期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2021
卷号：48
期号：2
语种：English
出版社：IAENG - International Association of Engineers
摘要：The dust removal technology of welding seam image has important practical significance for promoting the development of weld instance segmentation and target tracking. In this paper, we propose a welding seam image dust removal algorithm based on fusion of dual-scale dark channel and bright channel, which is to solve the problem that the color distortion and halo effect of dark channel prior image restoration algorithm in weld depth of field sudden change area and bright region. Firstly, the results of the minimum filtering of two scale windows are adaptively weighted and fused to obtain the fused dark channel. Secondly, the dark channel prior and the bright channel prior fusion strategy is adopted to obtain the fused atmospheric light to make the rough transmittance estimation more accurate. Finally, the weighted guided filtering is combined with up-sampling and down-sampling to optimize the rough transmittance, and the weld image is restored by combining the atmospheric scattering model. The experimental results indicate that our algorithm can restore the color and edge details of welding seam images and effectively suppress the halo effect. The objective comparison with several typical algorithms proves the feasibility and superiority of the proposed algorithm.
