BDNet: Bengali Handwritten Numeral Digit Recognition based on Densely connected Convolutional Neural Networks
This work addresses the problem of digit recognition for Bengali script, which is incremental as it applies an existing deep learning architecture to a specific domain with improved performance.
The paper tackles Bengali handwritten numeral digit recognition by proposing BDNet, a densely connected convolutional neural network, achieving a test accuracy of 99.775% on the ISI dataset, which represents a 62.5% error reduction compared to previous state-of-the-art models.
Images of handwritten digits are different from natural images as the orientation of a digit, as well as similarity of features of different digits, makes confusion. On the other hand, deep convolutional neural networks are achieving huge success in computer vision problems, especially in image classification. BDNet is a densely connected deep convolutional neural network model used to classify (recognize) Bengali handwritten numeral digits. It is end-to-end trained using ISI Bengali handwritten numeral dataset. During training, untraditional data preprocessing and augmentation techniques are used so that the trained model works on a different dataset. The model has achieved the test accuracy of 99.775%(baseline was 99.40%) on the test dataset of ISI Bengali handwritten numerals. So, the BDNet model gives 62.5% error reduction compared to previous state-of-the-art models. Here we have also created a dataset of 1000 images of Bengali handwritten numerals to test the trained model, and it giving promising results. Codes, trained model and our own dataset are available at: {https://github.com/Sufianlab/BDNet}.