There is a special kind of physical platform called [[cellular automata]] that can perform different kinds of computation. Although the principle of cellular automata is very attractive, it is difficult to build a [[general-purpose computer]] based on it for performing real engineering tasks. Since many [[image processing]] tasks are “cellular” in nature, it had been found that cellular processing hardware platforms can be used to perform these tasks. There are at least two kinds of hardware platforms for implementing cellular automata for the purpose of image processing. The first one is called [[cellular logic]] array and the second one is called [[cellular neural network]]. Cellular neural network is also known as cellular nonlinear network.
The theory of cellular image processing is based on cellular logic and is the basis for designing image processing algorithms based on [[cellular hardware]]. It consists of the follows.
*[[Local rule]]s and its implementation.
*Decomposing global image processing tasks by using local rules.
*Signal propagation along local connectedness.
Cellular image processing is a way of designing super-fast image processing platforms. There are different [[VLSI]] implementations of [[cellular nonlinear network]]s to achieve this goal. The first comprehensive book addressing cellular image processing was written by [[Tao Yang (Wuxi)|Tao Yang]].
