Cluster analysis methods for recognition of mineral rocks in the mining industry

This paper contains short description of cluster analysis algorithm for the mineral rock recognition in the mining industry. In this paper it describes the algorithm for automatic segmentation of color images of rocks, using the methods of cluster analysis. There are results of studies different color spaces for clustering k-means. Some realizations of this algorithm for computing the grading of mineral rocks are presented here. As a result it was determined color space provided sufficient quality rocks segmentation by the method of cluster analysis. It was supposed the technique of pre-computing the values of the centroids. There is formulas translation metrics color space HSV. The effectiveness of the proposed method lies in the automatic identification of objects of interest on the total image, tuning parameters of the algorithm is a number that indicates the amount allocated to the segments. Few examples concerning with cluster analysis algorithm in the solving of mineral rock recognition problems are described and discussed.

I. Introduction

Petrography is the science studies the material composition of the rocks. Unlike minerals, rocks are aggregates composed of different minerals [1]. Minerals called homogeneous in composition and structure of the rocks and ores. They are natural chemical compounds resulting from various geological processes. Historically, the minerals initially determined by color and shape.