A Generalized Deep Learning Model for Denoising Image Datasets
Kurian Thomas1, Pranav E.2, Supriya M.H.3
1Kurian Thomas, Department of Electronics, Cochin University of Science & Technology, Kochi, India.
2Pranav E., Department of Electronics, Cochin University of Science & Technology, Kochi, India.
3Supriya M.H.*, Department of Electronics, Cochin University of Science & Technology, Kochi, India.
Manuscript received on September 02, 2020. | Revised Manuscript received on September 15, 2020. | Manuscript published on October 30, 2020. | PP: 9-14 | Volume-10 Issue-1, October 2020. | Retrieval Number: 100.1/ijeat.F1555089620 | DOI: 10.35940/ijeat.A1665.1010120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Advance in technology world has lots of contributions from artificial intelligence which is a highly growing area. The failure of traditional algorithms has led to the employment of deep learning algorithms in various fields like pattern recognition, recommendation systems and classification systems. Removal of noise from images can be done using traditional noise removal filters. These filters can either remove more noise that wanted or leave unwanted noise than what is needed in the data. Utilization of Convolutional neural networks designed based on the dataset requirements along with the noise removal filter can yield better results. In this work, evaluation of the performance of convolutional neural network (CNN) against existing image denoising algorithms has been successfully executed . The proposed model is a generalized CNN model which can recognize and classify any type of noisy image given. Two types of model were compared where one model 1 uses the Adam optimizer and model 2 uses the Stochastic Gradient Descent (SGD) optimizer. The image dataset used here is MNIST handwritten dataset, which is trained, tested and validated with both the models by adding three different types of noise viz, Poisson, Salt and Pepper as well as Gaussian Noise. More accuracy and better results were given by the model 2 which uses the SGD optimizer.
Keywords: Adam, Convolutional Neural Network, Classification, SGD.
Scope of the Article: Deep Learning