Abstract:
Automatic mineral identification using evolutionary computation technology is discussed. Thin sections of mineral samples are digitally photographed using a computercontrolled rotating polarizer stage on a petrographic microscope. A suite of image processing functions is applied to the images. Filtered image data for identified mineral grains is then selected for use as training data for a genetic programming system, which automatically synthesizes computer programs that identify these grains. The evolved programs use a decision tree structure that compares the mineral image values with one other, resulting in a thresholding analysis of the multi-dimensional colour and textural space of the mineral images. Index terms - mineral classification, genetic programming, feature space thresholding. 1 Introduction Most rocks are composed of microscopic-sized minerals that can be identified by a variety of methods. The most common method of manual mineral identification involves placing a thi...
Citations
|
2526
|
Induction of decision trees
– Quinlan
- 1986
|
|
149
|
Data Mining Techniques
– Berry, Linoff
- 1997
|
|
25
|
Adaptation in natural and artificial systems
– JH
- 1975
|
|
25
|
Genetic Programming: On the Programming of Computers by Means of Natural Selection
– JR
- 1992
|
|
5
|
Classification using cultural co-evolution and genetic programming
– Abramson, Hunter
- 1996
|
|
5
|
Francone FD
– Banzhaf, Nordin, et al.
- 1998
|
|
5
|
Artificial intelligence structures and strategies for complex problem solving
– GF, WA
- 1998
|
|
3
|
Strongly typed genetic programming. Evolutionary Computation
– DJ
- 1995
|
|
2
|
The classification and characterisation of rock using texture analysis by co-occurrence matrices and the Hough transform
– Autio, Rantanen, et al.
- 1999
|
|
2
|
A computer controlled rotating polarizer stage for the petrographic microscope. Computers and Geoscience
– Fueten
- 1997
|
|
2
|
Edge detection in petrographic images using the rotating polarizer stage. Computers and Geosciences
– JS, Fueten
- 1998
|
|
1
|
Image processing of geological data
– AG
- 1984
|
|
1
|
A genetic programming framework for two data mining tasks: classification and generalized rule induction
– AA
- 1997
|
|
1
|
Martinez-Perez I, Arus C, Cerdan S
– HF, RJ
- 1996
|
|
1
|
Shape preferred orientation of object populations: automatic analysis of digitized images. Tectonophysics 180:201–211 Launeau P, Cruden CA, Bouchez J-L
– Launeau, Bouchez, et al.
- 1990
|
|
1
|
CA, Bouchez J-L
– Launeau, Cruden
- 1994
|
|
1
|
Automatic mineral classification in the macroscopic scale. Comput Geosci 23:119–126 Michalewicz Z
– Marschallinger
- 1997
|
|
1
|
Shortcourse on image analysis applied to mineral and earth sciences. Mineralogical Association of Canada Shortcourse Handbook. no 16
– Petruk
- 1989
|
|
1
|
AUTO: A computer program for the determination of the two-dimensional auto-correlation function of digital images. Computers and Geosciences
– Pfleiderer, DGA, et al.
- 1992
|
|
1
|
Competitively evolving decision trees against fixed training cases for natural language processing
– EV
- 1994
|
|
1
|
Samantary AK
– Starkey
- 1993
|
|
1
|
Fueten F, Bockus D
– Thompson
- 1999
|
|
1
|
Breaking Papers at the Genetic Programming 1996 Conference
– Late
|
|
1
|
pp 96–101 Fueten F
– Kaufmann
- 1997
|
|
1
|
et al.: Automatic mineral identification using genetic programming 69 Jain R, Kasturi R, Schunk BG
– Ross
- 1995
|
|
1
|
Strongly typed genetic programming. Evol Comput 3:199–230 Petruk W
– DJ
- 1995
|
|
1
|
Edge detection in petrographic images. J Microsc 172:263–266 Thompson S, Fueten F, Bockus D (2001) Mineral identification using artificial neural networks and the rotating polarizer stage. Comput Geosci, Elsevier, in press Whitley D, Goldberg D, Cantú-Paz
– Starkey, AK
- 1993
|
|
