What is it about?
Convolutional neural Network optimizes weights and filter parameters in hidden layers to generate features suitable for classification problems. In the paper CNN model with four layer architecture is best suited for recognition of Kannada characters
Featured Image
Photo by ROOQ Boxing on Unsplash
Why is it important?
In our algorithm , Feature visualization method to visualize the features and decide on the number of layers in CNN along with variation in size of the filter. Thus complexity of the model is analyzed
Perspectives
This article will help researchers in deep learning on pattern recognition. They can explore for other types of image recognition. This algorithm can used for text recognition and convert the text to speech. This can be used for online handwriting recognition.
Dr Indira K
M S Ramaiah Institute of Technology
Read the Original
This page is a summary of: Recognition of Kannada characters using deep learning approach, Journal of Intelligent & Fuzzy Systems, July 2022, IOS Press,
DOI: 10.3233/jifs-212680.
You can read the full text:
Contributors
The following have contributed to this page
