Offline Handwritten Devanagari Numeral Recognition Using Artificial Neural Network

P E Ajmire


Machine recognition of handwriting has been improving from last decay. The task of machine learning and recognition which also include reading handwriting is closely resembling human performance is still an open problem and also the central issue of an active field of research. Many researchers are working for fully automating the process of reading, understanding and interpretation of handwritten character. This research work proposes new approaches for extracting features in context of Handwritten Marathi numeral recognition. For classification technique Artificial Network is used. The overall accuracy of recognition of handwritten Devanagari numerals is 99.67% with SVM classifier, 99% with MLP and it is 98.13with GFF.

Full Text:



Ujjwal Bhattacharya, “Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals”, IEEE TRANSACTIONS On Pattern Analysis and Machine Intelligence, Vol.31, No.3, March, 2009.

G G Rajput and S M Mali , “Fourier Descriptor based Isolated Marathi Handwritten Numeral Recognition”, International Journal of Computer Applications, Vol.3, No.4, June 2010.

Gajanan Birajdar and Mansi Subheda, “Use of JPEG Algorithm in Handwritten Devanagari numeral Recognition”, International Journal of Distributed and Parallel Systems (IJDPS) Vol.2, No.4, July 2011.

Prerna Singh and Nidhi Tyagi, “Radial Basis Function for handwritten Devanagari Numeral Recognition”, International Journal of Advanced Computer Science and Applications, Vol. 2, No. 5, 2011.

Gita Sinha, Mrs. Rajneesh Rani, Prof. Renu Dhir, “Handwritten Devanagari Numeral Recognition Using Zonal Based Feature Extraction Method and SVM Classifier”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol.2(6), June 2012.

Mohamed H. Ghaleb, Loay, E. George, and Faisel G. Mohammed, “Numeral Handwritten Hindi/Arabic Numeric Recognition Method”, International Journal of Scientific & Engineering Research, Vol. 4(1), January-2013.

S. M. Mali, “Multiple Feature Extraction Method for Handwritten Marathi Numeral Recognition”, International Journal of Engineering Research & Technology, Vol. 2 (10), October – 2013.

Vijaya Rahul Pawar and Arun Gaikwad, “Performance Evaluation of Multistage Offline Marathi Script Recognition System”, International Journal of Computer Applications Vol. 88, No.4, February 2014.

P. E. Ajmire, R. V. Dharaskar, V. M. Thakare and S E Warkhede, “Structural Features for Character Recognition System-A Review”, International Journal of Advanced Research in Computer Science (IJARCS), Volume 3, No. 3, June 2012.

P. E. Ajmire, R. V. Dharaskar, V. M. Thakare, “Handwritten Devanagari (Marathi) Compound Character Recognition using Seventh Central Moment”, International Journal of Innovative Research in Computer and Communication Engineering, Vol. 3(6), June 2015.

N Dalal and B Triggs, “ Histogram oriented gradient for human detection”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.

Takuya Kobayashi, Akinori Hidaka, and Takio Kurita, “Selection of Histograms of Oriented Gradients Features for Pedestrian Detection”, International Conference on Neural Information Processing (ICONIP), LNCS Vol. 4985, pp. 598–607, 2008.

Parshuram M. Kamble , Ravinda S. Hegadi, “Handwritten Marathi character recognition using R-HOG Feature”, International Conference on Advanced Computing Technologies and Applications, Elsevier, Procedia Computer Science 45 pp.266 – 274, 2015

Sandhya Arora, D. Bhattacharjee, M. Nasipuri, D. K. Basu and M. Kundra, “Complementary Features Combined in a MLP-based System to Recognize Handwritten Devanagari Characters” Journal of Information Hiding and Multimedia Signal Processing Vo. 2,No.1 Jan 2011.

P. E. Ajmire, V M Thakare, R V Dharaskar, "Handwritten Devanagari (Marathi) Character Recognition Using SVM And MLP", International Journal Of Pure And Applied Research In Engineering And Technology, Vol. 4, Issue 4, pp. 1-10, July 2015.



  • There are currently no refbacks.

© International Journals of Advanced Research in Computer Science and Software Engineering (IJARCSSE)| All Rights Reserved | Powered by Advance Academic Publisher.