Abstract
The paper presents an overview of a new hybrid approach for Mizo optical character recognition. The preprocessing enhances the accuracy of recognition by removing noise. After this image enhancement, a hybrid approach character segmentation using bounding box and morphological dilation is performed which merges the isolated blobs of Mizo character into a single entity. In feature extraction, another hybrid method is derived using zoning and topological feature which enhances multi-font and multi-size character recognition. The segmented characters are subdivided into nine equal zones and from each zone, four topological features are extracted, forming a total of 9 × 4 = 36 features for each character. These features are used for classification and recognition. An experiment is carried out in 24 different types of fonts using four different types of artificial neural network architecture. Each architecture is compared and analysed. The backpropagation neural network has the highest accuracy, with above 99% rate of recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mori, S., Nishida, H., Yamada, H.: Optical Character Recognition. Wiley (1999)
Chang, F.: Retrieving information from document images: problems and solutions. Int. J. Doc. Anal. Recogn. 4(1), 46–55 (2001)
da Silva, A.R.F.: Wavelet denoising with evolutionary algorithms. Digit. Sig. Proc. 15(4), 382–399 (2005)
Hwang, H., Haddad, R.A.: Adaptive median filters: new algorithms and results. IEEE Trans. Image Process. 4(4), 499–502 (1995)
Wang, Z., Zhang, D.: Progressive switching median filter for the removal of impulse noise from highly corrupted images. IEEE Trans. Circ. Syst. II Analog Digit. Sig. Process. 46(1), 78–80 (1999)
Kumar, S., Kumar, P., Gupta, M., Nagawat, A.K.: Performance comparison of median and wiener filter in image de-noising. Int. J. Comput. Appl. 12, 0975–8887 (1999)
Haralick, R.M., Sternberg, S.R., Zhuang, X.: Image analysis using mathematical morphology. IEEE Trans. Pattern Anal. Mach. Intell. 4, 532–550 (1999)
Lempitsky, V., Kohli, P., Rother, C., Sharp, T.: Image segmentation with a bounding box prior. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 277–284 (2009)
Alam, M.M., Kashem, D.M.A.: A complete Bangla OCR system for printed characters. JCIT 1(01), 30–35 (2010)
Murthy, O.R., Hanmandlu, M.: Zoning based Devanagari character recognition. Int. J. Comput. Appl. 27(4) (2011)
Tou, J.T., Gonzalez, R.C.: Recognition of handwritten characters by topological feature extraction and multilevel categorization. IEEE Trans. Comput. 100(7), 776–785 (1972)
Wang, P.S.P., Zhang, Y.Y.: A fast and flexible thinning algorithm. IEEE Trans. Comput. 38(5), 741–745 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hussain, J., Vanlalruata (2018). A Hybrid Approach Optical Character Recognition for Mizo Using Artificial Neural Network. In: Sa, P., Bakshi, S., Hatzilygeroudis, I., Sahoo, M. (eds) Recent Findings in Intelligent Computing Techniques . Advances in Intelligent Systems and Computing, vol 709. Springer, Singapore. https://doi.org/10.1007/978-981-10-8633-5_54
Download citation
DOI: https://doi.org/10.1007/978-981-10-8633-5_54
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8632-8
Online ISBN: 978-981-10-8633-5
eBook Packages: EngineeringEngineering (R0)