Topic : Image Compression Using Neural Network
Submitted By :-
Omkar Lokhande (A-68)
Content
• Introduction to the Neural Network
• Neural Network Structure
• Neural Network Structure
• Activation Function
• Functions of Neural Network
• Image Compression using BP Neural Network
• Output of this Compression Algorithm
• Other Neural Network Techniques
• References
Introduction to the Neural Network
• An artificial neural network is a powerful data
modeling tool that is able to capture and
represent complex input/output relationships.
• Can perform "intelligent" tasks similar to those
performed by the human brain.
Neural Network Structure
• A neural network is an interconnected
group of neurons
A Simple Neural Network
Neural Network Structure
An Artificial Neuron
Activation Function
Depending upon the problem variety of
Activation function is used:
Linear Activation function like step function
Nonlinear Activation function like sigmoid
function
Functions of Neural Network
• Compute a known function
• Approximate an unknown function
• Pattern Recognition
• Signal Processing
• Learn to do any of the above
Image Compression using BP Neural
Network [1]
• Future of Image Coding(analogous to our visual
system)
• Narrow Channel
• K-L transform
• The entropy coding
of the state vector
hi’s at the hidden layer.
Image Compression [2]
• A set of image samples is used to train the
network.
• This is equivalent to compressing the input into
the narrow channel and then reconstructing the
input from the hidden layer.
Image Compression [3]
• Transform coding with multilayer Neural
Network: The image to be subdivided into non-
overlapping blocks of n x n pixels each. Such
block represents N-dimensional vector x, N = n x
n, in N-dimensional space. Transformation
process maps this set of vectors into
y=W (input)
output=W-1y
Image Compression [4]
The inverse transformation need to reconstruct
original image with minimum of distortions.
Output of this Compression
Algorithm
Other Neural Network
Techniques
• Hierarchical back-propagation neural network
• Predictive Coding
• Depending upon weight function we have
• Hebbian learning-based image compression
Wi (t + 1)= {W(t) + αhi(t)X(t)}/||Wi (t) + αhi(t)X(t)||
References
• Neural networks Wikipedia
(http://en.wikipedia.org/wiki/Neural_network)
• Ivan Vilovic' : An Experience in Image Compression Using
Neural Networks
• Robert D. Dony, Simon Haykin: Neural Network Approaches
to Image Compression
• Constantino Carlos Reyes-Aldasoro, Ana Laura Aldeco: Image
Segmentation and compression using Neural Networks
• Image compression with neural networks - A survey --J.
Jiang*
Thank You !

Image Compression Using Neural Network

  • 1.
    Topic : ImageCompression Using Neural Network Submitted By :- Omkar Lokhande (A-68)
  • 2.
    Content • Introduction tothe Neural Network • Neural Network Structure • Neural Network Structure • Activation Function • Functions of Neural Network • Image Compression using BP Neural Network • Output of this Compression Algorithm • Other Neural Network Techniques • References
  • 3.
    Introduction to theNeural Network • An artificial neural network is a powerful data modeling tool that is able to capture and represent complex input/output relationships. • Can perform "intelligent" tasks similar to those performed by the human brain.
  • 4.
    Neural Network Structure •A neural network is an interconnected group of neurons A Simple Neural Network
  • 5.
    Neural Network Structure AnArtificial Neuron
  • 6.
    Activation Function Depending uponthe problem variety of Activation function is used: Linear Activation function like step function Nonlinear Activation function like sigmoid function
  • 7.
    Functions of NeuralNetwork • Compute a known function • Approximate an unknown function • Pattern Recognition • Signal Processing • Learn to do any of the above
  • 8.
    Image Compression usingBP Neural Network [1] • Future of Image Coding(analogous to our visual system) • Narrow Channel • K-L transform • The entropy coding of the state vector hi’s at the hidden layer.
  • 9.
    Image Compression [2] •A set of image samples is used to train the network. • This is equivalent to compressing the input into the narrow channel and then reconstructing the input from the hidden layer.
  • 10.
    Image Compression [3] •Transform coding with multilayer Neural Network: The image to be subdivided into non- overlapping blocks of n x n pixels each. Such block represents N-dimensional vector x, N = n x n, in N-dimensional space. Transformation process maps this set of vectors into y=W (input) output=W-1y
  • 11.
    Image Compression [4] Theinverse transformation need to reconstruct original image with minimum of distortions.
  • 12.
    Output of thisCompression Algorithm
  • 13.
    Other Neural Network Techniques •Hierarchical back-propagation neural network • Predictive Coding • Depending upon weight function we have • Hebbian learning-based image compression Wi (t + 1)= {W(t) + αhi(t)X(t)}/||Wi (t) + αhi(t)X(t)||
  • 14.
    References • Neural networksWikipedia (http://en.wikipedia.org/wiki/Neural_network) • Ivan Vilovic' : An Experience in Image Compression Using Neural Networks • Robert D. Dony, Simon Haykin: Neural Network Approaches to Image Compression • Constantino Carlos Reyes-Aldasoro, Ana Laura Aldeco: Image Segmentation and compression using Neural Networks • Image compression with neural networks - A survey --J. Jiang*
  • 15.