| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 723127 | IFAC Proceedings Volumes | 2006 | 6 Pages |
This article presents the improvement of a defect recognition system for fibrous products by using knowledge integration from two expert fields. These two kinds of knowledge that we want to integrate respectively concern wood expertise and industrial vision expertise. First, extraction, modelling and integration of knowledge use the Natural language Information Analysis Method (NIAM) to be formalised from their natural language expression. Then, to improve a classical industrial recognition system using vision, we propose to use the resulting symbolic model of knowledge to partially build a numeric model of defect recognition. This model is created according to a tree structure where each inference engine is a Fuzzy Rules 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 with industrial data show the efficiency of such an approach.
