NORMA eResearch @NCI Library

Image Compression using Convolutional Autoencoder

Bhattacharya, Shreya (2020) Image Compression using Convolutional Autoencoder. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (553kB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (525kB) | Preview

Abstract

The rapid emergence of several online platforms has led to the generation of an enormous amount of data, mostly in the form of images and videos. Multimedia data including graphical, audio and video data in the uncompressed form needs noticeable amount of storage space and bandwidth for its transmission. To combat with this excessive data traffic, the necessity of suitable image compression methods has become a necessity. Image compression is the reduction in the dimension of an image for beneficial storage and transmission. Various methodologies had immerged to solve this problem, but mostly suffered a major drawback, that is the reconstructed image suffers significant data loss. To cope with this challenge this research work advocates the contribution of deep learning, by creating a convolutional autoencoder. A convolutional autoencoder model has been created with 20 different layers and filters to get a better image compression model. This unsupervised machine learning algorithm will do the image compression by applying the backpropagation and reconstruct the input image with minimum loss. To eliminate the minimum data loss, a new instance has been introduced into the architecture for performing denoising. The architecture has proven its success in image compression and denoising, however it has paved a new path in further investigation regarding the improvisation of the model in terms of better compression factor and further reduction of data loss in case of higher dimensional image.
Keywords- Image compression, Autoencoder, denoising, image

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 18 Jan 2021 16:43
Last Modified: 18 Jan 2021 16:43
URI: https://norma.ncirl.ie/id/eprint/4385

Actions (login required)

View Item View Item