Abstract
Image compression is one of the advantageous techniques in several types of multimedia services. And recently deep learning has been so developed that it is being used for image compression. In image compression, consider we have images of various dimensions. One such dimension is 28 by 28. Images are formed by combining red, green and blue (RGB) in various proportions to obtain any color in the visible spectrum. The image is made up of pixels and have some noise in them. We propose a Convolutional Auto encoder neural network for image compression by taking MNIST (Modern National Institute of Standards and Technology) dataset where we up sample and downs sample an image. We take an image 28 by 28 images with noise, which is an RGB image. By developing deep learning image should be compressed to 28 by 1 dimensional dense vector. After the compression final resulting image should have the original dimension of 28 by 28. The main objective is to compress an image without affecting the quality of image radically.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
El Zorkany M (2014) A hybrid image compression technique using neural network and vector quantization with DCT. In: Choras RS (ed) Image processing and communications challenges 5. advances in intelligent systems and computing, vol 233. Springer, Heidelberg
Deng L. The MNIST database of handwritten digit images for machine learning research. In: Proceedings of the digital object identifier. https://doi.org/10.1109/msp.2012.2211477
Zhu W. Classification of MNIST handwritten digit database using neural network. In: Proceedings of the research school of computer science. Australian National University, Acton, ACT 2601, Australia. u6148896@anu.edu.au
Wen T, Zhang Z. Deep convolution neural network and autoencoders-based unsupervised feature learning of EEG signals
Jiang J (1999) Image compression with neural networks a survey. In: Proceedings of the school of computing. University of Glamorgan, Pontypridd CF37 1DL, UK
Zhao H, Gallo O, Frosio I, Kautz J. Loss functions for image restoration with neural networks. In: Proceedings of the NVIDIA. MIT Media Lab
Huan G (2016) Densely connected convolutional networks
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Raut, Y., Tiwari, T., Pande, P., Thakar, P. (2020). Image Compression Using Convolutional Autoencoder. In: Kumar, A., Paprzycki, M., Gunjan, V. (eds) ICDSMLA 2019. Lecture Notes in Electrical Engineering, vol 601. Springer, Singapore. https://doi.org/10.1007/978-981-15-1420-3_23
Download citation
DOI: https://doi.org/10.1007/978-981-15-1420-3_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1419-7
Online ISBN: 978-981-15-1420-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)