Abstract
Deep learning is a multilayer neural network learning algorithm which emerged in recent years. It has brought a new wave to machine learning and making artificial intelligence and human-computer interaction spread with big strides. India is a heritage country where traditions, religions and languages are quite varied. MODI script is one of the oldest written forms of media. Most of the early written knowledge on subjects like medicine, Buddhist ideology, food habits and horoscope has been written using MODI script. MODI is one of the languages that present special challenge to OCR. The main challenge in MODI script is that it is mostly cursive and few characters look similar. The deep learning methods like InceptionV3 and RestNet on Modi script seems not experimented yet as per literature review. This motivates to apply the deep learning methods to offline handwritten character recognition using Residual and InceptionV3 framework. The handwritten Modi barakhadi dataset is prepared by collecting samples from around 25 different people. The dataset of size 7721 is experimented. The individual characters are cut and pre-processed using Otsu binarization technique. The performance evaluation of pre-processed data is done using both algorithms on the real-world handwritten character database written by different people. Processed images recognized through RestNet50 gives testing accuracy of 94.552% with precision of the model 0.86. Processed images recognized through InceptionV3 gives testing accuracy of 93.923% with precision of the model 0.843.
Similar content being viewed by others
Data availability
Data used for the experiment is handwritten and created with help of writing by different people, friends who are aware of writing Modi script. Different organizations like Bhartiya Itihas Sanshidhan Kendra (BISM) helped to introduce different people for writing. Few samples of the data are mentioned in the paper as Figs. 3 and 4.
References
Alom Z, Sidike P, Hasan M, Taha TM, Asari VK (2017) Handwritten Bangla character recognition using the state-of-art deep convolutional neural networks. Comput Vis Pattern Recognit 2017:1–12
Besekar DN (2012) Special approach for recognition of handwritten MODI Script’s vowels. Int J Comput Appl (IJCA), MAHA:48–52
Besekar DN, Ramteke RJ (2012) Feature extraction algorithm for handwritten numerals recognition of MODI script using zoning-based approach. In J Syst Algorithm Appl 2:1–4
Bhatt PP, Patel I (2018) Optical character recognition using deep learning-a technical review. Natl J Syste Inform Technol 11(1):55
Boufenar C, Kerboua A, Batouche M (2018) Investigation on deep learning for off-line handwritten Arabic character recognition. Cogn Syst Res 50:180–195
Brust CA, Käding C, Denzler J (2020) Active and incremental learning with weak supervision. KI-Künstliche Intell 34:1–16
Chaitali C et al (2023) Handwritten Modi Lipi Barakhadi dataset. IEEE data port. https://doi.org/10.21227/x24n-wm25
Chandure S, Inamdar V (2021) Handwritten MODI character recognition using transfer learning with discriminant feature analysis. IETE J Res: 1–11
Gan J, Wang W, Lu K (2020) Compressing the CNN architecture for in-air handwritten Chinese character recognition. Pattern Recogn Lett 129:190–197
GeeksforGeeks. (2020). Residual Networks (ResNet) - Deep Learning
Gharde SS, & Ramteke RJ (2016). Recognition of characters in Indian MODI script. In 2016 international conference on global trends in signal processing, information computing and communication (ICGTSPICC). IEEE pp. 236-240
Guha R, Das N, Kundu M, Nasipuri M, Santosh KC (2020) Devnet: an efficient CNN architecture for handwritten devanagari character recognition. Int J Pattern Recognit Artif Intell 34(12):2052009
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Jangid M, Srivastava S (2018) Handwritten devanagari character recognition using layer-wise training of deep convolutional neural networks and adaptive gradient methods. J Imag 4(2):41
Jindal U, Gupta S, Jain V, Paprzycki M (2020) Offline handwritten Gurumukhi character recognition system using deep learning. In: In advances in bioinformatics, multimedia, and electronics circuits and signals. Springer, Singapore, pp 121–133
Joseph S, George J (2019) Feature extraction and classification techniques of MODI script character recognition. Pertanika J Sci Technol 27(4):1649–1669
Joseph S, George J (2020) 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). IEEE, pp 32–36
Joseph S, Datta A, Anto O, Philip S, George J (2021) OCR system framework for MODI scripts using data augmentation and convolutional neural network. In: In data science and security. Springer, Singapore, pp 201–209
Koyuncu B & Koyuncu H (2019). Handwritten character recognition by using convolutional deep neural network; Review
Li Z, Purkaystha Q, Xiao Y, Jin M, Lu H (2020) Deep matching network for handwritten Chinese character recognition. Pattern Recogn 2020, 107471
Mujtaba,H (2020). Introduction to Resnet or residual network. GreatLearning blog: free resources what matters to shape your career!
Mustafa WA, & Kader MMMA (2018). Binarization of document images: a comprehensive review. In journal of physics: conference series. IOP publishing. 1019, no. 1, p. 012023
Raj B (2020). A Simple Guide to the Versions of the Inception Network Medium
Ram S, Gupta S, Agarwal B (2018) Devanagri character recognition model using deep convolution neural network. J Stat Manag Syst 21(4):593–599
Rao Z, Zeng C, Wu M, Wang Z, Zhao N, Liu M & Wan X (2018). Research on a handwritten character recognition algorithm based on an extended nonlinear kernel residual network. KSII Trans Internet Inform Syst 12(1)
Ren H, Wang W, Qu X, Cai Y (2019) A new hybrid-parameter recurrent neural network for online handwritten chinese character recogn0poiuydu7hition. Pattern Recogn Lett 128:400–406
Roy S, Das N, Kundu M, Nasipuri M (2017) Handwritten isolated Bangla compound character recognition: a new benchmark using a novel deep learning approach. Pattern Recogn Lett 90:15–21
Sadanand AK, Prashant LB, Ramesh RM & Pravin LY (2015). Impact of zoning on Zernike moments for handwritten MODI character recognition. In 2015 international conference on computer, communication and control (IC4). IEEE, pp. 1-6
Szegedy C, Vanhoucke V, Ioffe S, Shlens J & Wojna Z (2016). Rethinking the inception architecture for computer vision. In proceedings of the IEEE conference on computer vision and pattern recognition pp. 2818-2826
Vaidya, R., Trivedi, D., Satra, S., & Pimpale, M. (2018, April). Handwritten character recognition using deep-learning. In 2018 second international conference on inventive communication and computational technologies (ICICCT) (pp. 772-775). IEEE.
Vijayaraghavan P & Sra M (2014). Handwritten Tamil recognition using a convolutional neural network. In 2014 international conference on information, communication, engineering and technology (ICICET) pp. 1-4
Acknowledgments
We are thankful to Bhartiya Itihas sanshodhan mandal, Pune (BISM) who had given chance to collect handwritten Modi data from different related people who knows Modi script writing.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of Interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chandankhede, C., Sachdeo, R. Offline MODI script character recognition using deep learning techniques. Multimed Tools Appl 82, 21045–21056 (2023). https://doi.org/10.1007/s11042-023-14476-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14476-0