Handwritten character recognition using tensor flow

Abstract

In this paper we present an inventive strategy for disconnected manually written character discovery utilizing profound neural systems. In this day and age, it has gotten simpler to prepare profound neural systems in light of accessibility of enormous measure of information and different Algorithmic developments which are occurring. Presently a-days the measure of computational force expected to prepare a neural system has expanded because of the accessibility of GPU's and other cloud-based administrations like Google Cloud stage and Amazon Web Services which give assets to prepare a Neural system on the cloud. We have planned a picture division based Handwritten character acknowledgment framework. In our framework we have utilized OpenCV for performing Image handling and have utilized Tensor flow for preparing a neural Network. We have built up this framework utilizing python programming language.