IJBTT

Enhancing Performance of Devanagari Script Recognition using Hopfield ANN

	International Journal of Engineering Trends and Technology (IJETT)
	© 2016 by IJETT Journal
	Volume-36 Number-2
	Year of Publication : 2016
	Authors : Pooja Yadav, Sonia Sharma
	DOI :  10.14445/22315381/IJETT-V36P213

Citation 

Pooja Yadav, Sonia Sharma"Enhancing Performance of Devanagari Script Recognition using Hopfield ANN", International Journal of Engineering Trends and Technology (IJETT), V36(2),66-75 June 2016. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
Character Recognition (CR) has broad area of research in English as well as Hindi character. Hindi is the most widely spoken language in India, as there is no separation between the characters of texts written in Hindi as there is in English, Character Recognition systems developed for the handwritten Hindi language carry a very poor recognition rate. Devanagari character recognition provides less correctness and efficiency.In this paper, we propose a method for recognition of characters which implement Gabor filters and Freeman Chain Coding (FCC) for featureextraction and Hopfield neural network as classifiers to get best recognition rate of Hindi characters recognition.

 References

[1] V. Shiv Naga Prasad and Justin Domke, ”Gabor Filter Visualization”,IEEE Trans. Visualization and Computer Graphics, vol. 8, no. 1, pp. 1–8, March1996
[2] Tai Sing Lee,”Image Representation Using 2D Gabor Wavelets”,IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 10, october 1996
[3] Cheng-Lin Liu,Masashi Koga and iromichiFujisawa,” Gabor feature extraction for character recognition: Comparison with gradient feature”DOI: 10.1109/ICDAR.2005.119 · Source: IEEE Xplore Conference Paper · January 2005
[4] NicolaePopoviciu and MioaraBoncut,”On the Hopfield algorithm. Foundations and examples”,General Mathematics Vol. 13, No. 2 (2005)
[5] Satish Kumar,” Performance increment of Features on Devanagari Hand-printed Dataset”, International Journal of Recent Trends in Engineering, Vol. 1, No. 2, May 2009
[6] Nor AmizamJusohand JasniMohamadZain ,”Application of Freeman Chain Codes: An Alternative RecognitionTechnique for Malaysian Car Plates”, IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.11, November 2009
[7] Yash Pal Singh, AbhilashKhare and Amit gupta,”Analysis of Hopfield Autoassociative Memory in the Character Recognition”, (IJCSE) International Journal on Computer Science and EngineeringVol. 02, No. 03, 2010, 500-503
[8] Anshul Gupta, Manisha Srivastava and ChitralekhaMahanta,” Offline Handwritten Character Recognition Using Neural Network”, International Conference on Computer Applications and Industrial Electronics (ICCAIE 2011),2011
[9] Sukhpreet Singh, Ashutosh Aggarwal and RenuDhir,” Use of Gabor Filters for Recognition of Handwritten Devanagari Character”,International Journal of Advanced Research in Computer Science and Software Engineering Volume 2, Issue 5, May 2012 ISSN: 2277 128X
[10]Ashutosh Aggarwal, Rajneesh Rani and RenuDhir,”Handwritten Devanagari Character Recognition Using Gradient Features”, International Journal of Advanced Research in Computer Science and Software Engineering Research Paper,Volume 2,Issue 5, May 2012, ISSN: 2277 128X
[11]Prashant M. Kakde and Vivek R. Raut,” Performance Analysis of Handwritten Devnagri Characters Recognition through Machine Intelligence”, International Journal of Emerging Technology and Advanced Engineering, Volume 2, Issue 7, July 2012, ISSN 2250-2459
[12]Gunjan Singh and SushmaLehri,”Recognition of Handwritten Hindi Characters using Backpropagation Neural Network”, (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 3 (4) , 2012,4892-4895
[13] Ved Prakash Agnihotri,”Offline Handwritten Devanagari Script Recognition”,378-1-3299-3020-6190/$31.00 ©2012 IEEE,2012
[14] DivakarYadav, Sonia Sánchez-Cuadrado and Jorge Morato,”Optical Character Recognition for Hindi Language Using a Neural-network Approach”, J Inf Process Syst, Vol.9, No.1, March 2013
[15]Shruti Agarwal and Dr. Naveen Hemarjani,”Offline Handwritten Character Recognition with Devnagari Script”, IOSR Journal of Computer Engineering (IOSR-JCE) ,Volume 12, Issue 2 (May. - Jun. 2013), PP 82-86, e-ISSN: 2278-0661, p- ISSN: 2278-8727
[16]S SSayyad, AbhayJadhav, ManojJadhav, SmitaMiraje, PradipBele and AvinashPandhare,”Devnagiri Character Recognition Using Neural Networks”, 2277-3754-7156/$31.00 ©20l3 IEEE, July 2013
[17] Pulipati Annapurna, SriramanKothuri and SrikanthLukka,”Digit Recognition Using Freeman Chain Code”,IJAIEM Volume 2, Issue 8, August 2013 ISSN 2319 – 4847
[18] Prof. SonalP.Patil and Ms. Priyanka P. Kulkarni ,” Online Handwritten Hindi Character Recognition Using Support Vector Classification”, Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 5( Version 1), May 2014, pp.82-91
[19]NehaSahu,Shipra Gupta and Shilpa Srivastava Khare,” Neural Network based approach for Recognition for Devanagiri Characters”, International Journal of Advanced Technology in Engineering and Science Volume No.02, Issue No. 05, May 2014 ISSN (online): 2348 – 7550
[20] Andrea Torsello,”Artificial IntelligenceHopfield Networks”IJAIEM Volume 2, Issue 8, August 2014 ISSN 2319 – 4847
[21] Ms. Seema A. Dongare, Prof. Dhananjay,Kshirsagar, Mr. NitinJ.Khapale and Ms. Amruta D. Pawar,”Artificial Neural Network For Recognition Of Handwritten DevanagariCharacter”, IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, Volume 17, Issue 1, Ver. I (Jan – Feb. 2015), PP 60-64, ISSN: 2278-8727
[22] Pooja Yadav and Sonia Sharma,” A Review on Various Techniques of Devanagari Script Recognition”, International Journal of Engineering Trends and Technology (IJETT) – Volume 33 Number 6- March 2016
[23]http://www.macs.hw.ac.uk/~nkt/leares/Artificial%20Neural%2 0Networks/ANN%203a%20Hopfield%20Analysis.pdf,”“Hopf ield Training Rules”

Keywords
Devanagari Script, Offline Character Recognition, Gabor Filter, Freeman Chain Coding (FCC), Hopfield ANN.