Research Article
Image Denoising Using AI with Entropy as Metric Analysis
@INPROCEEDINGS{10.1007/978-3-031-66044-3_12, author={Mallellu Sai Prashanth and Ramesh Karnati and Muni Sekhar Velpuru and H. Venkateshwara Reddy}, title={Image Denoising Using AI with Entropy as Metric Analysis}, proceedings={Pervasive Knowledge and Collective Intelligence on Web and Social Media. Second EAI International Conference, PerSOM 2023, Hyderabad, India, November 24--25, 2023, Proceedings}, proceedings_a={PERSOM}, year={2024}, month={8}, keywords={RNN Flatten 2D layers Relu Sentiment Natural Language Processing Collective Intelligence Entropy}, doi={10.1007/978-3-031-66044-3_12} }- Mallellu Sai Prashanth
Ramesh Karnati
Muni Sekhar Velpuru
H. Venkateshwara Reddy
Year: 2024
Image Denoising Using AI with Entropy as Metric Analysis
PERSOM
Springer
DOI: 10.1007/978-3-031-66044-3_12
Abstract
This paper introduces a novel denoising approach Image denoising is one of the fundamental challenges in the field of image processing and computer vision. Our main aim of the project is to get a complete noiseless image with high accuracy and less time. So, in our project we are proposing an effective denoising technique using RNN (Recurrent neural network) for fixed pattern noisy images which may reduce the usage of number of auto encoders. Here, we are passing images into the recurrent neural networks as pixel information in the form of a 3D coordinate system. RNN doesn’t migrate the information from one node to another node until it gets its basic requirements. As we are using a single auto encoder, it will reduce noise as well as time complexity. The statistical analysis is going to be observed by using the following metric considerations, namely SNR (Signal to noise ratio), PSNR (Peak signal to noise ratio), MSE (Mean square error) and Entropy. From this research work we are going to get a complete noiseless image.
