Abstract
Bilingual script identification is one of the challenging steps in the development of optical character recognition (OCR). As India is a multilingual multiscript country, in its constitution for each state, the respective state language and the script is used for state official work. In Maharashtra, Marathi is the state official language with Devanagari script and English as the communication language. We need to develop the OCR that can identify and differentiate both scripts. This paper presents a research work for identification of Devanagari (Marathi) script from printed bilingual text document. In our work, we have developed a methodology that applies projection profile in line segmentation which is followed by twofold word segmentation. We examined the use of structural features (header-line pixel count and intercharacter gap) as a tool for determining the Devanagari words. The heuristic rule approach is used for classification. The proposed method is implemented on ten printed bilingual text images. These images consist of 77 lines and 474 words of varying font sizes. The result of our experimentation shows accuracy of 87.25 % in identification of Marathi words.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chaudhuri, B.B., Pal, U.: Automatic separation of words in Multi-lingual Multi-script India Documents. In: Proceedings of the Fourth International Conference on Document Analysis and Recognition, IEEE, 18–20 Aug 1997
Sarkar, R., Das, N., Basu, S., Kundu, M., Nasipuri, M., Kumar Basu, D.: Word level script identification from Bangla and Devanagri handwritten texts mixed with Roman Script. J. Comput. 2(2) (2010). ISSN: 2151-9617
Ajmire, P.E., Dharaskar, P.V., Thakare, V.M.: A Comparative study of handwritten Marathi character recognition. In: National Conference on Innovative Paradigms in Engineering and Technology (NCIPET-2012), Proceedings published by International Journal of Computer Application, pp. 26–28 (2012)
Shelke, S., Apte, S.: A multistage handwritten Marathi compound character recognition scheme using neural networks and wavelet features. Int. J. Signal Process. Image Process. Pattern Recogn. 4 (2011)
Ambekar, A.G., Hinge, C.S., Kulkarni, S.S.: Bilingual OCR for printed English and Devnagari Text. Int. J. Res. 2(1) (2013). ISSN: 2250-1991
Chaudhuri, B.B., Pal, U.: An OCR system to read two Indian language scripts: Bangla and Devnagari (Hindi). In: Proceedings of the Fourth International Conference on Document Analysis and Recognition, IEEE, 18–20 Aug 1997
Dhandra, B.V., Mallikarjun, H., Hegadil, R., Malemathl, V.S.: Word level script identification in Bilingual documents through discriminating features. In: International Conference on Signal Processing, Communications and Networking (ICSCN), IEEE, pp. 630–635 (2007)
Patil, S.B., Subbareddy, N.V.: Neural network based system for script identification in Indian documents. Sadhana Special Issue Indian Lang. Doc. Process. 27, Part-1, 83–97 (2002)
Zhou, L., Lu, Y., Tan, C.L.: Bangla/English script identification based on analysis of connected component profiles. In: Proceedings of 7th IAPR Workshop on Document Analysis System, New land, pp. 234–254 (2006)
Hassan, E., Garg, R., Chaudhury, S., Gopal, M.: Script based text identification: a multi-level architecture. In: Proceedings of the 2011 Joint Workshop on Multilingual OCR and Analytics for Noisy Unstructured Text Data, ACM (2011)
Dhir, R., Singh, C., Lehal, G.S.: A Structural Feature based approach for script identification of Gurumukhi and Roman characters and words. In: Proceedings of 39th Annual National Convention of Computer Society of India, Dec 2004 (2004)
Aithal, P.K., Rajesh, G., Acharya, D.U., Krishnamoorthi, M., Subbareddy, N.V.: Text line script identification for a tri-lingual document. In: IEEE Second International conference on Computing, Communication and Networking Technologies, pp. 1–3 (2010). ISBN: 978-4244-6589-7
Vijaya, P.A., Padma, M.C.: Text line identification from a multilingual document. In: IEEE International Conference on Digital Image Processing, pp. 302–305 (2009). ISBN: 978-0-7695-3565-4
Elgammal, A.M., Ismail, A.M.: Techniques for language identification for hybrid Arabic-English document images. In: Proceedings Sixth International Conference on Document Analysis and Recognition, IEEE (2001)
Godara, S.P., Patwal, P.S.: Latin script detection and removal from Devanagari document image for OCR. Int. J. Comput. Organ. Trends 6, 33–36 (2014). ISSN: 2249-2593
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer India
About this paper
Cite this paper
Zinjore, R.S., Ramteke, R.J. (2016). Identification of Devanagari Script from Bilingual Printed Text Documents. In: Afzalpulkar, N., Srivastava, V., Singh, G., Bhatnagar, D. (eds) Proceedings of the International Conference on Recent Cognizance in Wireless Communication & Image Processing. Springer, New Delhi. https://doi.org/10.1007/978-81-322-2638-3_52
Download citation
DOI: https://doi.org/10.1007/978-81-322-2638-3_52
Published:
Publisher Name: Springer, New Delhi
Print ISBN: 978-81-322-2636-9
Online ISBN: 978-81-322-2638-3
eBook Packages: EngineeringEngineering (R0)