Mineral identification using color spaces and artificial neural networks

Identification of minerals and percentage of their area within a thin section of rock are important for identifying and naming rocks. Colors of minerals are the basic factors for identification. In this study, an artificial neural network is used for the classification of minerals. Optical data of thin sections is acquired from the rotating polarizing microscope stage. For the first analysis we selected a set of parameters based on red, green, blue (RGB) and the second based on hue, saturation, value (HSV) color spaces are extracted from the segmented minerals within each data set. A neural network with k-fold cross validation is trained with manually classified mineral samples based on their pixel values. The most successful artificial network to date is the three-layer feed forward network which uses minimum square error correction. The network uses 6 distinct input parameters to classify 5 different minerals, namely, quartz, muscovite, biotite, chlorite, and opaque. Testing the network with previously unseen mineral samples yielded successful results as high as 81-98%.

[1]  Lee Jiann-Der,et al.  Object recognition using a neural network with optimal feature extraction , 1997 .

[2]  Michel Verleysen,et al.  Resampling methods for parameter-free and robust feature selection with mutual information , 2007, Neurocomputing.

[3]  R. Porter,et al.  Robust rotation-invariant texture classification: wavelet, Gabor filter and GMRF based schemes , 1997 .

[4]  Paulo J. G. Lisboa,et al.  A review of evidence of health benefit from artificial neural networks in medical intervention , 2002, Neural Networks.

[5]  N. A. Diamantidis,et al.  Unsupervised stratification of cross-validation for accuracy estimation , 2000, Artif. Intell..

[6]  Elif Derya Übeyli,et al.  Detection of ophthalmic artery stenosis by least-mean squares backpropagation neural network , 2003, Comput. Biol. Medicine.

[7]  Tim W. Nattkemper,et al.  Multivariate image analysis in biomedicine , 2004, J. Biomed. Informatics.

[8]  C.-H. Yu,et al.  Universal colour quantisation for different colour spaces , 2006 .

[9]  Elif Derya Übeyli,et al.  Detection of ophthalmic arterial doppler signals with Behcet disease using multilayer perceptron neural network , 2005, Comput. Biol. Medicine.

[10]  Uçman Ergün,et al.  Classification of the Frequency of Carotid Artery Stenosis with MLP and RBF Neural Networks in Patients with Coroner Artery Disease , 2004, Journal of Medical Systems.

[11]  R. Marschallinger,et al.  Automatic mineral classification in the macroscopic scale , 1997 .

[12]  Noël Bonnet,et al.  Some trends in microscope image processing , 2004 .

[13]  Frank Fueten,et al.  An artificial neural net assisted approach to editing edges in petrographic images collected with the rotating polarizer stage , 2007, Comput. Geosci..

[14]  F. Fueten,et al.  Mineral identification using artificial neural networks and the rotating polarizer stage , 2001 .

[15]  F. Fueten.  A computer-controlled rotating polarizer stage for the petrographic microscope , 1997 .

[16]  James C. Hower,et al.  Studies of the relationship between petrography and grindability for Kentucky coals using artificial neural network , 2008 .

[17]  P J Sjöström,et al.  Artificial neural network-aided image analysis system for cell counting. , 1999, Cytometry.

[18]  Elif Derya Übeyli,et al.  Multilayer perceptron neural networks to compute quasistatic parameters of asymmetric coplanar waveguides , 2004, Neurocomputing.

[19]  Elif Derya Übeyli,et al.  ECG beat classifier designed by combined neural network model , 2005, Pattern Recognit..