The aesthetic defects of polymeric polarizers have a serious impact on the quality of thin film transistor liquid crystal display (TFT-LCD) panels. However, some of these slight and transparent defects can barely be imaged and characterized using conventional illumination. To inspect these special defects, a new and automated inspection method is proposed that employs structured-light illumination. A machine vision system that uses a LCD monitor to produce a binary stripe pattern was designed to enhance the imaging defects. Thus, subsequent image processing is straightforward and simple because of this enhancement. One hundred and fifty defect samples were successfully imaged and then processed and characterized by the Robust Principal Component Analysis (RPCA) algorithm. The total inspection accuracy was up to 99%. The experiments demonstrate that the width of the luminous stripe should be optimized at 2 to 3 times the size of the defect. The mechanism of the imaging enhancement is preliminarily discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.