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 Tensor flow backend.
Highlights
Data Compression is one of the fascinating areas all over the world since people have limited storage to store huge data files such as high-quality images and videos
We have proposed an image compression algorithm based on an autoencoder model using a deep fully connected feed-forward neural network
Structural Similarity Index Measure (SSIM) The SSIM is a perceptual metric that quantifies the degradation of images
Summary
Data Compression is one of the fascinating areas all over the world since people have limited storage to store huge data files such as high-quality images and videos. Compression can be performed on various multimedia components such as text, video, image, audio, and graphics. A digital image is basically a two-dimensional array of pixels arranged on a two-dimensional space. Those pixels of an image may have redundant or irrelevant pixels. What we do is reduce those redundant pixels and remove irrelevant pixels. Those pixels are ignored by the human visual system in such a way that the compressed array of pixels consists of a smaller number of pixels than the original array of pixels
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Soft Computing and Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
