Object-centered representation for species systematics and identification in living systems in nature

An artificial intelligence application to identification in biological taxonomy is presented. An object-centered representation is described using SHIRKA, a knowledge-based system developed in France. The capacities of this system, relating to a classification algorithm, are described. An application to the identification of the trees and lianas of the evergreen forests of the Western Ghats (India) is presented to illustrate the problems encountered in the development of the knowledge base. A model of a systematist's reasoning, using evolutionary principles, is the basis of this work. Finally the efficiency of the system is discussed.