A mineral flotation foam image color correction method and a foam color detection system

Abstract

The invention discloses a mineral flotation froth image color correction method and a froth color detection system. The mineral flotation froth image color correction method comprises the following steps of collecting the froth images under specific illumination to form a reference color gamut sample set of a froth image; training two generative adversarial networks A and B for foam image color correction under unknown illumination; and finally, calculating statistics such as the mean value, the skewness and the kurtosis of the corrected foam image in an HSV space and a CIELab space to form afoam color feature vector which can be used for concentrate grade estimation and working condition evaluation in the flotation process, wherein A and B share two same generators G1 and G2, but have respective independent discriminators; and through confrontation training, the color cast foam image under any illumination can be converted into color representation under a reference color gamut by the generator G1, and the structural details of the original image are kept unchanged. The color detection system has an online model correction function, and can effectively detect the color characteristics of the floating foam under various unknown illumination conditions under reference illumination.

Description

technical field [0001] The invention relates to the field of on-line monitoring of industrial processes, in particular to color correction of foam images and detection of foam colors in automatic monitoring of mineral flotation processes based on machine vision. Background technique [0002] Mineral resources are indispensable and important materials for the development of economy, people's livelihood, national defense industry, and high-tech science and technology. Although the total amount of mineral resources in my country is large, they are dominated by associated ores with many lean ores and few rich ores. Therefore, it is necessary to improve the beneficiation technology to increase the utilization rate of mineral resources. Mineral flotation technology, which uses the difference in surface wettability between minerals to separate different mineral particles by floating, is the most widely used mineral processing method in the field of mineral processing engineering t...

AI Technical Summary

Problems solved by technology

[0005] Traditional color constancy algorithms are usually based on statistical methods, such as single-illumination color constancy, image enhancement algorithms, and linear transformation of the color values ​​of each pixel of the image etc., but they are all based on the assumption of the external environment, the scope is limited, and they cannot solve the problem perfectly

Images