Call for Paper - August 2022 Edition
IJCA solicits original research papers for the August 2022 Edition. Last date of manuscript submission is July 20, 2022. Read More

Handwritten Script Recognition using DCT and Wavelet Features at Block Level

© 2010 by IJCA Journal
Number 3 - Article 1
Year of Publication: 2010
G. G. Rajput
Anita H. B.

G G Rajput and Anita H B.. Handwritten Script Recognition using DCT and Wavelet Features at Block Level. IJCA,Special Issue on RTIPPR (3):158–163, 2010. Published By Foundation of Computer Science. BibTeX

	author = {G. G. Rajput and Anita H. B.},
	title = {Handwritten Script Recognition using DCT and Wavelet Features at Block Level},
	journal = {IJCA,Special Issue on RTIPPR},
	year = {2010},
	number = {3},
	pages = {158--163},
	note = {Published By Foundation of Computer Science}


In a country like India where different scripts are in use, automatic identification of handwritten script facilitates many important applications such as automatic transcription of multilingual documents and for the selection of script specific OCR in a multilingual environment. Existing script identification techniques depend on various features extracted from document images at character, word, text line or block level. In this paper, we propose a novel method towards multi-script identification at block level. The recognition is based upon features extracted using Discrete Cosine Transform (DCT) and Wavelets of Daubechies family. The proposed method is experimented on handwritten documents of eight Indian scripts that include English script and yielded encouraging results.


  • Liangrui Peng, Changsong Liu, Xiaoqing Ding, Hua Wang, "Multilingual document recognition research and its application in China," dial, pp.126-132, Second International Conference on Document Image Analysis for Libraries (DIAL'06), 2006.
  • Offline cursive script word recognition: a survey, Ta Steinherz, Ehud Rivlin, Nathan Intrator, International journal on Document Analysis and Recognition, IJDAR (1999) 2: 90-110.
  • S Madhvanath, G Kim, V Govindaraju, .Chaincode Contour Processing for Handwritten Word Recognition. IEEE transactions on pattern analysis and machine intelligence, 1996, Vol 21 , No 9, pg 928 . 932.
  • Indian script character recognition: a survey Pattern Recognition, Volume 37, Issue 9, September 2004, Pages 1887-1899, U. Pal and B. B. Chaudhuri.
  • U. Pal and B. Chaudhuri. Automatic identification of English, Chinese, Arabic, Devnagari and Bangla script line. In International Conference on Document Analysis and Recognition, pages 790-794, 2001
  • Script identification in printed bilingual documents, D Dhanya, A G Ramakrishnan_ And Peeta Basa Pati, Sadhana Vol. 27, Part 1, February 2002, pp. 73–82.
  • M. C. Padma and P. Nagbhushan, Identification and separation of text words of Kannada, Hindi, and English languages through discriminating features, Proceedings of NCDAR 2003, 252-260
  • Script Identification from Indian Documents, Gopal Datt Joshi, Saurabh Garg, and Jayanthi Sivaswamy, DAS 2006, LNCS 3872, pp. 255–267, 20069.
  • Peeta Basa Pati and A.G. Ramakrishnan Word level multi-script identification, Pattern Recognition Letters, Volume 29, Issue 9, 1 July 2008, Pages 1218-1229.
  • Gabor filters for Document analysis in Indian Bilingual Documents Peeta Basa Pati S Sabari Raju Nishikanta Pati A G Ramakrishnan, ICISIP 2008, pp 123-126.
  • A Survey of Script Identification techniques for Multi-Script Document Images, S. Abirami, Dr. D. Manjula, International Journal of Recent Trends in Engineering, Vol. 1, No. 2, May 2009
  • U. Pal, S. Sinha, and B. B. Chaudhuri, Multi-script line identification from Indian document. Seventh International Conference on Document Analysis and Recognition 2 (2003) 880–884.
  • B. V. Dhandra. P. Nagabhushan, Mallikarjun Hangarge, Ravindra Hegdi, V. S. Malemath, Script Identification Based on Morphological Reconstruction in Document Images, Proceedings of 18th International Conference on Pattern Recognition, Honkong, 2006
  • Peeta Basa Patil and A. G. Ramkrishnan, HVS Inspired System for Script Identification in Indian Multi-script Documents, LNCS, Volume 3872, pp 380-389, 2006
  • Kannada, English, and Hindi Handwritten Script Recognition using multiple features, Proc. of National Seminar on Recent Trends in Image Processing and Pattern Recognition (RTIPPR-10), Editors: Dr. P. S. Hiremath et. al., Excel India Pub., New Delhi, ISBN: 93-80043-74-0, pp 149-152.
  • N. Otsu, “A Threshold Selection Method from Gray-Level Histogram”, IEEE Tansaction Systems, Man and Cybernetics, vol 9, no.1, pp.62-66,1979.
  • Digital Image processing, 3/e,Gonzalez and Woods, Pearson Education, 2008.
  • I. Daubechies 1992, “Ten Lectures on Wavelets”, SIAM CBMS-NSF, Series on Applied Mathematics, SIAM.
  • R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, 2nd ed., Wiley, New York.