Deep convolutional neural network classifier for handwritten devanagari character recognition

Abstract

The performance of two architecture of Neural Networks are compared for handwritten Devanagari character recognition. The first one is the fully connected Feed-forward Neural Network and the second one is deep Convolutional Neural Network. Deep learning is basically a biologically inspired technique based on human brain. A part of brain called neocortex is having layered architecture. The advantage of using CNN is that it does not require complex preprocessing or feature extraction algorithm. Image pixels are the input for the two networks. We obtained the improved result for standard character benchmarking datasets.