ABSTRACT
Text line segmentation is a challenging task in Optical Character Recognition, due to writing style of writers and touching characters or Matra between lines. In this paper, we have proposed an algorithm for dividing the merged lines into individual multiple lines from Handwritten Bilingual (Marathi-English) documents. The algorithm is tested on different images; we have obtained promising results. Afterward, script is identifying at word level using fusion of moment based features and visual discriminating features. Two different classifiers are evaluated on a dataset consisting of 242 Marathi-English words for training and 82 words for testing. We have received average identification accuracy of 67% in K-NN classifier and 80.14% in SVM classifier.
- B. V. Dhandra. and Mallikarjun H., 2011, Morphological Reconstruction for Word Level Script Identification, IJCSS, Vol 1, Issue 1, 41--51.Google Scholar
- M C Padma. and P A Vijaya., 2009, Identification of Telugu, Devanagari and English Scripts using Discriminating Features, IJCSIT, Vol. 1, No. 2,pp-64--76.Google Scholar
- M C Padma. and P A Vijaya., 2010, Global Approach for script Identification using Wavelet Packet Based Features, IJSIP, Vol. 3, No. 3, 29--40.Google Scholar
- Kulkarni S., Borde P, Manza R., Yannawar P., 2017, Text line segmentation of handwritten historical MODI Documents, IJICCT, Vol V, Issue I, ISSN: 2347--7202, 285--290.Google Scholar
- Shafali G. and Ashok K., 2014, Method for line segmentation in handwritten documents with Touching and Broken Parts in Devanagari Script, IJCA, Vol. 102, No. 12, ISBN: 0975-8887, 22--27.Google Scholar
- Snehdeep. And Manoj Kumar., 2014, Segmentation of connected componenets and Overlapping lines in Gurumukhi Handwritten Documents, IJCA, Vol. 102, No. 13, 10--14.Google ScholarCross Ref
- Rahul Garg. and Naresh K., 2014, An algorithm for text line Segmentation in Handwritten Skewed and Overlapped Devanagari Script, IJETAAE, Vol. 4, Issue 5, ISSN: 2250--2459, 114--118.Google Scholar
- Anurag B. and Huaigu C. and Venu G., 2009, Script Identification of Handwritten Images, SPIE-IS&T/ Vol. 7247,Google Scholar
- K. Roy. and U. Pal., 2006, Word-wise Hand-written Script Separation for Indian Postal automation.Google Scholar
- Rajneesh Rani. and Renu Dhir. and Gurpreet Singh Lehal., 2005, Modified Gabor Feature Extraction Method for Word Level Script Identification -- Experimentation with Gurumukhi and English scripts, IJSIP Vol. 6, No. 5, ISBN NO: 2005--4254, 25--38.Google Scholar
- Ram S., Nibaran D. and Subhadip B. and Mahantapas K. and Mita N. and Dipak K., 2010, Word level script identification from Bangla and Devanagari handwritten texts mixed with Roman Script, Journal of Computing, Vol. 2, Issue 2, ISSN 2151--9617, PP -- 103--108.Google Scholar
- B. V. Dhandra. And Mallikarjun H., 2007, Global and Local features based Handwritten text words and numerals script identification, IEEE Computer Society, ISBN NO.: 0-7695-3050-8/07. Google ScholarDigital Library
- G. G. Rajput. and Anita H. B., 2011,Handwritten Script Identification from a Bi-Script Document at Line Level using Gabor Filters, http://ceur-ws.org/Vol-758.Google Scholar
- Ranjana S. Zinjore. and R. J. Ramteke., 2016, Identification of Devanagari Script From Bilingual Printed Text Documents", Proceeding of International Conference on Recent Cognizance in Wireless Communication & Image Processing (ICRCWIP 2014), Springer booklet (ebook, 978-81-322-2638-3), 451--462.Google Scholar
- Ranjana S. Zinjore. and R. J. Ramteke., 2015, Identification and Removal of Devanagari script and Extraction of Roman Words from Printed Bilingual Text Document", International Journal of Computer Application (0975-8887), 17--20.Google Scholar
Recommendations
Local features-based script recognition from printed bilingual document images
Classification and identification of language in a biscript document is one of the important steps in the design of an OCR system for successful analysis and recognition. This paper presents architecture for script recognition of bilingual document ...
Indic script identification from handwritten document images
Script identification plays an important role in document image processing especially for multilingual environment. This paper hires two conventional textural methods for recognition of the scripts of the handwritten documents inscribed in different Indic ...
Word-Wise Thai and Roman Script Identification
In some Thai documents, a single text line of a printed document page may contain words of both Thai and Roman scripts. For the Optical Character Recognition (OCR) of such a document page it is better to identify, at first, Thai and Roman script ...
Comments