Abstract

Rain-like layer removal from hot-rolled steel strip surface has been proven to be a workable measure for suppressing the false alarms frequently triggered in automated visual inspection (AVI) instruments. This article extends the scope of the “rain-like layer” from dispersed waterdrops to splashing water streaks and tiny white droplets. And a targeted method with both channel-wise and spatial-wise attention, namely attentive dual residual generative adversarial network (ADRGAN), is proposed. Meanwhile, a newly updated steel surface image dataset with typical natures of a “rain-like layer” gathered from an actual hot-rolling line, Steel_Rain, is opened for the first time. The comparison of experimental results between our proposed network and 11 prestigious networks shows that our ADRGAN-restored images are the closest to the ground-truth images on six public datasets, especially on the newly opened industrial dataset Steel_Rain; it yields the best scores of 56.8627 peak signal to noise ratio (PSNR), 0.9980 structural similarity index (SSIM), 0.134 mean-square error (MSE) and 0.006 learned perceptual image patch similarity (LPIPS). In the final verification test, the concept of rain-like layer removal has been proved to perform best in defect inspection, where four traditional defect detection algorithms are involved. And as expected, defect detection methods assisted by ADRGAN yield the minimum false alarms.