摘要: This paper describes an active vision approach to rock recognition for the purpose of measuring size distributions or fragmentation. Such a measure is useful in mining industry facilitate control and monitoring autogenous mills. A new recognising segmenting images described. It based on rapid identification targets at which attention focused analysis. In addition, multiscalar image pyramid used novel way allow target detection analysis be optimised particular size, thereby improving their performances. The results that have been obtained with this are both robust accurate.
sci-hub.se 参考文章(6)
G.C. Hunter, C. McDermott, N.J. Miles, A. Singh, M.J. Scoble, A review of image analysis techniques for measuring blast fragmentation Mining Science and Technology. ,vol. 11, pp. 19- 36 ,(1990) , 10.1016/0167-9031(90)80003-Y
S.J. Raudys, A.K. Jain, Small sample size effects in statistical pattern recognition: recommendations for practitioners IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 13, pp. 252- 264 ,(1991) , 10.1109/34.75512
Theory of Edge Detection Proceedings of The Royal Society B: Biological Sciences. ,vol. 207, pp. 187- 217 ,(1980) , 10.1098/RSPB.1980.0020
R.C. Crida, G. de Jager, Rock recognition using feature classification Proceedings of COMSIG '94 - 1994 South African Symposium on Communications and Signal Processing. pp. 152- 157 ,(1994) , 10.1109/COMSIG.1994.512454
X. Wu, J.M. Kemeny, A segmentation method for multi-connected particle delineation workshop on applications of computer vision. pp. 240- 247 ,(1992) , 10.1109/ACV.1992.240305