Automatic Generation of Digital Filters by NN Based Learning: An Application on Paper Pulp Inspection
This paper presents an implementation of a digital filtering inspection system applied on a paper pulp sheet production process. The automation of the inspection phase is particularly critical during this process and its solution is highly complex. The system is based on neural network learning, allowing a compromise between resolution and processing speed. The experimental results demonstrating the use of this algorithm for the visual detection of defects in images obtained from a real factory environment are presented. These results show that the developed learning method generates filters that fulfil the required inspection standard.
KeywordsDigital Filter Defect Type Automatic Generation Multi Layer Perceptron Inspection System
Unable to display preview. Download preview PDF.
- 1.Campoy, P.: Nuevas Tendencias sobre Control Avanzado: Redes Neuronales, pp. 37–53, Fundacion Repsol Publicaciones, 1999.Google Scholar
- 2.Campoy, P.: Sistemas Inteligentes en la Inspeccin Visual, “Industria XXI” Revista ETSII, Número 0, Universidad Politcnica de Madrid, pp. 23–33, 2000.Google Scholar
- 3.Conners, R. Identifying and locating surface defects in wood, IEEE Transactions PAMI 5(6) (1983), pp 573–583.Google Scholar
- 4.Dewaele, P., Van Gool, L., and Oosterlinchk, A. Texture Inspection withself-adaptive convolution filters, Proceedings of the Ninth International Conference on Pattern Recognition, 1, 1988, pp 14–17.Google Scholar
- 5.Lee, C.S., Choi, C.H., Choi, J.Y., Kim, Y.K. and Choi, S.H., Feature extraction algorithm based on adaptive wavelet packet for surface detect classification, IEEE International Conference on Image Processing, 1996, pp. 673–675.Google Scholar
- 6.Normas ENCE: Technical Specification of the Product, Empresa Nacional de Celulosas, S.A., 1994.Google Scholar