A Hybrid Inspection Method for Surface Defect Classification
A vision-based inspection method based on rough set theory, fuzzy set and BP algorithm is presented. The rough set method is used to remove redundant features for its data analysis and procession ability. The reduced data is fuzzified to represent the feature data in a more suitable form as input data of a BP network classifier. The classifier is optimised using uniform design. By the experimental research, the hybrid method shows good classification accuracy and short running time, which are better than the results using BP network and neural network with fuzzy input.
KeywordsVision-Based Inspection Classification Fuzzy Rough Set Neural Network Uniform design
Unable to display preview. Download preview PDF.
- 1.Huber, H.A., Mcmilin, C.W., Mckinney, J.P.: Lumber Defect Detection Abilities of Furniture Rough Mill Employees. Forest Products Journal 35(11/12), 79–82 (1985)Google Scholar
- 2.Polzleitner, W., Schwingshakl, G.: Real-time Surface Grading of Profiled Wooden Boards. Industrial Metrology, 283–298 (1992)Google Scholar
- 3.Li, M.X., Wu, C.D., Yue, Y.: A Hierarchical Clustering Method for Attribute Discretization in Rough Set Theory. In: Proceedings of International Conference on Machine Learning and Cybernetics (ICMLC), Shanghai, China, August 26-29, vol. 6, pp. 3650–3654 (2004)Google Scholar
- 5.Kjell, B., Woods, W.A., Freider, O.: Information Retrieval Using Letter Tuples with Neural Network and Nearest Neighbour Classifiers. In: IEEE International Conference on Systems, Man and Cybernetics, Vancouver, Canada, pp. 1222–1226 (1995)Google Scholar
- 6.Li, M.X., Wu, C.D., Yue, Y.: An Automatic Inspection System Based on a Neural Network and Uniform Design. In: International Conference on Machine Learning and Cybernetics, pp. 245–248 (2005)Google Scholar