MATLAB SIMULATION FOR IMPROVED
IMAGE COMPRESSION USING
CSC 363 1.5 Research Methodologies and Scientific Computing
Department of Computer Science and Statistics , USJP
The development of Internet and multimedia
technologies that grow exponentially, resulting in
the amount of information managed by computer is
This causes serious problems in storage and
transmission image data.
Therefore, should be considered a way to
compress image data so that the storage capacity
required will be smaller.
Image Compression using Artificial Neural
Networks (ANN) is a topic where research is being
carried out in various directions towards achieving a
generalized and economical network.
Feed-forward Networks using Back propagation
Algorithm adopting the method of steepest descent
for error minimization is popular and widely adopted
and is directly applied to image compression.
Qie et al. in 1994 proposed an image compression
scheme using the Backpropagation algorithm.
MATLAB is consist with
MATLAB is consist with
can be easily
MATLAB system for image compression using neural
To find out how the visual quality of the compressed
image is preserved with proposed system
To make a better image compression system using
1. Image segmentation.
2. Choose network parameters.
I. Input parameters
II. Output parameters (target)
III. Activation function
IV. Number of layers
V. Number of neurons in each layer.
3. Build and train the NN.
4. Reconstruct images.
Analyzing and Evaluation
Apply NN with novel images.
Small training image set
Small testing image set
Only grayscale images
Simulation in a single computer, so that it will
consume considerable computational time
Image compression using back propagation is a
wide research area.
Improvements to the back propagation can be
easily implemented with MATLAB.
Simulation for back propagation will construct a
foundation before the actual implementation.
AL-Allaf, O. N., 2010. Improving the Performance of
Backpropagation Neural Network. Journal of Computer
Science 6 (11), pp. 1347-1354.
Anon., n.d. MATLAB Toolbox. [Online]
Available at: http://www.mathworks.in/products/neural-
[Accessed 09 08 2013].
Demuth, H., Beale, M. & Hagan, M., 1992. Neural Network
Toolbox™ 6, s.l.: s.n.
Masters, T., 1994. Signal and Image Processing with Neural
Networks, s.l.: John Wiley & Sons,Inc.
Qie, G., Terrell, T. J. & Varley, M. R., 1994. Improved Image
Compression using Backpropagation Networks. U.K., IEEE,
Sivanandam, S. N., 2006. In: Introduction to Neural Networks
using MATLAB 6.0. New Delhi: Tata McGrow-Hill, pp. 397-