Deep Autoencoder-Based Image Compression using Multi-Layer Perceptrons
G.G.H.M.T.R. Bandara1, R. Siyambalapitiya2
1YG.G.H.M.T.R. Bandara*, Department of Statistics & Computer Science, Faculty of Science, University of Peradeniya, Peradeniya, Sri Lanka.
1R. Siyambalapitiya, Department of Statistics & Computer Science, Faculty of Science, University of Peradeniya, Peradeniya, Sri Lanka.
Manuscript received on May 02, 2020. | Revised Manuscript received on May 05, 2020. | Manuscript published on May 30, 2020. | PP: 1-6 | Volume-9 Issue-6, May 2020. | Retrieval Number: E3357039620/2020©BEIESP | DOI: 10.35940/ijsce.E3357.039620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: 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: The Artificial Neural Network is one of the heavily used alternatives for solving complex problems in machine learning and deep learning. In this research, a deep autoencoder-based multi-layer feed-forward neural network has been proposed to achieve image compression. The proposed neural network splits down a large image into small blocks and each block applies the normalization process as the preprocessing technique. Since this is an autoencoder-based neural network, each normalized block of pixels has been initialized as the input and the output of the neural network. The training process of the proposed network has been done for various block sizes and different saving percentages of various kinds of images by using the backpropagation algorithm. The output of the middle-hidden layer will be the compressed representation for each block of the image. The proposed model has been implemented using Python, Keras, and Tensorflow backend.
Keywords: Image Compression, Deep Learning, Autoencoder, Backpropagation Algorithm.