Mukesh M. Goswami
Skip Abstract Section
Abstract
This article presents an elegant technique for extracting the low-level stroke features, such as endpoints, junction points, line elements, and curve elements, from offline printed text using a template matching approach. The proposed features are used to classify a subset of characters from Gujarati script. The database consists of approximately 16,782 samples of 42 middle-zone symbols from the Gujarati character set collected from three different sources: machine printed books, newspapers, and laser printed documents. The purpose of this division is to add variety in terms of size, font type, style, ink variation, and boundary deformation. The experiments are performed on the database using a k-nearest neighbor (kNN) classifier and results are compared with other widely used structural features, namely Chain Codes (CC), Directional Element Features (DEF), and Histogram of Oriented Gradients (HoG). The results show that the features are quite robust against the variations and give comparable performance with other existing works.
- Government of India. 2003. THE CONSTITUTION (NINETY-SECOND AMENDMENT) ACT, 2003. Retrieved December 5, 2014 from http://lawmin.nic.in/coi/EIGHTH-SCHEDULE.pdf.Google Scholar
- Government of India. 2001. Abstract of Speakers. Strength of Languages and Mother Tongues-2000. Census of India. (2001).Google Scholar
- Sameer Antani and L. Agnihotri. 1999. Gujarati character recognition. In Proceedings of the 5th International Conference on Document Analysisand Recognition (ICDAR’99). 418--421. Google ScholarDigital Library
- K. Aparna and A. G. Ramakrishnan. 2002. A complete Tamil optical character recognition system. In Document Analysis Systems V, Daniel Lopresti, Jianying Hu, and Ramanujan Kashi (Eds.). Springer Berlin, 53--57. Google ScholarDigital Library
- S. Belongie, J. Malik, and J. Puzicha. 2002. Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 4 (2002), 509--522. Google ScholarDigital Library
- R. L. Brown. 1994. The fringe distance measure: An easily calculated image distance measure with recognition results comparable to gaussian blurring. IEEE Transactions on Systems, Man, and Cybernetics 24, 1 (1994), 111--115.Google ScholarCross Ref
- B. B. Chaudhuri. 2007. Digital Document Processing: Major Directions and Recent Advances. Springer-Verlag London Ltd. Google ScholarDigital Library
- B. B. Chaudhuri and U. Pal. 1998. A complete printed Bangla OCR system. Pattern Recognition 31, 5 (1998), 531--549.Google ScholarCross Ref
- B. B. Chaudhuri, U. Pal, and M. Mitra. 2001. Automatic recognition of printed Oriya script. In Proceedings of the 6th International Conference on Document Analysis and Recognition (ICDAR’01). 795--799. Google ScholarDigital Library
- T. M. Cover and P. E. Hart. 1967. Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13, 1, 21--27. Google ScholarDigital Library
- Navneet Dalal and Triggs Bill. 2005. Histograms of oriented gradients for human detection. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). IEEE. Google ScholarDigital Library
- Jignesh Dholakia, A. Negi, and S. Ram Mohan. 2009. Progress in Gujarati document processing and character recognition. In Guide to OCR for Indic Scripts: Document Recognition and Retrieval, Venu Govindaraju and Srirangaraj Setlur (Eds.). Springer, 73--95.Google Scholar
- J. Dholakia, A. Yajnik, and A. Negi. 2007. Wavelet feature based confusion character sets for Gujarati script. In Proceedings of the International Conference on Computational Intelligence and Multimedia Applications. 366--370. Google ScholarDigital Library
- R. O. Duda, P. E. Hart, and D. G. Stork. 2000. Pattern Classification (2 ed.). Wiley-Interscience. Google ScholarDigital Library
- T. Ejima, Y. Nakamura, and M. Kimura. 1985. The characteristic feature based on four types of structural information and their effectiveness for character recognition. Transactions of the IEICE J68-D (1985), 789--796.Google Scholar
- Herbert Freeman. 1974. Computer processing of line-drawing images. ACM Computing Surveys (CSUR) 6, 1 (1974), 57--97. Google ScholarDigital Library
- Hiromichi Fujisawa. 2008. Forty years of research in character and document recognition an industrial perspective. Pattern Recognition 41, 8 (Aug. 2008), 2435--2446. DOI:http://dx.doi.org/10.1016/j.patcog.2008.03.015 Google ScholarDigital Library
- M. M. Goswami, H. B. Prajapati, and V. K. Dabhi. 2011. Classification of printed Gujarati characters using som based k-nearest neighbor classifier. In Proceedings of the International Conference on Image Information Processing. 1--5.Google Scholar
- V. Govindaraju. 1999. Chaincode contour processing for handwritten word recognition. IEEE Transactions on Pattern Analysis and Machince Intelligence 21, 9 (1999), 928--932. Google ScholarDigital Library
- V. Govindaraju and S. Setlur. 2009. Guide to OCR for Indic Scripts: Document Recognition and Retrieval. Springer. Google ScholarDigital Library
- E. Hassan, S, Chaudhury, and M. Gopal. 2014. Feature combination for binary pattern classification. International Journal of Document Analysis and Recognition (IJDAR) (2014), 1--18. Google ScholarDigital Library
- T. S. Huang, G. Y. Yang, and G. Y. Tang. 1979. A fast two-dimensional median filtering algorithm. IEEE Transactions on Acoustics, Speech, and Signal Processing 27 (1979), 13--18.Google ScholarCross Ref
- J. J. Hull. 1998. Document Analysis System. Vol. II. World Scientific, Chapter Document image skew detection: Survey and annotated bibliography, 40--64.Google Scholar
- M. Ishtiaq. 1999. Language Shifts Among the Scheduled Tribes in India: A Geographical Study. Vol. 13. Motilal Banarsidass Publ.Google Scholar
- C. V. Jawahar, Pavan Kumar, and S. S. Ravi Kiran. 2003. A bilingual OCR for Hindi-Telugu documents and its applications. In Proceedings of the 7th International Conference on Document Analysis and Recognition (ICDAR’03). 408--412. Google ScholarDigital Library
- T. Kaneko and M. Okudaira. 1985. Encoding of arbitrary curves based on the chain code representation. IEEE Transactions on Communications 33, 7 (Jul 1985), 697--707.Google ScholarCross Ref
- N. Kato, M. Suzuki, S. I. Omachi, H. Aso, and Y. Nemoto. 1999. Handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance. IEEE Transactions on Pattern Analysis and Machine Intelligence 21 (1999), 258--262. Google ScholarDigital Library
- Murphy Kevin. 2012. Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge, MA/London. Google ScholarDigital Library
- R. Keys. 1981. Cubic convolution interpolation for digital image processing. IEEE Transactions on Acoustics, Speech, and Signal Processing 29 (1981), 1153--1160.Google ScholarCross Ref
- Suryaprakash Kompalli, Sankalp Nayak, Srirangaraj Setlur, and Venu Govindaraju. 2005. Challenges in OCR of Devanagari documents. In Proceedings of the 8th International Conference on Document Analysis and Recognition (ICDAR’05). IEEE, 1--5. Google ScholarDigital Library
- C. V. Lakshmi and C. Patvardhan. 2002. A multi-font OCR system for printed Telugu text. In Proceedings of the Langauge Engineering Conference. 7--17. Google ScholarDigital Library
- Gurpreet Singh Lehal and Chandan Singh. 2000. A Gurmukhi script recognition system. In Proceedings of the 15th International Conference on Pattern Recognition (ICPR’00). 557--560.Google ScholarCross Ref
- C. Mandar, M. Gitam, M. Suman, and G. Mukesh. 2012. Similar looking Gujarati printed character recognition using locality preserving projection and artificial neural network. In Proceedings of the 3rd International Conference on Emerging Applications of Information Technology (EAIT’12). IEEE, 457--461.Google Scholar
- V. N. Manjunath, P. S. Aradhyal, G. Hemantha Kumar, and S. Noushathl. 2006. Fisher linear discriminant analysis based technique useful for efficient character recognition. In Proceedings of the 4th International Conference on Intelligent Sensing and Information Processing. 49--52.Google Scholar
- S. Y. Mehta and J. Dholakia. 2004. Gujarati Script. Technical Report. 6--33 pages.Google Scholar
- U. Pal and B. B. Chaudhuri. 2004. Indian script character recognition: A survey. Pattern Recognition 37, 9 (sep 2004), 1887--1899. DOI:http://dx.doi.org/10.1016/j.patcog.2004.02.003Google ScholarCross Ref
- A. Sharma and S. K. Shah. 2006. Design and implementation of optical character recognition system to recognize Gujarati script using template matching. IE(I) Journal(ET) 86, 1 (2006), 44--49.Google Scholar
- I. Siddiqi and N. Vincent. 2009. A set of chain code based features for writer recognition. In Proceedings of the 10th International Conference on Document Analysis and Recognition (ICDAR’09). 981--985. Google ScholarDigital Library
- R. M. K. Sinha and H. N. Mahabala. 1979. Machine recognition of Devanagari script. IEEE Transactions on Systems, Man, and Cybernetics 9, 8 (1979), 435--441.Google ScholarCross Ref
- G. Srikantan, S. Lam, and S. Srihari. 1996. Gradient-based contour encoding for character recognition. Pattern Recognition 29, 7 (July 1996), 1147--1160.Google ScholarCross Ref
- N. Sun, M. Abe, and Y. Nemoto. 1995. A handwritten character recognition system by using improved directional element feature and subspace method. Transactions of the IEICE J78-D-II (1995), 922--930.Google Scholar
- S. B. Suthar, M. M. Goswami, and A. R. Thakkar. 2014. Empirical study of thinning algorithms on printed Gujarati characters and handwritten numerals. In Proceedings of the 2nd International Conference on Emerging Research in Computing, Information, Communication, and Applications (ERCICA’14), Nitte Meenakshi (Ed.), Vol. 2. ELSEVIER, 104--110.Google Scholar
- O. D. Trier, A. K. Jain, and T. Taxt. 1996. Feature extraction methods for character recognition: A survey. Pattern Recognition 29, 4 (1996), 641--662.Google ScholarCross Ref
- Dengsheng Zhang and Guojun Lu. 2004. Review of shape representation and description techniques. Pattern Recognition 37, 1 (Jan. 2004), 1--19. DOI:http://dx.doi.org/10.1016/j.patcog.2003.07.008Google ScholarCross Ref
- Y. Y. Zhang and P. S. P. Wang. 1996. A parallel thinning algorithm with two-subitration that generates one-pixel-wide skeletons. In Proceedings of the 13th International Conference on Pattern Recognition (ICPR’96). IEEE, 457--461. Google ScholarDigital Library
Index Terms
- Classification of Printed Gujarati Characters Using Low-Level Stroke Features
Recommendations
On-line handwritten Gujarati character Recognition using low level stroke
ICIIP '15: Proceedings of the 2015 Third International Conference on Image Information Processing (ICIIP)This paper presents a low level stroke feature based method for recognition of online handwritten Gujarati characters and numerals. A reasonable size database of online handwritten Gujarati characters and numerals has been developed. This is the first ...
Stroke effect on legibility of Japanese characters
This study applied a computer program to analyze the descriptors of Japanese characters, including 56 Hiragana, 56 Katakana, and 98 Kanji characters. An experiment was designed to test the legibility of these characters by 40 Japanese students studying ...
Zone Identification in the Printed Gujarati Text
ICDAR '05: Proceedings of the Eighth International Conference on Document Analysis and RecognitionGujarati, is a language from the Indo-Aryan family of languages, used by 50 million people in the western part of India. Gujarati - script used to write the Gujarati language, is a multilevel script, written in three zones: base character zone, upper ...
Comments