Title: Spatial-temporal joint zinc flotation froth image denoising based on bubble dynamic features
Authors: Wenhui Xiao; Zhaohui Tang; Jinping Liu
Addresses: School of Computer Science and Engineering, Central South University, Changsha, Hunan, China; School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China ' School of Computer Science and Engineering, Central South University, Changsha, Hunan, China ' College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China
Abstract: The environment of the flotation plant is harsh, and the noise pollution of the collected froth images is severe. It is challenging to obtain real-time and high-quality froth images by common denoising methods. A spatial-temporal joint denoising method based on bubble dynamic features is proposed. This method first analyses the dynamic features of the bubble and detects the stability of each reference image sub-blocks; then selects the corresponding filtering to denoising according to the different states of the froth sub-blocks; and finally obtains a weighted average result of temporal filtering and spatial filtering. This method uses a modified and noise-robust cross-correlation method to estimate the sub-blocks' motion, which improves the denoising performance of time-domain filtering. The experiments show that the method can obtain a high signal-to-noise ratio and strong structural similarity result for non-static background images. It has also been well verified in the application of zinc flotation froth images.
Keywords: flotation froth image; bubble dynamic features; temporal filtering; non-local mean; NLM; spatial-temporal joint denoising.
International Journal of Embedded Systems, 2022 Vol.15 No.2, pp.108 - 118
Received: 26 May 2021
Accepted: 19 Jun 2021
Published online: 08 Jun 2022 *