Back Propagation Neural Network Based Image Compression
Journal Title: International journal of Emerging Trends in Science and Technology - Year 2014, Vol 1, Issue 7
Abstract
Compression algorithms are methods that reduce the number of symbols used to represent source information, therefore reducing the amount of space needed to store the source information or the amount of time necessary to transmit it for a given channel capacity. This paper presents a neural network based technique and wavelet based compression. A three layered Back propagation Neural Network (BPNN) was designed for building image compression system. The Back propagation neural network algorithm (BP) was Used for training the designed BPNN.
Authors and Affiliations
Ashu Bansal
Keywords
Related Articles
- EP ID EP221040
- DOI -
- Views 111
- Downloads 0
Profitability Analysis of Selected New Private Sector Banks in India: Who is better?
New private sector banks developed the concept of direct selling agents who reached out to customers with credit products, taking loans to the customer’s doorstep. Not only did the private sector banks expand in this man...
Non-Local Image De-noising and Post Processing Using KL Transform
In this paper an efforts has been made to estimate pixel intensity based on information present in the whole image and thereby exploiting the presence of similar patterns and features. The method is called non-local imag...
E-Learning: An Effective virtual way to understand the physical world
The objective of physical laboratory training is to provide an experimental base for the theoretical concepts introduced during the lectures. It gives an opportunity to students to verify ideas which they learn in theory...
Malicious Agent Detection In Multi Party Data Access Structure
A data distributor has given sensitive data to a set of supposedly trusted agents (third parties). Some amount of data is leaked and found in an unauthorized machines (e.g., on the internet or computer). The distributor...
Cubic Graceful Labeling for Star and Bistar Related Graphs
In this paper we proved some new theorems related with Cubic Graceful Labeling. A graphG(V,E) with n vertices and m edges is said to be a Cubic graceful graph if there exists an injective functionf:V(G)→{0,1,2,3,………m3 }...