• Panil Jain
• Rajneesh Gupta
• Tejas Bhatkal
• Amit Kumar Yadav
• Dinesh Chaudhari

In terms of character recognition there are several papers reported and most of them are for English character. This paper focused on Devanagari character recognition from images. Devanagari script is used for many languages such as Sanskrit, Marathi, Nepali and Hindi. Lot of work has been done in character recognition and lot of work is to be done. Devanagari script should be given a special attention so that analysis of this language can be done effectively. This paper presents an approach for recognition of handwritten Devanagari characters, Total Fifty Eighth handwritten characters each having (vowels=220, consonant=2000, digits=2000) resulting in 94640 images are used for this experimentation. The final accuracy is around 90%. The handwritten characters are scanned and on every individual character’s image transform is applied so as to get decomposed images of characters. Character recognition provides an alternative way of converting manual text into digital format and reduces the dependence of man power

Devanagari, Character Recognition, Feature Extraction, Machine Learning, Neural Network

"Devanagari Character recognition using Image Processing & Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.300-303, April-2019, Available :http://www.jetir.org/papers/JETIR1904C48.pdf

"Devanagari Character recognition using Image Processing & Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp300-303, April-2019, Available at : http://www.jetir.org/papers/JETIR1904C48.pdf