Handwritten Kannada Character Recognition Using Convolutional Neural Networks and Transfer Learning

Handwritten Kannada Character Recognition is special field of pattern recognition as different human being will have their own handwritten styles, machine considers even noise as a pattern. In order to classify each character, we present Convolutional Neural Networks and Transfer Learning techniques...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2023-10, Vol.2571 (1), p.12012
Main Authors: Madhu, S B, Aravinda, C V, Sannidhan, M S
Format: Article
Language:English
Subjects:
Artificial neural networks
Character recognition
Datasets
Edge detection
Gray scale
Handwriting recognition
Image processing
Learning
Neural networks
Pattern recognition
Physics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Handwritten Kannada Character Recognition is special field of pattern recognition as different human being will have their own handwritten styles, machine considers even noise as a pattern. In order to classify each character, we present Convolutional Neural Networks and Transfer Learning techniques. Here we use 74k dataset and labelling individual character as one class totally we had made 25 classes. Initially we pre-process each image of character to remove noise, convert to gray-scale, applied gaussian blur and canny edge detection and cropped the images and at last resizing it. These methods help in training neural networks to recognize the characters with good accuracy. Then we apply transfer learning to same dataset, here we resize image into three-dimensional and convert images into gray-scale and using xception we train the model. Even though a few of the kannada language’s characters have similarities, this model can accurately categorise each character to the appropriate class and identify it with better accuracy than CNN.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2571/1/012012