Contribution of fuzzy reasoning method to knowledge integration in a defect recognition system

This article presents the improvement of a defect recognition system for wooden boards by using knowledge integration from two expert fields. These two kinds of knowledge to integrate respectively concern wood expertise and industrial vision expertise. First of all, extraction, modelling and integration of knowledge use the Natural Language Information Analysis method (NIAM) to be formalized from their natural language expression. Then, to improve a classical industrial vision system, we propose to use the resulting symbolic model of knowledge to partially build a numeric model of wood defect recognition. This model is created according to a tree structure where each inference engine is a fuzzy rule based inference system. The expert knowledge model previously obtained is used to configure each node of the resulting hierarchical structure. The practical results we obtained in industrial conditions show the efficiency of such an approach.