Recently, the development of computer vision with deep learning has made object detection using images applicable to diverse fields, such as medical care, manufacturing, and transportation. The manufacturing industry is saving time and money by applying computer vision technology to detect defects or issues that may occur during the manufacturing and inspection process. Annotations of collected images and their location information are required for computer vision technology. However, manually labeling large amounts of images is time-consuming, expensive, and can vary among workers, which may affect annotation quality and cause inaccurate performance. This paper proposes a process that can automatically collect annotations and location information for images using eXplainable AI, without manual annotation. If applied to the manufacturing industry, this process is thought to save the time and cost required for image annotation collection and collect relatively high-quality annotation information.

I propose an algorithm to detect defects in the production of wire mesh using computer image processing. The process is explained as follows, First reading consecutive frames coming through the camera, then the preprocessing process is performed. Second calculate the absolute difference between the two images to distinguish the moving wire mesh from the unnecessary background image. Third based on the past moving data of the welded wire mesh, predict and track future movement. As a result of observing the samples of some defective welded wire mesh products, it was confirmed that the horizontal line of the defective wire mesh had a higher height value of the tracked wire netting. Therefore it is possible to judge whether there is a defect or not at the same time without any additional process to judge. Finally, shear strength test were performed on the welds determined to be normal products by the algorithm proposed in this paper, so that I could verify the reliability and validity of the proposed algorithm.

This study is a duralumin and applying heat to the STS-wide measurement range is used, the surface temperature by using the temperature of studying the non-destructive testing of a new paradigm to estimate the position and size of a structure defect purpose. STS and duralumin which has a structure defect is applied a heat by a heater. Its difference of STS and duralumin surface temperature is measured using IR thermography. The estimated result of the STS and duralumin experiment and that of theoretical analysis of PDE are compared and analyzed to diagnose the STS and duralumin defect. Moreover, this study can save time and money and improve accuracy contrast to the existing ultrasonic NDE experiment. In addition, the new paradigm of NDT/NDE by reverse-engineering is going to be valid if the data of thermal analysis and temperature distribution from the specifications of many materials is accumulated and verified. In this study, the average surface temperature of the STS in the same heating condition was 4.53 ° K higher than that of duralumin and both of the surface temperature showed an inflection point in the defect 2.5mm.The maximum surface temperature difference was formed on the 2.5mm, and the study proves its reliability because the average surface temperature of the STS and duralumin was 0.74°K, 0.45°K higher than the theoretical surface temperature.

A image defect detecting vision system for the automatic optical inspection of wafer has been developed. For the successful detection of various kinds of defects, the performance of two threshold selection methods are compared and the improved Otsu method is adopted so that it can handle both unimodal and bimodal distributions of the histogram equally well. An automatic defect detection software for practical use was developed with the function of detection of ROI, fast thresholding and area segmentation. Finally each defect pattern in the wafer is classified and grouped into one of user-defined defect categories and more than 14 test wafer samples are tested for the evaluation of detection and classification accuracy in the inspection system.