Article citationsMore>>

Jang, J., Shin, M., Lim, S., Park, J., Kim, J. and Paik, J. (2019) Intelligent Image-Based Railway Inspection System Using Deep Learning-Based Object Detection and Weber Contrast-Based Image Comparison. Sensors, 19, Article 4738. https://doi.org/10.3390/s19214738

has been cited by the following article:

• TITLE: A Study of Lighting Models for Automatic Detection of Regions of Interest and Surface Defects in Cast Metal Parts

  AUTHORS: George Kyriakides, Alexandros Daskalakis

  KEYWORDS: Industrial Inspection, Surface Defect Visibility, Lighting Models, Computer Vision

  JOURNAL NAME: Open Access Library Journal, Vol.10 No.11, November 13, 2023

  ABSTRACT: This paper investigates the influence of ultraviolet (UV) lighting configurations on the automatic detection of Regions of Interest (ROIs) and the visual identification of surface defects in cast metal parts. A meticulous experimental setup was devised employing four UV light bars arranged in a rectangle, with varying combinations of active light sources. The study utilized the OpenCV library to automate the detection of mounting holes (ROIs) on the cast metal parts. Additionally, a visual inspection was carried out to ascertain the visibility of surface defects under different lighting configurations. The findings revealed a significant enhancement in both ROI detection efficiency and defect visibility as the number of active UV light sources increased. A comparative analysis illustrated the distinct impact of each lighting configuration on the visibility and detectability of critical features on the cast metal parts. This research underscores the importance of optimized lighting conditions in advancing automated inspection systems within the metal casting industry, laying a solid foundation for further exploration into advanced lighting models and sophisticated computer vision algorithms to bolster industrial inspection processes.