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.

[1]  Olli Silven,et al.  Nonsegmenting defect detection and SOM-based classification for surface inspection using color vision , 1999, Industrial Lasers and Inspection.

[2]  G. M. Nijssen,et al.  Conceptual schema and relational database design - a fact oriented approach , 1989 .

[3]  Alan F. Murray,et al.  Synaptic Rewiring for Topographic Map Formation , 2008, ICANN.

[4]  Simon Y. Foo.  A rule-based machine vision system for fire detection in aircraft dry bays and engine compartments , 1996, Knowl. Based Syst..

[5]  Lotfi A. Zadeh,et al.  The Calculus of Fuzzy If/Then Rules , 1992, Fuzzy Days.

[6]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[7]  F. Herrera,et al.  A proposal on reasoning methods in fuzzy rule-based classification systems , 1999 .

[8]  Cheng-shung Wang,et al.  A fuzzy approximate reasoning model for a rule-based system in laser threat recognition , 1998, Fuzzy Sets Syst..

[9]  Vincent Bombardier,et al.  A FUZZY RECOGNITION MODEL BASED ON HUMAN SKILL INTEGRATION , 2006 .

[10]  Henri Prade,et al.  What are fuzzy rules and how to use them , 1996, Fuzzy Sets Syst..

[11]  Terry Halpin,et al.  Object-Role Modeling (ORM/NIAM) , 2006, Handbook on Architectures of Information Systems.

[12]  Daniel L. Schmoldt,et al.  Ultrasonic detection of knots, cross grain and bark pockets in wooden pallet parts , 2000 .

[13]  Hideo Tanaka,et al.  Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms , 1994, CVPR 1994.

[14]  Seref Sagiroglu,et al.  Training multilayered perceptrons for pattern recognition: a comparative study of four training algorithms , 2001 .

[15]  Yang Tao,et al.  Building a rule-based machine-vision system for defect inspection on apple sorting and packing lines , 1999 .

[16]  Terry Halpin,et al.  Information modeling and relational databases: from conceptual analysis to logical design , 2001 .

[17]  Anthony C. Bloesch,et al.  Data Modeling in UML and ORM: A Comparison , 1999, J. Database Manag..

[18]  Michael R. Berthold,et al.  Mixed fuzzy rule formation , 2003, Int. J. Approx. Reason..

[19]  Hisao Ishibuchi,et al.  A simple but powerful heuristic method for generating fuzzy rules from numerical data , 1997, Fuzzy Sets Syst..

[20]  Shakhatreh,et al.  Fuzzy Logic and Its Applications , 2007 .

[21]  Michio Sugeno,et al.  An introductory survey of fuzzy control , 1985, Inf. Sci..

[22]  Vincent Bombardier,et al.  A Fuzzy Reasoning Classification Method for Pattern Recognition , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[23]  H. Ishibuchi,et al.  Distributed representation of fuzzy rules and its application to pattern classification , 1992 .

[24]  Terry Halpin,et al.  Conceptual Schema and Relational Database Design , 1995 .

[25]  Sylvie Galichet,et al.  Integrating expert knowledge into industrial control structures , 2003, Comput. Ind..

[26]  Jouko Lampinen,et al.  WOOD SURFACE INSPECTION SYSTEM BASED ON GENERIC VISUAL FEATURES , 1998 .