Illumination Consistency Processing Based on Illumination Domain Signal-Guided Unsupervised Generative Adversarial Network for Flotation Froth Images

In the machine vision-based online monitoring of the flotation process, froth images acquired in real-time are subject to color distortion and excessive bright spots caused by inconsistent illumination, which hinders the effectiveness of image analysis and further online measurement for operating performance indicators. Current image processing methods struggle to correct color distortion and remove excess bright spots in froth images simultaneously. Therefore, in this article, an illumination domain signal-guided unsupervised generative adversarial network (IDS-GUGAN) is proposed for illumination consistency processing of flotation froth images. First, considering the varying effects of inconsistent illumination on froth images, the illumination domain signal-guided image generation (IDS-GIG) mechanism based on the theory of unsupervised disentangled representation learning is designed to achieve adaptive correction of froth images with varying degrees of distortion. Moreover, a novel lightweight double-closed-loop network architecture is introduced to support unsupervised learning utilizing unpaired froth images and improve computational efficiency, which makes the proposed approach highly suitable for industrial applications. Comprehensive experiments on a real tungsten cleaner flotation process dataset and two public benchmark datasets related to image illumination processing tasks consistently endorse the superiority of IDS-GUGAN.