Abstract
In this paper, we have presented an offline handwritten Gurmukhi character recognition system using various transformations techniques, namely, discrete wavelet transformations (DWT2), discrete cosine transformations (DCT2), fast Fourier transformations and fan beam transformations. DWT2 has also been considered with three different types, namely, Haar wavelet, Daubechies (db) 1 wavelet and Daubechies (db) 2 wavelet transformations. In this work, we have used support vector machine (SVM) classifier for classification, as well as for linear kernel and polynomial kernel. For the purpose of training and testing data set, we have collected around 10,500 samples of isolated offline handwritten Gurmukhi characters. After due experiments with the help of 5-fold cross validation technique using DCT2 coefficients as features, 95.8 % recognition accuracy has been achieved with SVM for linear kernel.
Similar content being viewed by others
References
Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84
Pal U, Chaudhuri BB (1994) OCR in Bangla: an Indo-Bangladeshi language. In: Proceedings of 12th international conference on pattern recognition (ICPR), pp 269–273
Bansal V, Sinha RMK (2000) Integrating knowledge sources in Devanagari text recognition system. IEEE Trans Syst Man Cybern 30(4):500–505
Impedovo S, Dimauro G (1990) An interactive system for the selection of handwritten numeral classes. In: Proceedings of 10th international conference on pattern recognition (ICPR), pp 563–566
Roy K, Vajda S, Pal U, Chaudhuri, BB (2004) A system towards Indian postal automation. In: Proceedings of 9th international workshop on frontiers in handwriting recognition (IWFHR), pp 361–367
Pal U, Sharma N, Wakabayashi T, Kimura F (2007) Off-line handwritten character recognition of Devanagari script. In: Proceedings of 9th international conference on document analysis and recognition (ICDAR), pp 446–450
Alaei A, Pal U, Nagabhushan P (2009) Using modified contour features and SVM based classifier for the recognition of Persian/Arabic handwritten numerals. In: Proceedings of the 7th international conference on advances in pattern recognition (ICAPR), pp 391–394
Shrivastava SK, Gharde SS (2010) Support vector machine for handwritten Devanagari numeral recognition. Int J Comput Appl 7(10):9–14
Pal U, Wakabayashi T, Kimura F (2007) Handwritten Bangla compound character recognition using gradient feature. In: Proceedings of 10th international conference on information technology (ICIT), pp 208–213
Lehal GS, Singh C (1999) Feature extraction and classification for OCR of Gurmukhi script. Vivek 12(2):2–12
Jindal MK, Sharma RK, Lehal GS (2007) Segmentation of horizontally overlapping lines in printed Indian scripts. Int J Comput Intell Res 3(4):277–286
Sharma A, Kumar R, Sharma RK (2008) Online handwritten Gurmukhi character recognition using elastic matching. Int J Congr Image Signal Process 2:391–396
Sharma DV, Jain U (2010) Recognition of isolated handwritten characters of Gurmukhi script using Neocognitron. Int J Comput Appl 10(8):10–16
Kumar M, Sharma RK, Jindal MK (2011) SVM based offline handwritten Gurmukhi character recognition. Proc Int Workshop Soft Comput Knowl Discov (SCAKD) 758:51–62
Rajput GG, Anita HB (2010) Handwritten script recognition using DCT and wavelet features at block level. In: IJCA special issue on “Recent trends in image processing and pattern recognition (RTIPPR), pp 158–163
Kumar R, Sharma RK, Sharma A (2015) Recognition of multi-stroke based online handwritten Gurmukhi Aksharas. Proc Natl Acad Sci India Sect A 85(1):159–168
Anguita D, Ghelardoni L, Ghio A, Oneto L, Ridella S (2012) The ‘K’ in K-fold cross validation. In: Proceedings of European symposium on artificial neural networks, computational intelligence and machine learning, pp 441–446
Lehal GS, Singh C, Lehal R (2001) A shape based post processor for Gurmukhi OCR. In: Proceedings of 6th international conference on document analysis and recognition (ICDAR), pp 1105–1109
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kumar, M., Jindal, M.K. & Sharma, R.K. Offline Handwritten Gurmukhi Character Recognition: Analytical Study of Different Transformations. Proc. Natl. Acad. Sci., India, Sect. A Phys. Sci. 87, 137–143 (2017). https://doi.org/10.1007/s40010-016-0284-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40010-016-0284-y