The Cellular Frame Model for Representation and Aggregation of Knowledge in Image Understanding
Ryuichi Oka · Systems and Computers in Japan · 1988
Abstract This paper proposes a computational model of hierarchical labeling based on cellular automaton “Cellular Frame Model.” The model of the objective world is described by defining a set of labels called Cellular Frame used for representing knowledge. The reliability of existence of labels for representation by state equations whose initial conditions are determined by input level patterns is described. The state equations are of the form of local, parallel and iterative operations. The computational process of the state equations is considered as a process of aggregation (based on input label patterns) of label knowledge introduced for model description. In this paper, model describability of Cellular Frame is discussed from two viewpoints: hierarchy of the set of labels, and graphic interpretation of aggregate model. Convergence of labeling is ensured by the fact that the state equations always converge. In addition, several hypotheses have been ascertained by showing examples of models and simulation of labeling processes by state equations.