Automated defect detection of reflective product surface is a challenging task due to the appearance of specular highlight. Although various highlight removal methods have been proposed, they fail to distinguish bright areas from highlight, and may remove bright defects as specular highlights, which can affect the accuracy of subsequent defect detection. In this paper, we propose a dual-mask guided deep learning model for detecting surface defects on highly reflective leather, which can remove surface specular highlights in industrial product images while preserving bright defects. Specifically, we propose an image transformation network for joint specular highlight detection and removal. The network is composed of multiple large window attention and MLP blocks, which can capture multi-scale features effectively. In addition, we create a dataset with 522 reflective leather images and perform pixel-level annotation of both high-light regions and defect regions. We conduct experiments on the reflective leather dataset and public dataset to evaluate the performance of our method. Compared with other approaches, the results demonstrate the superiority of our proposed method.
Hydrogen permeation techniques have been widely utilized to extract hydrogen effective diffusivity, as well as hydrogen trapping site characteristics in steels. Several methods have been proposed to examine reversible and irreversible trapping site characteristics. However, the inappropriate utilization of these simplified models, as well as incorrect value assignment to the key parameters, can result in several orders of magnitude difference in hydrogen trapping site density. Therefore, in order to evaluate these models and verify their application prerequisites, a serial of hydrogen permeation tests were numerically simulated and examined, separately considering reversible and irreversible hydrogen trapping sites. In the meantime, suggestions were given to conduct hydrogen permeation test more effectively, and evaluate hydrogen trapping site characteristics more precisely.