Neural network based detection of defects in texture surfaces (CROSBI ID 509460)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Rimac-Drlje, Snježana ; Keller, Alen ; Hocenski, Željko
engleski
Neural network based detection of defects in texture surfaces
In this article we present an algorithm for automatic detection of surface defects on ceramic tiles. This algorithm is based on the probabilistic neural network with radial basis. To improve sensitivity of the detection procedure an image of the tile is divided into segments and one neural network is made for each segment. The discrete wavelet transform (DWT) is used for the feature extraction in every segment. Maximums of the wavelet coefficients as well as the mean value of the approximation coefficients form an input vector for the neural network. Experimental results of the defect detection for different types of tiles and with different parameters of the algorithm show a high sensitivity and applicability of the proposed procedure.
defect detection; wavelets; neural network; radial basis
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1255-1261-x.
2005.
objavljeno
Podaci o matičnoj publikaciji
Preceedings of IEEE International Symposium on Industrial Electronics ISIE 2005
Perić, Nedjeljko, Petrović, Ivan, Butković, Željko
Zagreb: Institute of Electrical and Electronics Engineers (IEEE)
Podaci o skupu
IEEE International Symposium on Industrial Electronics (ISIE) 2005
predavanje
20.06.2005-23.06.2005
Dubrovnik, Hrvatska