Rock Textures Classification Based on Textural and Spectral Features
In this paper, we proposed a method to classify each
type of natural rock texture. Our goal is to classify 26 classes of rock
textures. First, we extract five features of each class by using
principle component analysis combining with the use of applied
spatial frequency measurement. Next, the effective node number of
neural network was tested. We used the most effective neural
network in classification process. The results from this system yield
quite high in recognition rate. It is shown that high recognition rate
can be achieved in separation of 26 stone classes.
[1] M. Partio, B. Cramariuc, M. Gabbouj, and A. Visa, "Rock texture
retrieval using gray level co-occurrence matrix" Norsig2002, Oct 2002.
[2] L. Lepisto, I. Kunttu, J. Autio and A. Visa, "Rock image classification
using non-homogeneous textures and spectral imaging". WSCD-2003,
Feb 2003.
[3] Haralick, R.M., Shanmugam, L., Dinstein, "Textural features for image
classification", IEEE Trans. Systems, Manufact, Cybernet., Vol. 3, Issue
6, pp. 610-621, 1973.
[4] Topi Mäenpää, Matti Pietikää, "Classification with color and texture:
jointly or separately", Pattern Recognition 37, Issue 8, pp. 1629-1640,
August 2004.
[5] L.I. Smith, A tutorial on Principle Component Analysis, Feb 2002.
[6] A.McAndrew, "Introduction to Digital Image Processing with Matlab",
Thomson, 2004.
[7] S. Grgic, M.Grgic, and M. Mrak, "Reliability of Objective Picture
Quality Measures Measurement", Journal of Electrical Engineering,
Vol. 55, No. 1-2, pp.3-10, 2004.
[8] S. Walczak, N. Cerpa, "Heuristic principles for the design of artificial
neural networks", Information and Software Technology 41, pp. 107-
117, 1999.
[9] S. B. Park, J. W. Lee, S. K. Kim, "Content-based image classification
using neural network", Pattern Recognition Letters 25, pp. 287-300,
2004.
[10] N. Wanas, G. Auda, M. S. Kamel, F. Karray, "On the Optimal Number
of Hidden Nodes in a Neural Network", IEEE Canadian Conference,
Volume 2, pp. 918-921, 1998.
[11] V. DeBrunner, M. Kadiyala, "Texture Classification Using Wavelet
Transform", IEEE Trans on Circuits and Systems, Volume 2, pp. 1053-
1056, Aug 1999.
[1] M. Partio, B. Cramariuc, M. Gabbouj, and A. Visa, "Rock texture
retrieval using gray level co-occurrence matrix" Norsig2002, Oct 2002.
[2] L. Lepisto, I. Kunttu, J. Autio and A. Visa, "Rock image classification
using non-homogeneous textures and spectral imaging". WSCD-2003,
Feb 2003.
[3] Haralick, R.M., Shanmugam, L., Dinstein, "Textural features for image
classification", IEEE Trans. Systems, Manufact, Cybernet., Vol. 3, Issue
6, pp. 610-621, 1973.
[4] Topi Mäenpää, Matti Pietikää, "Classification with color and texture:
jointly or separately", Pattern Recognition 37, Issue 8, pp. 1629-1640,
August 2004.
[5] L.I. Smith, A tutorial on Principle Component Analysis, Feb 2002.
[6] A.McAndrew, "Introduction to Digital Image Processing with Matlab",
Thomson, 2004.
[7] S. Grgic, M.Grgic, and M. Mrak, "Reliability of Objective Picture
Quality Measures Measurement", Journal of Electrical Engineering,
Vol. 55, No. 1-2, pp.3-10, 2004.
[8] S. Walczak, N. Cerpa, "Heuristic principles for the design of artificial
neural networks", Information and Software Technology 41, pp. 107-
117, 1999.
[9] S. B. Park, J. W. Lee, S. K. Kim, "Content-based image classification
using neural network", Pattern Recognition Letters 25, pp. 287-300,
2004.
[10] N. Wanas, G. Auda, M. S. Kamel, F. Karray, "On the Optimal Number
of Hidden Nodes in a Neural Network", IEEE Canadian Conference,
Volume 2, pp. 918-921, 1998.
[11] V. DeBrunner, M. Kadiyala, "Texture Classification Using Wavelet
Transform", IEEE Trans on Circuits and Systems, Volume 2, pp. 1053-
1056, Aug 1999.
@article{"International Journal of Information, Control and Computer Sciences:57890", author = "Tossaporn Kachanubal and Somkait Udomhunsakul", title = "Rock Textures Classification Based on Textural and Spectral Features", abstract = "In this paper, we proposed a method to classify each
type of natural rock texture. Our goal is to classify 26 classes of rock
textures. First, we extract five features of each class by using
principle component analysis combining with the use of applied
spatial frequency measurement. Next, the effective node number of
neural network was tested. We used the most effective neural
network in classification process. The results from this system yield
quite high in recognition rate. It is shown that high recognition rate
can be achieved in separation of 26 stone classes.", keywords = "Texture classification, SFM, neural network, rock
texture classification.", volume = "2", number = "3", pages = "817-7", }