• R Vijaya Kumar Reddy
• U Ravi Babu

In this paper we present an efficient handwritten numeral digit recognition system based on a Deep Feed Forward Neural Network for Handwritten Hindi Digits Recognition using CELSoftmax technique. Handwritten digit recognition plays an important role in with the explosive growth in size of datasets of document processing and it becomes more significant to develop effective learning schemes for neural networks to deal with large scale data modeling. The proposed system has been trained on samples of 15000 images and tested on samples of 5000 images from kaggle data set and from this experiment we achieved 99.52% recognition An experimental result showed a very good recognition rate in comparison with other neural network based algorithm that use the same recognition classifier.

"A Deep Feed Forward Neural Network for Handwritten Hindi Digits Recognition using CELSoftmax", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.556-565, February-2019, Available :http://www.jetir.org/papers/JETIR1902075.pdf

"A Deep Feed Forward Neural Network for Handwritten Hindi Digits Recognition using CELSoftmax", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp556-565, February-2019, Available at : http://www.jetir.org/papers/JETIR1902075.pdf