Skip to main content
SpringerLink
Log in

Recognition of Handwritten Gujarati Conjuncts Using the Convolutional Neural Network Architectures: AlexNet, GoogLeNet, Inception V3, and ResNet50

  • Conference paper
  • First Online:
Advances in Computing and Data Sciences (ICACDS 2022)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1614))

Included in the following conference series:

Abstract

A methodology for recognizing offline handwritten Gujarati conjuncts has been introduced in the proposed article. This article includes 767 types of frequently utilized conjuncts. The convolutional neural network (CNN) architectures AlexNet, GoogLeNet, Inception V3, as well as ResNet50, are used to recognize handwritten Gujarati conjuncts. The performance of these CNN architectures is systematically evaluated. Gujarati conjuncts are required to segment from the appropriate place before recognition. Conjuncts are segmented into preceding components and succeeding components before recognition. These preceding components and succeeding components can be then individually recognized by the system. 19694 sample images of preceding components of the conjuncts and 28050 samples images of the succeeding components of the conjuncts are utilized for the proposed research work. Maximum accuracy of 93.41% for the preceding components and maximum accuracy of 89.01% for the succeeding components have been achieved by using GoogLeNet.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    In Gujarati script, consonant clusters   as well as  are considered as basic consonants.

References

  1. Bai, J., Chen, Z., Feng, B., Xu, B.: Image character recognition using deep convolutional neural network learned from different languages. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 2560–2564 (2014).  https://doi.org/10.1109/ICIP.2014.7025518

  2. Maitra, D.S., Bhattacharya, U., Parui, S.K.: CNN based common approach to handwritten character recognition of multiple scripts. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1021–1025 (2015).  https://doi.org/10.1109/ICDAR.2015.7333916

  3. Desai, A.A.: Gujarati handwritten numeral optical character reorganization through neural network. Pattern Recogn. 43(7), 2582–2589 (2010). https://doi.org/10.1016/j.patcog.2010.01.008

    Article  MATH  Google Scholar 

  4. Desai, A.A.: Support vector machine for identification of handwritten Gujarati alphabets using hybrid feature space. CSI Transactions on ICT 2(4), 235–241 (2015). https://doi.org/10.1007/s40012-014-0059-z

    Article  Google Scholar 

  5. Desai, A.A.: Handwritten Gujarati numeral optical character recognition using hybrid feature extraction technique. In: Proceedings of the 2010 International Conference on Image Processing, Computer Vision, Pattern Recognition, vol. 2, pp. 733–739 (2010)

    Google Scholar 

  6. Parikh, M.,  Desai, A.A.: Segmentation of Frequently Used Handwritten Gujarati Conjunctive Alphabet. In: 2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), pp. 1–6 (2019).  https://doi.org/10.1109/ICCUBEA47591.2019.9128510

  7. Patel, C., Desai, A.A.: Segmentation of text lines into words for Gujarati handwritten text. In:  2010 International Conference on Signal and Image Processing, pp. 130–134 (2010).  https://doi.org/10.1109/ICSIP.2010.5697455

  8. Patel, C.,  Desai, A.A.: Zone Identification for Gujarati Handwritten Word. In: 2011 Second International Conference on Emerging Applications of Information Technology,  pp. 194–197 (2011).  https://doi.org/10.1109/EAIT.2011.47

  9. Shukla, D., Desai, A.: Extraction and recognition of handwritten Gujarati characters and numerals from images using deep learning. In: Thakkar, F., Saha, G., Shahnaz, C., Hu, Y.-C. (eds.) Proceedings of the International e-Conference on Intelligent Systems and Signal Processing. AISC, vol. 1370, pp. 657–669. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-2123-9_51

    Chapter  Google Scholar 

  10. Bora, M.B., Daimary, D., Amitab, K., Kandar, D.: Handwritten character recognition from images using CNN-ECOC. Proced. Comput. Sci. 167, 2403–2409 (2020). https://doi.org/10.1016/j.procs.2020.03.293, ISSN 1877–0509

  11. Purkaystha, B., Datta, T.,  Islam, M.S.: Bengali handwritten character recognition using deep convolutional neural network. In: 2017 20th International Conference of Computer and Information Technology (ICCIT), pp. 1–5 (2017).  https://doi.org/10.1109/ICCITECHN.2017.8281853

  12. Zhong, Z., Jin, L., Xie, Z.: High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 846–850 (2015).  https://doi.org/10.1109/ICDAR.2015.7333881

  13. James, A., Manjusha, J., Saravanan, C.: Malayalam handwritten character recognition using AlexNet based architecture. Indonesian J. Elec. Eng. Inf. (IJEEI), 6(4), 393–400, ISSN: 2089–3272. (2018).  https://doi.org/10.11591/ijeei.v6i1.518

  14. Prashanth, D.S., Mehta, R.V.K., Ramana, K., Bhaskar, V.: Handwritten devanagari character recognition using modified Lenet and Alexnet convolution neural networks. Wireless Pers. Commun. 122(1), 349–378 (2021). https://doi.org/10.1007/s11277-021-08903-4

    Article  Google Scholar 

  15. Aneja, N., Aneja, S.: Transfer Learning using CNN for Handwritten devanagari character recognition. In: 2019 1st International Conference on Advances in Information Technology (ICAIT), pp. 293–296 (2019).  https://doi.org/10.1109/ICAIT47043.2019.8987286

  16. Patel, C., Desai, A.: Extraction of characters and modifiers from handwritten Gujarati words. Int. J. Comput. Appli. 73(3), 7–12 (2013). https://doi.org/10.5120/12719-9541

    Article  Google Scholar 

  17. Bhati, G.S., Garg, A.R.: Handwritten devanagari character recognition using CNN with transfer learning. In: Sharma, H., Saraswat, M., Yadav, A., Kim, J.H., Bansal, J.C. (eds.) CIS 2020. AISC, vol. 1335, pp. 269–279. Springer, Singapore (2021). https://doi.org/10.1007/978-981-33-6984-9_22

    Chapter  Google Scholar 

  18. Rajpal, D., Garg, A.R., Mahela, O.P., Alhelou, H.H., Siano, P.: A fusion-based hybrid-feature approach for recognition of unconstrained offline handwritten Hindi characters. Future Internet. 13(9), 239 (2021). https://doi.org/10.3390/fi13090239

  19. Ghosh, S., Das, N., Nasipuri, M.: Reshaping inputs for convolutional neural network: Some common and uncommon methods. Pattern Recog. 93, 79–94 (2019). https://doi.org/10.1016/j.patcog.2019.04.009, ISSN 0031–3203

  20. Huang, S.-C.,  Le, T.-H.: Chapter 8 - convolutional neural network architectures.  In: Huang, S.-Le, T.-H., (eds.) Principles and Labs for Deep Learning, pp. 201–217. Academic Press, ISBN 9780323901987 (2021). https://doi.org/10.1016/B978-0-323-90198-7.00001-X

  21. Gupta, V., Sachdeva, S., Dohare, N.: Chapter 8 - Deep similarity learning for disease prediction. In:  Piuri, V., Raj, S., Genovese, A., Srivastava, R., (eds.) Hybrid Computational Intelligence for Pattern Analysis, Trends in Deep Learning Methodologies, pp. 183–206. Academic Press (2021). https://doi.org/10.1016/B978-0-12-822226-3.00008-8, ISBN 9780128222263

  22. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Neural Inf. Process. Syst. 25, 1097–1105 (2012). https://doi.org/10.1145/3065386

    Article  Google Scholar 

  23. Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015).  https://doi.org/10.1109/CVPR.2015.7298594

  24. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J.,  Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016).  https://doi.org/10.1109/CVPR.2016.308

  25. He, K., Zhang, X., Ren, S.,  Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016).  https://doi.org/10.1109/CVPR.2016.90

  26. Khan, A., Sohail, A., Zahoora, U., Qureshi, A.S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53(8), 5455–5516 (2020). https://doi.org/10.1007/s10462-020-09825-6

    Article  Google Scholar 

  27. Govindaraju, V., Setlur, S.: Guide to OCR for Indic Scripts: Document Recognition and Retrieval, 1st edn. Springer Publishing Company, Incorporated (2009)

    Google Scholar 

  28. Wikipedia contributors. Data augmentation. Wikipedia, The Free Encyclopedia. February 10, 2022, 21:55 UTC. Available at: https://en.wikipedia.org/w/index.php?title=Data_augmentation&oldid+1071104120, (Accessed 16 February  2022)

  29. Wikipedia contributors. Gujarati script. Wikipedia, The Free Encyclopedia.  https://en.wikipedia.org/w/index.php?title=Gujarati_script&oldid=1079209121, (Accessed  16 December  2021)

  30. Indian Mirror. https://www.indianmirror.com/languages/gujarati-language.html, (Accessed  16 December 2021)

  31. Wikipedia contributors. Eighth Schedule to the Constitution of India. Wikipedia, The Free Encyclopedia. 27 October 2021, 17:50 UTC.  https://en.wikipedia.org/w/index.php?title=Eighth_Schedule_to_the_Constitution_of_India&oldid=1052154181, (Accessed 16 December  2021)

  32. Omniglot. http://www.omniglot.com/writing/gujarati.htm, (Accessed 16 December 2021)

Download references

Acknowledgments

The authors acknowledge the support of the University Grants Commission (UGC), New Delhi, for this research work through project file no.: F.3–12/2018/ DRS-II (SAP-II).

Author information

Authors and Affiliations

  1. Department of Computer Science, Veer Narmad South Gujarat University, Surat, India

    Megha Parikh & Apurva Desai

Authors
  1. Megha Parikh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Apurva Desai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Megha Parikh .

Editor information

Editors and Affiliations

  1. University of KwaZulu-Natal, Durban, South Africa

    Mayank Singh

  2. Jaypee University of Engineering and Technology, Guna, India

    Vipin Tyagi

  3. Jaypee University of Information Technology, Waknaghat, India

    P. K. Gupta

  4. Institute of Information Theory and Automation, Prague, Czech Republic

    Jan Flusser

  5. University of Ottawa, Ottawa, ON, Canada

    Tuncer Ören

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Parikh, M., Desai, A. (2022). Recognition of Handwritten Gujarati Conjuncts Using the Convolutional Neural Network Architectures: AlexNet, GoogLeNet, Inception V3, and ResNet50. In: Singh, M., Tyagi, V., Gupta, P.K., Flusser, J., Ören, T. (eds) Advances in Computing and Data Sciences. ICACDS 2022. Communications in Computer and Information Science, vol 1614. Springer, Cham. https://doi.org/10.1007/978-3-031-12641-3_24

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-12641-3_24

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-12640-6

  • Online ISBN: 978-3-031-12641-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation