Rock Textures Classification Based on Textural and Spectral Features

Recognition 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.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  Moncef Gabbouj,et al.  Rock Texture Retrieval Using Gray Level Co-occurrence Matrix , 2002 .

[3]  Mohamed S. Kamel,et al.  On the optimal number of hidden nodes in a neural network , 1998, Conference Proceedings. IEEE Canadian Conference on Electrical and Computer Engineering (Cat. No.98TH8341).

[4]  Steven Walczak,et al.  Heuristic principles for the design of artificial neural networks , 1999, Inf. Softw. Technol..

[5]  Jae Won Lee,et al.  Content-based image classification using a neural network , 2004, Pattern Recognit. Lett..

[6]  Marta Mrak,et al.  Reliability of Objective Picture Quality Measures , 2004 .

[7]  Matti Pietikäinen,et al.  Classification with color and texture: jointly or separately? , 2004, Pattern Recognit..

[8]  Victor DeBrunner,et al.  Texture classification using wavelet transform , 1999, 42nd Midwest Symposium on Circuits and Systems (Cat. No.99CH36356).

[9]  Alasdair McAndrew,et al.  Introduction to digital image processing with Matlab , 2004 .