In the realm of advances in Processing Capabilities as well as Algorithms and their Efficiencies, transliteration mechanisms between Handwritten and Digital data namely called as Recognition Systems or Machine Reading Systems have been able to reach reliable precision. Devanagari and its variant scripts are widely used in the Indian Subcontinent. Being used by the second largest population in the world, it is practical to have research for Devanagari as well. While the current advances in recognition of Devanagari suggest requirement of more work and scope for accuracy levels, this survey aims to enlist the approaches taken in research to read handwritten Devanagari script. Citing works from different papers using different classifiers and techniques, it attempts to compare results and also imply the need of taking research forward. The survey contains methodologies followed in recent times, mentions data collection strategies or datasets available, uses classifiers and their recognition rates respectively.

Devanagari, Recognition, Segmentation, Pre-processing, Classification

[1] V.P. Agnihotri, “Offline Handwritten Devanagari Script Recognition”, International Journal Information Technology and Computer Science, pp. 37-42, 2012.
[2] A.N. Holambe, Dr. R.C.Thool, Dr. C.M.Jagade, “Printed and Handwritten Character & Number Recognition of Devanagari Script using Gradient Features”, International Journal of Computer Applications, Vol.2, Issue 9, pp. 0975-8887, 2010.
[3] A.Gaur, S.Yadav, “Handwritten Hindi Character Recognition using K-Means Clustering and SVM”, In the Proceedings of the 2015 IEEE 4th Symposium on Emerging Trends and Technologies in Libraries and Information Sciences, 2015.
[4] Niranjan Joshi, G.Sita, A.G. Ramakrishnan, Deepu V., Sriganesh Madhvanath, “Machine Recognition of Online Handwritten Devanagari Characters”, In the Proceedings of the 2005 8th International Conference on Document Analysis and Recognition (ICDAR’05), IEEE, 2005.
[5] P.B. Khanale, S.D. Chitnis, “Handwritten Devanagari Character Recognition using Artificial Neural Network”, Journal of Artificial Intelligence 4 (1), 2011.
[6] A. Dixit, A. Navghane, Y. Dandawate, “Handwritten Devanagari Character Recognition using Wavelet Based Feature Extraction and Classification Scheme”, In the Proceedings of 2014 IEEE Indian Conference (INDICON), 2014
[7] V.J. Dongre, V.M. Mankar, “A review of Research on Devanagari Character Recognition”, International Journal of Computer Applications, Vol.12, 2010.
[8] T. Mondal, U. Bhattacharya, S.K. Parui, K. Das, “Online Handwritten Recognition of Indian Scripts - the first benchmark”, In the Proceedings of the IEEE 12th International Conference on Frontiers in Handwriting Recognition, 2010 .
[9] R. Jayadevan, S.R. Kolhe, P.M. Patil, U. Pal, “Offline Recognition of Devanagari Script: A Survey”, IEEE Transactions on Systems, Man and Cybernetics- Part C: Applications and Reviews, Vol. 41, 2011.
[10] Shreya N. Patankar, Leena N. Ragha, “Zonal Moments Based Handwritten Marathi Barakhadi Recognition”, International Journal of Engineering Research and Technology (IJERT), Vol. 1, Issue 6, August 2012.
[11] J. Ryu, H.I. Koo, N.I. Cho, “Word Segmentation Method for Handwritten Documents based on Structured Learning”, IEEE Signal Processing Letters, Vol. 22, 2015.
[12] Shalaka Deore, Leena Ragha, “Moment Based Online and Offline Handwritten Character Recognition”, CiiT International Journal of Biometric and Bioinformatics, Vol. 3, March 2011, ISSN: 0974-9675.