Handwritten recognition is for all time a pioneering area of research in the field of pattern recognition and image processing and there is a huge demand for optical character recognition (OCR) on handwritten documents. Most of these systems work for Arabic, roman, Japanese and Chinese characters, but not as much of research on Indian languages, though there are 11 main scripts in India. This article provides a comprehensive survey of recent developments in popular Indian scripts for handwriting recognition by comparing the feature selection techniques, classifiers and the recognition accuracy for each technique. Finally, some future research directions on offline handwritten recognition techniques are discussed.

handwritten recognition, optical character recognition, feature selection, pattern recognition, image processing

[1]. Impedovo S, Ottaviano L, and Occhinegro S,“Optical Character Recognition — A Survey. Character and Handwriting Recognition”,1-24,1991.
[2]. Setitra I, Hadjadj Z, and Meziane A,"A Tracking Approach for Text Line Segmentation in Handwritten Documents",In the Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods, (2017).
[3]. Gattal A,Djeedi C, Siddqi I, Chibani Y,“Gender classification from offline multi-script handwriting images using oriented basic image features”, Expert Syst Appl, 99,155–167,2018.
[4]. Plamondon R. and Srihari S.N,“Online and Off-Line Handwriting Recognition: A Comprehensive Survey”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 63-84, 2000.
[5]. Pal U and Chaudhuri B. B,“Indian script character recognition: A survey”,Patt.Recog. 37, 9, 1887–1899,2004.
[6]. Pal U, Jayadevan, R, and Sharma, N,“Handwriting recognition in Indian regional scripts: A survey of offline techniques”, ACM Trans. Asian Lang. Inform. Process,11, 1, Article 1 (March 2012).
[7]. Roy K, And Majumder K,“Trilingual script separation of handwritten postal document”, In Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP’08),693–700,2008.
[8]. Bhowmik T. K, Parui S. K, Bhattacharya U, and Shaw B,“An HMM based recognition scheme for handwritten Oriya numerals”, In Proceedings of the 9th Information Technology Conference (ICIT’06),105–110,2006.
[9]. Bhowmik T. K,Parui S. K, and Roy U,“Discriminative HMM Training with GA for Handwritten Word Recognition”, In Proceedings of the 19th International Conference on Pattern Recognition (ICPR’08),1–4,2008.
[10]. Bhowmik T. K, Ghanty P, Roy A, and Parui S. K,“SVM-based hierarchical architectures for handwritten Bangla character recognition”, Int. J. Document Analy.Recog.,12, 2, 97–108,2009.
[11]. 11.Liu C. L. and Suen C. Y,“A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters”,Patt.Recog.,42, 12, 3287–3295,2009.
[12]. 12. Pal U, Wakabayashi T, and Kimura F, a.“Handwritten Bangla compound character recognition using gradient feature”, In Proceedings of the 10th Information Technology Conference (ICIT’07),208–213,2007.
[13]. 13. Pal U, Wakabayashi T, and Kimura F, b.“A system for off-line Oriya handwritten character recognition using curvature feature”, In Proceedings of the 10th Information Technology Conference (ICIT’07),227–229,2007.
[14]. 14.Pal U, Wakabayashi T, Sharma N, and Kimura F, c.“Handwritten Numeral Recognition of Six Popular Indian Scripts”,In Proceedings of 9th International Conference on Document Analysis and Recognition (ICDAR’07),749–753,2007.
[15]. 15. Pal U, Sharma N, Wakabayashi T, and Kimura F,“Handwritten character recognition of popular south Indian scripts”, Lecture Notes in Computer Science, vol. 4768, D. Doermann and S. Jaeger, Eds., Springer Verlag, 251–264,2008.
[16]. 16. Pal U, Roy K, and Kimura F,“A lexicon-driven handwritten city-name recognition scheme for Indian postal automation”, IEICE Trans. Inf. Syst. E92.D, 5, 1146–1158,2009.
[17]. 17. Sagheer M. W, He C. L., Nobile N, and Suen C. Y,“A new large Urdu database for offline handwriting recognition”, In Proceedings of the International Conference on Image Analysis and Processing (ICIAP’09),538–546,2009.
[18]. 18.http://lipitk.sourceforge.net/datasets/teluguchardata.html
[19]. 19. Hawkins W. (n.d.),“FFT interpolation for arbitrary factors: A comparison to cubic spline interpolation and linear interpolation”, Proceedings of 1994 IEEE Nuclear Science Symposium - NSS94.
[20]. 20. Kowalski M,“ThresholdingRulesand Iterative Shrinkage/ Thresholding Algorithm: A Convergence Study”,IEEE International Conference On Image Processing (ICIP),2014.
[21]. 21. Saha P. K, Borgefors G, and Baja G. S,“Skeletonization and its applications–a review”, Skeletonization,3-42,2017.
[22]. 22. Singh C, Bhatia N, and Kaur A,“Hough transform based fast skew detection and accurate skew correction methods”, PatternRecognition,41(12),3528-3546,2008.
[23]. 23. Ngoko Y, and Cerin C,“An Edge Computing Platform for the Detection of Acoustic Events”, IEEE International Conference on Edge Computing (EDGE),2017.
[24]. 24. A. Vaishnav and M. Mandot, "An Integrated Automatic Number Plate Recognition for Recognizing Multi Language Fonts," 2018 7th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida, India, 2018, pp. 551-556.
[25]. 25. Feng W, and Boukir S,“Class noise removal and correction for image classification using ensemble margin”, IEEE International Conference on Image Processing (ICIP),2015.
[26]. 26. Sawant A. S, and Chougule D,“Script independent text pre-processing and segmentation for OCR”, International Conference on Electrical, Electronics, Signals, Communication and Optimization (EESCO),2015.
[27]. 27. S. Senda and K. Yamada, "A maximum-likelihood approach to segmentation-based recognition of unconstrained handwriting text," Proceedings of Sixth International Conference on Document Analysis and Recognition, Seattle, WA, USA, 2001, pp. 184-188.
[28]. 28. C. J. Mathew, R. C. Shinde and C. Y. Patil, "Segmentation techniques for handwritten script recognition system," 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015], Nagercoil, 2015, pp. 1-7.
[29]. 29. Joshi, A., & Bharadwaj, D. (2015). “A Survey on Word Segmentation Method for Handwritten Documents", International Journal of Science and Research (IJSR),4(11), 993-996,2015.
[30]. 31. R. Amarnath, and Nagabhushan, P,“Spotting Separator Points at Line Terminals in Compressed Document Images for Text-line Segmentation”, International Journal of Computer Applications,172(4), 40-47,2017.
[31]. 32. Bal A, and Saha R,“An Improved Method for Handwritten Document Analysis Using Segmentation, Baseline Recognition and Writing Pressure Detection”, Procedia Computer Science,93, 403-415,2016.
[32]. 33. Gupta J. D, and Chanda B,“An Efficient Slope and Slant Correction Technique for Off-Line Handwritten Text Word”, Fourth International Conference of Emerging Applications of Information Technology,2014
[33]. 34. Anwar K,Adiwijaya, and Nugroho H,“A segmentation scheme of Arabic words with harakat”. IEEE International Conference on Communication, Networks and Satellite (COMNESTAT),2015.
[34]. 35. Gonzalez J. D, and Kinsner W,“Zero-crossing analysis of Lévy walks for real-time feature extraction”, IEEE International Conference on Electro Information Technology (EIT),2016.
[35]. 36. Jangid M, and Srivastava S,“Gradient Local Auto-Correlation for handwritten Devanagari character recognition”, International Conference on High Performance Computing and Applications (ICHPCA),2014.
[36]. 37. Gao X, JinL, Yin J, and Huang J. (n.d.),“A new stroke-based directional feature extraction approach for handwritten Chinese character recognition”, Proceedings of Sixth International Conference on Document Analysis and Recognition.
[37]. 38. Arefin N, Hassan M, Khaliluzzaman M, and Chowdhury,S. A,“Bangla handwritten characters recognition by using distance-based segmentation and histogram-oriented gradients”, IEEE Region 10 Humanitarian Technology Conference (R10-HTC),2017.
[38]. 39. Soltanzadeh H, and Rahmati M, “Recognition of Persian handwritten digits using image profiles of multiple orientations”, Pattern Recognition Letters,25(14), 1569-1576.
[39]. 40. R. Li, H. Wang and K. Ji, "Feature Extraction and Identification of Handwritten Characters", 8th International Conference on IntelligentNetworks and Intelligent Systems (ICINIS), Tianjin, pp. 193-196,2015.
[40]. 41.A. R. Zarei and R. Safabakhsh, "A new approach for feature extraction with applications to Automatic Writer Recognition", 2014 4th International Conference on Computer and Knowledge Engineering (ICCKE), Mashhad, pp. 13-17,2014.
[41]. 42.Cheng-Lin Liu,“Handwritten Chinese character recognition: effects of shape normalization and feature extraction”, In Proceedings of the conference on Arabic and Chinese handwriting recognition (SACH`06), David Doermann and Stefan Jaeger (Eds.). Springer-Verlag, Berlin, Heidelberg, 104-128,2006.
[42]. 43. B. El qacimy, M. Aitkerroum and A. Hammouch, "Handwritten digit recognition based on DCT features and SVM classifier", Second World Conference on Complex Systems (WCCS), Agadir, pp. 13-16,2014.
[43]. 44.Hamood, Mounir&Boussakta, Said,“Fast Walsh–Hadamard–Fourier Transform Algorithm. Signal Processing”, IEEE Transactions on. 59. 5627-5631,2011.
[44]. 45.Su, Teng& Yu, Feng.,“A Family of Fast Hadamard-Fourier Transform Algorithms. IEEE Signal Processing Letters”,19. 583-586,2012.
[45]. 46.Nguyen, Vu & Blumenstein, Michael, “An Application of the 2D Gaussian Filter for Enhancing Feature Extraction in Off-line Signature Verification”, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 339–343,2011.
[46]. 47. Dash K. S, Puhan N. B, and Panda G, “Odia character recognition:Adirectional review”, Artificial Intelligence Review, 48(4), 473-497,2016.
[47]. 48. Rushiraj I, Kundu S, and Ray B, “Handwritten character recognition of Odia script”, International Conference on Signal Processing, Communication, Power and Embedded System (SCOPUS),2016.
[48]. 49. A. Mowlaei, K. Faez and A. T. Haghighat, "Feature extraction with wavelet transform for recognition of isolated handwritten Farsi/Arabic characters and numerals", 14th International Conference on Digital Signal Processing Proceedings, DSP (Cat. No.02TH8628),Santorini, Greece, pp. 923-926,2002, vol.2.
[49]. 50.N. Rodrigues Gomes and Lee Luan Ling, "Feature extraction based on fuzzy set theory for handwriting recognition", Proceedings of Sixth International Conference on Document Analysis and Recognition, Seattle, WA, USA, pp. 655-659,2001.
[50]. 51.J. F. L. De Oliveira, G. V. Mendonca and R. J. Dias, "A modified fractal transformation to improve the quality of fractal coded images", Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269), Chicago,IL,USA,pp.756-759,1998,vol.1.
[51]. 52. B.V.Dhandra, R.G.Benne, MallikarjunHangarge, “ Handwritten Kannada Numeral Recognition Based on Structural Features” , Int. conference on Computational Intelligence and multimedia Applications,2007.
[52]. 53. Rajput, Ganapatsingh& H. B. Anita,“Handwritten Script Recognition using DCT and Wavelet Features at Block Level”, International Journal of Computer Applications,2010.
[53]. 54. Hiremath, Prakash &Shivashankar, S & D. Pujari, Jagdeesh&Mouneswara, V, “Script identification in a handwritten document image using texture features”,2010 IEEE 2nd International Advance Computing Conference, IACC 2010. 110–114,2010.
[54]. 55. K. Roy, A. Alaei and U. Pal, "Word-Wise Handwritten Persian and Roman Script Identification", 12th International Conference on Frontiers in Handwriting Recognition, Kolkata, pp. 628-633,2010.
[55]. 56.Roy, Kaushik& Banerjee, A & Pal, Umapada,“A system for word-wise handwritten script identification for Indian postal automation”, Proceedings of the IEEE INDICON 2004 - 1st India Annual Conference,266–271,2005.
[56]. 57. Majumder M, Saha A.K,“Artificial Neural Network. In: Feasibility Model of Solar Energy Plants by ANN and MCDM Techniques”,SpringerBriefs in Energy, Springer, Singapore,2016.
[57]. 58.Acharyya, Ankush&Rakshit, Sandip& Sarkar, Ram &Basu, Subhadip&Nasipuri, Mita,“Handwritten Word Recognition Using MLP based Classifier: A Holistic Approach”,2013.
[58]. 59. V. Babu, L. Prasanth, R. Sharma, G. V. Rao and A. Bharath, "HMM-Based Online Handwriting Recognition System for Telugu Symbols", Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), Parana,pp.63-67,2007.
[59]. 60. Yuan-Xiang Li and Chew Lim Tan, "Influence of language models and candidate set size on contextual post-processing for Chinese script recognition", Proceedings ofthe17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, pp. 537-540,2004, Vol.2.
[60]. 61.Natarajan P., MacRostie E., Decerbo M. (2009) The BBN Byblos Hindi OCR System. In: Govindaraju V., Setlur S. (eds) Guide to OCR for Indic Scripts. Advances in Pattern Recognition. Springer, London
[61]. 62. A. Basu, C. Walters and M. Shepherd, "Support vector machines for text categorization," 36th Annual Hawaii International Conference on System Sciences, 2003. Proceedings of the, Big Island, HI, USA, 2003, pp. 7 pp.-.
63.Pal, Umapada & Belaı̈d, A & Choisy, Christophe. (2003). "Touching Numeral Segmentation Using Water Reservoir Concept". Pattern Recognition Letters. 24. 261-272. 10.1016/S0167-8655(02)00240-4.
[62]. 64. B. B. Chaudhuri and S. Bera, "Handwritten Text Line Identification in Indian Scripts," 2009 10th International Conference on Document Analysis and Recognition, Barcelona, 2009, pp. 636-640