村上
计算机科学
人工智能
算法
分水岭
计算机视觉
模式识别(心理学)
作者
Ye Jian Zhang,Hyonam Joo,Joon Seek Kim
出处
期刊:Journal of Institute of Control Robotics and Systems
[Institute of Control, Robotics and Systems]
日期:2017-06-30
卷期号:23 (6): 446-454
标识
DOI:10.5302/j.icros.2017.17.0020
摘要
Many kinds of defects show up during the process of manufacturing display panels. However, mura defects are the most difficult to detect using the conventional image processing algorithms. Many factors cause mura defects to appear in display panels. When images are taken using cameras, mura defects normally show up as relatively dark or bright regions with no definite shape, no clear contours, and very low contrast against their surrounding background. When an imaged mura defect is relatively dark compared to its background, it can be considered a water catchment basin when the whole image is visualized in three dimensions (i.e., is topographically interpreted), and such catchment basins can be detected by watershed algorithms. In this paper, for the accurate segmentation of the mura region, the flooding step of the original watershed algorithm is carefully redesigned to detect the mura defect that exists both inside and at the boundary of an image. The depth of the catchment basins is recorded iteratively and then is used to segment the mura defects. The just noticeable difference (JND) technique is used to quantify the level of the mura defects. It is shown, by extensive experiments, that the proposed algorithm performs well, detecting very low-contrast mura defects, and quickly detects defects located anywhere in the image.
科研通智能强力驱动
Strongly Powered by AbleSci AI