Handwritten Bangla Numerical Digit Recognition Using Fine Regulated Deep Neural Network

The recognition of handwritten Bangla digit is providing significant progress on optical character (OCR). It a very critical task due to the similar pattern and alignment handwriting digits. With modern research recognition, it reducing complexity classification by several methods, few problems encounter during wait be solved with simpler methods. emerging field artificial intelligence Deep Neural Network, which promises solid solution these problems. This paper proposed fine regulated deep neural network (FRDNN) for numeric problem that uses convolutional (CNN) models regularization parameters makes model generalized preventing overfitting. applied Traditional Network (TDNN) Fine layer experienced BanglaLekha-Isolated databases accuracies two were 96.25% 96.99%, respectively over 100 epochs. performance FRDNN dataset was more robust accurate than TDNN depend experimentation. Our method obtained good accuracy compared other existing available