In this paper, an attempt is made to develop an algorithm for recognition of machine printed isolated Kannada vowels and numerals of different font size and style using modified invariant moments and that are invariant with respect to rotation, scale and translation. A minimum distance nearest neighbor classifier is adopted for classification. The proposed algorithm is experimented on 1800 images of vowels and 1000 images of numerals. The experimental results confirm the recognition accuracy as of 97.7% for vowels and 98.92% for numerals. The algorithm is simple, robust and invariant with respect to rotation, scale and translation of an image.

1. Liao S.X. and Pawlak M., “On image analysis by moments invariants”, IEEE Trans. On PAMI, vol.18, no. 3, pp. 254-266, 1996.
2. Boyce J. F. and W.J. Hossach, “Moment invariants for pattern recognitition “, Pattern recognitition Letters, vol. 1 no. 5-6, pp.451-456 1983.
3. Cho-Huak the and Roland T. Chin, “On image Analysis by the methods of moments”, IEEE Trans on PAMI, VOl.10 no. pp.496-512, 1988.
4. Abu Y. S. Mustafa and D. Psaltis, “Recognition aspects of moment invariants”, IEEE Trans. On PAMI, Vol. PAMI-6, pp.698-706, NOV.1984.
5. Yang L. and F. Albregtsen, “Fast computation of invariant moments: A new method giving correct results”, Proc. Of 12 International Conference on Pattern Recognition, Jerusalem, Israel, Vol. 1, pp.201-204, Oct.1994.
6. Flusser J., “Moment Invariants in Image Analysis”, Trans. On Engineering, Computing and Technology, Vol. VII, pp. 196-201, Feb.2006.
7. Khotanzad A. and Y.H. Hong. “Invariant image recognition by Zernike moments”, IEEE Trans. On PAMI, Vol. 12, no. 5, pp.489-497, 1990.
8. Teague M.R., “Image analysis via the general theory of moments “, jour .Optical Society America, Vol. 70, pp. 920-30, 1980.
9. Palaniappan R., P. Raveendran and Sigoru Omata, "Improved moments invariant for invariant image representation" , invariants for Pattern recognition and Classification, World Scientific Publishing Co., pp. 167-185, 2000.
10. Trier O.D., A.K.jain and T. Tax, “Feature extraction methods for character recognition- A survey”, Pattern Recognition, Vol.29, no.4, pp. 641-662, 1996.
11. Hu M. K., “visual pattern Recognition by moment invariants”, IRE Trans. On Information theory, Vol.IT-8, pp. 179-187, 1962.
12. Reddi S., “Radial and angular moment invariants for Image identification”, IEEE Trans. On PAMI-3, pp.240-242, 1986.
13. Ashwin T v, Sastry P S 2002 A fonts and size-independent OCR system for printed Kannada documents using support vector machines. Sadhana 27:35-58
14. Negi Atual, Chakravarthy Bhagavathi, Krishna B 2001 An OCR system for Telugu. Proc. Sixth Inter. Conference. On Document Anal. And rec. 1110-1114
15. Nagbhushan P, Pai Radhika M 1999 Modified region decomposition method and optimal depth decomposition tree in the recognition of non –uniform sized characters – An experimentation with Kannada characters. Pattern Recognition .Letter. 20:1467-1475
16. Jawahar C V, Pavan Kumar , Ravi Kiran S S 2003 Bilingual OCR for Hindi & Telugu documents & its Applications. Proc. Seventh Int.Confer. On Documents Anal ana Rec. 408-412.
17. Kunte Sanjeev R, Sudhaker Samuel (2006), Hu’s invariant moments & Zernike moments approach for the recognition of basic symbols in printed Kannada text. Sadhana vol .32, part 5, October 2007, pp. 521-533.
18. Chaudhuri B.B. and U.Pal, An OCR system to read two Indian language scripts: Bangle and Devanagari, Proceedings of ICDAR, 1997, 1011-1015.
19. R.C.Gonzal, R.E. Woods, “Digital Image Processing”, Pearson Education, 2002.
20. B.V.Dhandra, Mallikarjun Hangarge and shashikala Patil 2010, Multi-Font Kannada Vowels Recognition Based on Modified Invariant Moments. Proceedings of RTIPPR-2010, 119-122.
21. Skew detection in Binary image documents based on Image Dilation and Region labeling Approach, Proceedings of 18th International Conference on Pattern Recognition - ICPR 2006, Hong Kong 2006, V. No. II-3, pp. 954-957

OCR Modified Invariant Moments