Application of image processing and radial basis neural network techniques for ore sorting and ore classification

Ore sorting is a useful tool to remove gangue material from the ore of bigger size ranges. The radical development in the area of artificial intelligence allows speedy processing the full color digital images for the preferred investigations. In this paper a novel approach to classify the ores for ferromanganese metallurgical plant feed has been proposed based on the visual texture of the ore particles (Mn, Fe, and Al₂O₃ rich) and radial basis neural network. The visual texture of ore particles vary with the mineral contents. This information can be quantified by using image processing technique in RGB color space and, first and second-order statistical analysis. Commonly used Hartlic’s textural features was calculated and presented as neural network inputs along with red, green and blue color values for 5 × 5 pixel size windowpanes extracted from three separate images. Results obtained show encouraging accuracy to apply the approach to develop an expert system for on line ore quality monitoring to control the ore blending in the feed ore circuits as well as separating gangue minerals present in the feed ores. Matlab^® 7.0 was used for visual textural analysis and neural network classification.