Bengali Handwritten Numeric Character Recognition using Denoising Autoencoders

This work describes the recognition of Bengali Handwritten Numeral Recognition using Deep Denoising Autoencoder using Multilayer Perceptron (MLP) trained through backpropagation algorithm (DDA). To bring the weights of the DDA to some good solution a layer wise pre-training is done with Denoising Autoencoders. Denoising Autoencoders using MLP trained through backpropagation algorithm are made by introducing masking noise at input to the Autoencoder to capture meaningful information while hidden layers are remain untouched at pre-training. Those pre-trained Denoising Autoencoders are then stacked to build a DDA. DDA is then converted to a Deep Classifier (DC) by using a final output layer. After a final fine-tune best DC is selected to discriminate classes. Performance of the DC using DDA is compared with the Deep Autoencoder using MLP trained through backpropagation (DA) and Support Vector Machines (SVM). From the experiment it is evident that recognition performance of DDA that is 98.9% is higher than DA and SVM those are 97.3% and 97%. Using their performance at validation set results are further combined to build a Hybrid Recognizer that gives a performance of 99.1%