论文信息 - A neural network construction algorithm with application to image compression

A neural network construction algorithm with application to image compression

We propose an algorithm for constructing a feedforward neural network with a single hidden layer. This algorithm is applied to image compression and it is shown to give satisfactory results. The neural network construction algorithm begins with a simple network topology containing a single unit in the hidden layer. An optimal set of weights for this network is obtained by applying a variant of the quasi-Newton method for unconstrained optimisation. If this set of weights does not give a network with the desired accuracy then one more unit is added to the hidden layer and the network is retrained. This process is repeated until the desired network is obtained. We show that each addition of the hidden unit to the network is guaranteed to increase the signal to noise ratio of the compressed image.

Guojun Lu | Rudy Setiono

[1] Giovanni L. Sicuranza,et al. Artificial neural network for image compression , 1990 .

[2] Raymond L. Watrous. Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization , 1988 .

[3] Tao Li,et al. Hierarchical classification and vector quantization with neural trees , 1993, Neurocomputing.

[4] Timur Ash,et al. Dynamic node creation in backpropagation networks , 1989 .

[5] Leon O. Chua,et al. A neural network approach to transform image coding , 1988 .

[6] S. Miyake,et al. Image data compression using a neural network model , 1989, International 1989 Joint Conference on Neural Networks.

[7] Yoshio Hirose,et al. Backpropagation algorithm which varies the number of hidden units , 1989, International 1989 Joint Conference on Neural Networks.

[8] Philipp Slusallek,et al. Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[9] D. Taylor,et al. A comparison of image compression by neural networks and principal component analysis , 1990, 1990 IJCNN International Joint Conference on Neural Networks.