• Mikita R. Gandhi
• Dr. Vishvjit Thakar
• Dr. Hetal Patel

In the morden world, Handwritten charecter recognition is a method extensively used and still it is very essential challenge. Conventional machine-learning techniques need hand craft feature vector extraction from raw data and its required skill to convert input pattern into descriptor which could used in classifier to make a decision for a particular class where it belongs. To handle herewith dilemma, the Convolutional Neural Networks (CNN) was introduced recently, had not required traditional feature extraction method, the network learned itself and had given the better result than usual classification methods. In this paper, off- line Gujarati character was recognizing using Convolutional Neural Network. This method has been shown a new era for Gujarati handwritten OCR and gave satisfactory result in the field of Gujarati Handwritten Character Recognition. In this approach, Gujarati Handwritten database was created, 5000 samples for numerals and 10,000 samples for alphabets. Experiment result had shown 95.10% and76.25% accuracy for numerals and alphabets respectivly

Handwritten Gujarati character Recognition, Convolutional Neural Network, Convolutional Layer, Pooling Layer, Fully connected Layer

"Gujarati Handwritten character Recognition using Convolutional Neural Network ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.518-523, May-2019, Available :http://www.jetir.org/papers/JETIR1905L79.pdf

"Gujarati Handwritten character Recognition using Convolutional Neural Network ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp518-523, May-2019, Available at : http://www.jetir.org/papers/JETIR1905L79.pdf