Multiscale Convolutional Network for Repairing Coal Slime Foam Images.

Abstract

Visual feature information regarding flotation foam is crucial for the flotation process. Owing to a large amount of noise and blur in the foam images collected in the floatation field, feature extraction and segmentation of foam images pose considerable challenges. Furthermore, the visual properties of foam are strongly correlated with current flotation conditions. Therefore, this study presents a method to repair blurred pixels in foam images. In addition to enhancing the image dataset necessary for network model training, the restored images can provide high-quality images extracting foam-feature information. In addition, this research presents a novel fifth-order residual structure that enlarges the network structure by stacking, enhancing the learning ability of complex networks. Experimental results demonstrate that the suggested method can achieve a satisfactory repair effect for foam images under various blurring conditions, laying a foundation for guiding the intelligent adjustment of flotation field parameters.