Title :
Image compression using stochastic neural networks
Author_Institution :
Dept. of Math. & Comput. Sci., Savannah State Coll., GA, USA
Abstract :
Image compression using stochastic artificial neural networks (SANNs) is studied. The ideal is to store an image in a stable distribution of a stochastic neural network. Given an input image f εF, one can find a SANN t ε T such that the equilibrium distribution of this SANN is the given image f. Therefore, the input image, f, is encoded into a specification of a SANN, t. This mapping from F (image space) to T (parameter space of SANN) defines the SANN transformation. It is shown that the compression ratio R of the SANN transformation is R=O(n/(K (log n)2)) where n is the number of pixels. To complete a SANN transformation, SANN equations must be solved. Two SANN equations are presented. The solution of SANN is briefly discussed
Keywords :
computational complexity; image coding; image processing; neural nets; equilibrium distribution; image compression; image space; mapping; parameter space; stochastic neural networks; Artificial neural networks; Equations; Fractals; Image coding; Neural networks; Neurons; Pixel; Predictive coding; Stochastic processes; Stochastic systems;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298788
