Survey on Deep Learning using CNN for Character Recognition |
Author(s): |
Prajwal Sunil Walhekar , RMD Sinhgad School Of Engineering, Pune, Maharashtra; Mrs. Vina M. Lomte, RMD Sinhgad School Of Engineering, Pune, Maharashtra |
Keywords: |
Deep Learning, Transfer Learning, Convolutional Neural Networks (CNN), image classification, image segmentation, Optical Character Recognition (OCR), Feature Extraction |
Abstract |
Since past few years, deep neural networks are becoming highly popular because of their increasing performance. They are getting highly used in various machine learning tasks such as regression, segmentation, classification, detection and pattern recognition. Character recognition is currently gaining attention of most of the researchers because of its enormous applications in various sectors like human-robot interaction, data entry for business documents, etc. Recognition of characters is challenging task, but Deep learning techniques can be effectively used as a solution for various such problems. Person to person variations in writing style makes handwritten character recognition one of the most difficult tasks. There are hundreds of ways to write a single letter or a digit which automatically increases the size of the dataset to be used. The aim of this work is to incorporate machine learning techniques to improve the character recognition process. |
Other Details |
Paper ID: IJSRDV8I30054 Published in: Volume : 8, Issue : 3 Publication Date: 01/06/2020 Page(s): 90-94 |
Article Preview |
|
|