Own Handwritten Digit recognition using MLP and CNN in tensorflow
Author(s):
Deepti Nikumbh, Rupali Santosh Kale
Keywords:
Digit recognition,MLP,CNN
Abstract
Object recognition in image is very popular and is widely used in almost all image processing applications. Handwritten digit recognition system is one such application. This paper presents an approach on developing a handwritten digit recognition system using multi-layer neural network and Convolutional Neural Network. These neural network models are trained and tested using the MNIST dataset. Further a real time dataset of authors own handwritten digit where used to test the performance of the system , a comparison of two deep learning models in terms of accuracy i.e successfully classifying digits between 0-9 and computational time taken is presented. The neural network models are developed in python using tensorflow a machine learning library.
Article Details
Unique Paper ID: 148591
Publication Volume & Issue: Volume 6, Issue 3
Page(s): 180 - 184
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024