Title :
Rock recognition using feature classification
Author :
Crida, R.C. ; De Jager, G.
Author_Institution :
Fac. of Eng., Cape Town Univ., Rondebosch, South Africa
Abstract :
A knowledge based approach to finding fixed size rocks within an image is described. It is intended to be a building block within a multiresolution system. Each point is hypothesised to be a rock and a region surrounding it is labelled using knowledge of rock characteristics. Twelve features are then measured and used to test the hypothesis by means of a combination of thresholding and k-nearest-neighbour classification
Keywords :
edge detection; feature extraction; image classification; image resolution; knowledge based systems; mineral processing industry; mining; rocks; edge detection; feature classification; fixed size rock; k-nearest-neighbour classification; knowledge based approach; mining industry; multiresolution system; rock characteristics; rock recognition; thresholding; Cities and towns; Control systems; Image edge detection; Image processing; Image resolution; Monitoring; Size control; Size measurement; Testing; Time measurement;
Conference_Titel :
Communications and Signal Processing, 1994. COMSIG-94., Proceedings of the 1994 IEEE South African Symposium on
Conference_Location :
Stellenbosch
Print_ISBN :
0-7803-1998-2
DOI :
10.1109/COMSIG.1994.512454