Abstract
Human development analyses have revealed that only a significant fraction of Indians can write and read the English language. It outlines the necessity of conducting research for Indian scripts based on OCR technology. Integration of an autonomous OCR system that identifies handwritten texts from documents can improve the user experience by offering quick access to details, allowing for revisions, and consuming less storage space. There are numerous unresolved difficult issues for research in Indian scripts like Gujarati, which is still in its infancy due to a large number of consonants, vowels, vowel modifiers, and compound characters. As a result, its major issue is achieving a high recognition rate. The performance of handwritten Gujarati character identification using deep learning and machine learning approaches is improved by the investigation of a unique fusion strategy. The suggested strategies were tested over the handwritten Gujarati alphanumeric datasets. One of the recommended hybrid strategies, MobileNet-SVM, surpassed all other methodologies, obtaining a 97.29% recognition accuracy.
Similar content being viewed by others
References
Sharma A, Thakkar P, Adhyaru D and Zaveri T 2017 Features fusion based approach for handwritten Gujarati character recognition. Nirma Univ. J. Eng. Technol. (NUJET) 5(2): 13–19
Desai A A 2010 Gujarati handwritten numeral optical character reorganization through neural network. Pattern Recognit. 43(7): 2582–2589
Maloo M and Kale K V 2011 Support vector machine based Gujarati numeral recognition. Int. J. Comput. Sci. Eng. 3(7): 2595–2600
Patel C and Desai A 2013 Gujarati handwritten character recognition using hybrid method based on binary tree-classifier and k-nearest neighbour. Int. J. Eng. Res. Technol. (IJERT) 2(6): 2337–2345
Shah L, Patel R, Patel S and Maniar J 2014 Handwritten character recognition using radial histogram. J. Res. Advent. Technol. E-ISSN 2321: 9637
Thaker H R and Kumbharana C K 2014 Structural feature extraction to recognize some of the offline isolated handwritten Gujarati characters using decision tree classifier. Int. J. Comput. Appl. 99(15): 0975–8887
Nagar R and Mitra S K 2015 Feature extraction based on stroke orientation estimation technique for handwritten numeral. In: 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR). IEEE, pp. 1–6
Goswami M M and Mitra S K 2015 Offline handwritten Gujarati numeral recognition using low-level strokes. Int. J. Appl. Pattern Recognit. 2(4): 353–379
Desai A A 2015 Support vector machine for identification of handwritten Gujarati alphabets using hybrid feature space. CSI Trans. ICT 2(4): 235–241
Prasad J R and Kulkarni U 2015 Gujrati character recognition using weighted k-NN and mean \(\chi 2\) distance measure. Int. J. Mach. Learn. Cybern. 6: 69–82
Prasad J R and Kulkarni U 2015 Gujarati character recognition using adaptive neuro fuzzy classifier with fuzzy hedges. Int. J. Mach. Learn. Cybern. 6: 763–775
Sharma A K, Adhyaru D M, Zaveri T H and Thakkar P B 2015 Comparative analysis of zoning based methods for Gujarati handwritten numeral recognition. In: 5th Nirma University International Conference on Engineering (NUiCONE). IEEE, pp. 1–5
Sharma A, Adhyaru D M and Zaveri T H 2017 Chain code feature based recognition of handwritten Gujarati numerals. Int. J. Adv. Res. Comput. Sci. 8(1)
Sharma A K, Thakkar P, Adhyaru D M and Zaveri T H 2017 Gujarati handwritten numeral recognition through fusion of features and machine learning techniques. Int. J. Comput. Syst. Eng. 3(1–2): 35–47
Sharma A, Thakkar P, Adhyaru D and Zaveri T 2017 Features fusion based approach for handwritten Gujarati character recognition. Nirma Univ. J. Eng. Technol. (NUJET) 5(2): 13–19
Sharma A K, Adhyaru D M and Zaveri T H 2018 A novel cross correlation-based approach for handwritten Gujarati character recognition. In: Proceedings of First International Conference on Smart System, Innovations and Computing: SSIC 2017, Jaipur, India. Springer, Singapore, pp. 505–513
Rajyagor B and Rakholia R 2021 Isolated Gujarati handwritten character recognition (HCR) using deep learning (LSTM). In: 2021 Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT). IEEE, pp. 1–6
Yao G, Lei T and Zhong J 2019 A review of convolutional-neural-network-based action recognition. Pattern Recognit. Lett. 118: 14–22
Huang G, Liu Z, Van Der Maaten L and Weinberger KQ 2017 Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4700–4708
Szegedy C, Vanhoucke V, Ioffe S, Shlens J and 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
Zoph B, Vasudevan V, Shlens J and Le Q V 2018 Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710
Simonyan K and Zisserman A 2014 Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Howard A G, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M and Adam H 2017 Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861
Acknowledgements
The authors would like to express their sincere appreciation to the Institute of Technology, Nirma University, for their valuable support and insights during the research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Limbachiya, K., Sharma, A., Thakkar, P. et al. Performance optimization for handwritten Gujarati alphanumeric script identification. Sādhanā 48, 250 (2023). https://doi.org/10.1007/s12046-023-02307-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12046-023-02307-9