Abstract
Recognition of characters present in natural scene images is a nascent and challenging area of research in computer vision and pattern recognition. This paper proposes a convolutional neural network (CNN) based natural scene character recognition system for Meetei Mayek. Meetei Mayek text present in natural scene images have been detected using maximally stable extremal regions (MSER), geometrical properties, strokewidth and distance. The extracted and manually cropped characters have been used to create a small database. The experiments of the proposed CNN have been conducted on the isolated characters of the Meetei Mayek natural scene character database. The proposed system has been compared with different combinations of feature descriptors, extracted using pretrained CNNs - Alexnet, VGG16, VGG19 and Resnet18 employing three classifiers - support vector machine (SVM), multilayer perceptron (MLP) and k-nearest neighbour (K-NN). The proposed system has achieved better performance with a classification accuracy of 97.57%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Govindan, V.K., Shivaprasad, A.P.: Character recognition - a review. Pattern Recogn. 23(7), 671–683 (1990)
Mori, S., Suen, C.Y., Yamamoto, K.: Historical review of OCR research and development. In: Proceedings of the IEEE, vol. 80, pp. 1029–1058, (1992). https://doi.org/10.1109/5.156468
Baran, R., Partila, P., Wilk, R.: Automated text detection and character recognition in natural scenes based on local image features and contour processing techniques. In: Karwowski, W., Ahram, T. (eds.) IHSI 2018. AISC, vol. 722, pp. 42–48. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-73888-8_8
Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. 54(2), 1–35 (2022)
Yang, L., Ergu, D., Cai, Y., Liu, F., Ma, B.: A review of natural scene text detection methods. Procedia Comput. Sci. 199, 1458–1465 (2022)
Ephstein, B., Ofek, E., Wexler, E.: Detecting text in natural scene with strokewidth transform. In:18th IEEE International Conference on Computer Vision and Pattern Recognition Proceedings, pp. 2963–2970 (2010). https://doi.org/10.1109/CVPR.2010.5540041
Chen, H., Tsai, S.S., Schroth, G., Chen, D.M., Grzeszczuk, R., Girod B.: Robust text detection in natural images with edge- enhanced maximally stable regions. In:18th IEEE International Conference on Image Processing Proceedings, pp. 2609–2612 (2011). https://doi.org/10.1109/ICIP.2011.6116200
Zhou, X.-D., Wang, D.-H., Tian, F., Liu, C.-L., Nakagawa, M.: Handwritten Chinese/Japanese text recognition using Semi-Markov conditional random fields. IEEE Trans. Pattern Anal. Mach. Intell. 35(10), 2413–2426 (2013)
Zhou, M.-K., Zhang, X.-Y., Yin, F., Liu, C.-L.: Discriminative quadratic feature learning for handwritten Chinese character recognition. Pattern Recogn. 49, 7–18 (2016)
Supriana, I., Nasution, A.: Arabic character recognition system development. Procedia Technol. 11, 334–341 (2013)
Karimi, H., Esfahanimehr, A., Mosleh, M., Ghadam, F.M.J., Salehpour, S., Medhati, O.: Persian handwritten digit recognition using ensemble classifiers. Procedia Comput. Sci. 73, 416–425 (2015)
Thokchom, T., Bansal, P.K., Vig, R., Bawa, S.: Recognition of handwritten character of manipuri script. J. Comput. 5(10), 1570–1574 (2010)
Ghosh, S., Barman, U., Bora, P.K., Singh, T.H., Chaudhuri, B.B.: An OCR system for the Meetei Mayek script. In: 4th National Conference on Computer Vision, Pattern Recognition and Graphics Proceedings, pp. 1–4 (2013). https://doi.org/10.1109/NCVPRIPG.2013.6776228
Hijam, D., Saharia, S.: Convolutional neural network based Meitei Mayek handwritten character recognition. In: Tiwary, U.S. (ed.) IHCI 2018. LNCS, vol. 11278, pp. 207–219. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04021-5_19
Darab, M., Rahmati, M.: A hybrid approach to localize Farsi text in natural scene images. Procedia Comput. Sci. 13, 171–184 (2012)
Gonzalez, A., Bergasa, L.M.: A text reading algorithm for natural images. Image Vision Comput. 31(3), 255–274 (2013)
Meetei, L.S., Singh, T.D., Bandyopadhyay, S.: Extraction and identification of manipuri and mizo texts from scene and document images. In: Deka, B., Maji, P., Mitra, S., Bhattacharyya, D.K., Bora, P.K., Pal, S.K. (eds.) PReMI 2019. LNCS, vol. 11941, pp. 405–414. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34869-4_44
Lei, Z., Zhao, S., Song, H., Shen, J.: Scene text recognition using residual convolutional recurrent neural network. Mach. Vision Appl. 29(5), 861–871 (2018). https://doi.org/10.1007/s00138-018-0942-y
Khalil, A., Jarrah, M., Al-Ayyouba, M., Jararweh, Y.: Text detection and script identification in natural scene images using deep learning. Comput. Electr. Eng. 91 (2021)
Devi, C. N., Devi, H. M, Das, D.: Text detection from natural scene images for manipuri meetei mayek script. In: International Conference on Computer Graphics, Vision and Information Proceedings, pp. 248–251. IEEE (2015). https://doi.org/10.1109/CGVIS.2015.7449930
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: 6th IEEE International Conference on Computer Vision Proceedings, pp. 839–846. IEEE (1998). https://doi.org/10.1109/ICCV.1998.710815
Krizhevsky, A., Sutskever, I., Hinton, G. H.: Imagenet classification with deep convolutional netural networks. In: Pereira, F., Burges, C. J., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv (2015). https://arxiv.org/abs/1409.1556
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Devi, C.N. (2023). Meetei Mayek Natural Scene Character Recognition Using CNN. In: Patel, K.K., Santosh, K.C., Patel, A., Ghosh, A. (eds) Soft Computing and Its Engineering Applications. icSoftComp 2022. Communications in Computer and Information Science, vol 1788. Springer, Cham. https://doi.org/10.1007/978-3-031-27609-5_33
Download citation
DOI: https://doi.org/10.1007/978-3-031-27609-5_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27608-8
Online ISBN: 978-3-031-27609-5
eBook Packages: Computer ScienceComputer Science (R0)