Computer Vision for Estimating Cooper Density by Optical Microscope Images

Computer vision is one of the innovative methods in structure analyzing. In this paper computer vision and digital image processing were used for predict area of copper particle in the mineral soil. Iran is one of the most important mineral producers in the word and ranked among 15 major mineral-rich countries. The overall purpose has been to develop skills and techniques on detection and quantification of mineralogy and microstructures by means of various optical microscopy techniques and to study important microstructure parameters. In this research three new techniques are introduced: in first technique: images were decomposed to red, green and blue images. Secondly continuous and discrete wavelet transform of soil images were calculated. Finally percentage of energy for each wavelet coefficient was calculated. Accuracy of this analyze is under ±7.60% error in copper area estimation. symlets is selected the best wavelet for mineral analyzing. The threshold of copper energy coefficient is calculated equal to 3.23x10 in optical microscope images.