Automatic Image Analysis for Mineral Beneficiation

Ash content prediction of coarse coal by image analysis and GA-SVM

“…In rock classification, color features have been widely used [11][12][13][14]. Simple and effective color features were color moments proposed by Stricker and Orengo [19].…”

“…Petruk showed one image analysis system, MP-SEM-IPS, developed in the CANMET laboratories of the Department of Energy, Mines and Resources at Ottawa, Canada, consisted of an electron microprobe to produce an image, an energy dispersive X-ray analyzer (EDXA) to identify the minerals, and a Kontron SEM-IPS image analyzer to determine mineral characteristics [11].…”

“…Machine vision has been widely applied into mineral processing field in recent twenty years, also including ore grade estimation [1][2][3]. Concentrate grade estimation of flotation froth and metallic ore grade estimation have been researched in several reports [4][5][6][7][8][9][10][11][12][13][14][15].…”

“…Concentrate grade estimation of flotation froth and metallic ore grade estimation have been researched in several reports [4][5][6][7][8][9][10][11][12][13][14][15].…”

Particle texture analysis using polarized light imaging and grey level intercepts

“…The most efficient and productive way being probably to couple both imaging systems: BSE helps to identify domains with different average atomic numbers, whereas punctual EDX spectra help to attribute compositional data to BSE pixels (Gu, 2003). Optical microscopy has often been disregarded because of its sensitivity to specimen preparation and its poor discriminative power (Petruk, 1988). This is particularly true with poor CCD sensors but can be significantly improved when using calibration and proper color imaging principles (Berrezueta, 2004).…”