A brain can easily able to recognize handwritten words which computers are still struggling to figure out what they are. This amazing power of the brain requires to be transferred to a computer for automatic digitalization of handwritten texts and manuscript. The work proposed in this paper tried to make a model which is able to recognize and predict different Hindi character which can be further used to identify and digitalize the whole page or text. Our model uses different approaches like a base-line neural network, convolutional neural network, and a simple logistic regression model. © 2019 IEEE.