Image Compression Technique Based on Fractal Image Compression Using Neural Network – A Review release_xfzerlnpynanfolnypa7nbzm6i

by Diyar Waysi Naaman

Published in Asian Journal of Research in Computer Science by Sciencedomain International.

2021   p47-57

Abstract

Image compression research has increased dramatically as a result of the growing demands for image transmission in computer and mobile environments. It is needed especially for reduced storage and efficient image transmission and used to reduce the bits necessary to represent a picture digitally while preserving its original quality. Fractal encoding is an advanced technique of image compression. It is based on the image's forms as well as the generation of repetitive blocks via mathematical conversions. Because of resources needed to compress large data volumes, enormous programming time is needed, therefore Fractal Image Compression's main disadvantage is a very high encoding time where decoding times are extremely fast. An artificial intelligence technique similar to a neural network is used to reduce the search space and encoding time for images by employing a neural network algorithm known as the "back propagation" neural network algorithm. Initially, the image is divided into fixed-size and domains. For each range block its most matched domain is selected, its range index is produced and best matched domains index is the expert system's input, which reduces matching domain blocks in sets of results. This leads in the training of the neural network. This trained network is now used to compress other images which give encoding a lot less time. During the decoding phase, any random original image, converging after some changes to the Fractal image, reciprocates the transformation parameters. The quality of this FIC is indeed demonstrated by the simulation findings. This paper explores a unique neural network FIC that is capable of increasing neural network speed and image quality simultaneously.
In application/xml+jats format

Archived Files and Locations

application/pdf  761.8 kB
file_oxkrge374zex7bcejz5xmerkle
www.journalajrcos.com (publisher)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2021-07-23
Journal Metadata
Not in DOAJ
Not in Keepers Registry
ISSN-L:  2581-8260
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d0017793-a596-4a91-9081-f0f580ed4015
API URL: JSON