Pregled bibliografske jedinice broj: 211883
Surface quality control of ceramic tiles using neural networks approach
Surface quality control of ceramic tiles using neural networks approach // Proceedings of the 2002 IEEE International Symposium on Industrial Electronics, ISIE 2002 / Carlo Cecati (ur.).
L'Aquila: University of L Aquila, 2002. str. 1731-1734 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 211883 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Surface quality control of ceramic tiles using neural networks approach
Autori
Hocenski, Željko ; Nyarko, Emmanuel Karlo
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 2002 IEEE International Symposium on Industrial Electronics, ISIE 2002
/ Carlo Cecati - L'Aquila : University of L Aquila, 2002, 1731-1734
Skup
IEEE International Symposium on Industrial Electronics, ISIE 2002
Mjesto i datum
L'Aquila, Italija, 08.07.2002. - 11.07.2002
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
ceramic tiles; quality control; neural networks; image processing; algorithm
Sažetak
The image processing described in this paper is used for visual quality control in ceramic tile production. The tiles surface quality depends on the surface defects. The described image processing is based on the neural network approach. The described diagnostic algorithm is presented to detect surface failures on white ceramic tiles. The tiles are scanned and the digital images are pre-processed and classified using neural networks. Pre-processing of the image data is used to keep the number of inputs of the neural networks performing the classification relatively small. It is important to reduce the amount of input data with problem specific pre- processing. The auto-associative neural network is used for feature generation and selection while the probabilistic neural network is used for classification. Simulation was performed in Matlab using the Neural Network Toolbox. The algorithm is evaluated experimentally using the real tile images. The analysis of the detection capabilities and sensitivity expressed in non-detected failures and false proclaimed defect is done also. The results obtained were satisfactory considering the fact that the images were scanned under the normal conditions. The developing and testing of this method is used for early design of the computer aided visual control.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
