2023. doi: 10.1007/978-981-99-3878-0_24.
A. Shirkande and A. Agarwal, “A Review on Various MODI Text Recognition Techniques,” J. Image Process. Artif. Intell., 2023, doi: 10.46610/joipai.2023.v09i01.001.
D. N. Besekar, “Special Approach for Recognition of Handwritten MODI Script’s Vowels,” Int. J. Comput. Appl., 2012.
S. Bhalerao and H. D. Gadade, “A systematic review on advancement in Modi Handwritten Character Recognition,” in Recent Advances in Material, Manufacturing, and Machine Learning, 2023. doi: 10.1201/9781003370628-44.
P. A. Patil, “Character Recognition System for Modi Script,” Int. J. Comput. Eng. Res., 2016.
I. Hussain, R. Ahmad, S. Muhammad, K. Ullah, H. Shah, and A. Namoun, “PHTI: Pashto Handwritten Text Imagebase for Deep Learning Applications,” IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3216881.
M. Ahmed, M. A. Awel, and A. I. Abidi, “REVIEW ON OPTICAL CHARACTER RECOGNITION,” Int. Res. J. Eng. Technol., 2019.
Z. Jia, S. Xu, S. Mu, and Y. Tao, “Learning-Based Text Image Quality Assessment with Texture Feature and Embedding Robustness,” Electron., 2022, doi: 10.3390/electronics11101611.
S. Patil et al., “Enhancing Optical Character Recognition on Images with Mixed Text Using Semantic Segmentation,” J. Sens. Actuator Networks, 2022, doi: 10.3390/jsan11040063.
S. Chandure and V. Inamdar, “Handwritten MODI Character Recognition Using Transfer Learning with Discriminant Feature Analysis,” IETE J. Res., 2023, doi: 10.1080/03772063.2021.1902867.
A. Institutions, “Bharat Itihas Sanshodhak Mandal.” https://map.sahapedia.org/article/Bharat-Itihas Sanshodhak Mandal/2769
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.
