Summary: | 碩士 === 中原大學 === 機械工程研究所 === 95 === Currently, most equipments used in TFT-LCD manufacturing cannot classify defects, but detect them. However, to repair the defects and maintain the equipments, we need to know the types of the defects exactly. So if we can develop a system which can classify the defects in real time, the yield rate of panels would can be increased, but also the cost can be reduced.
Most companies set up quality control departments to increase the yield rate of their products. However, in order to reduce the influences of human factors, an automatic inspection system is needed. The purpose of this study is to develop an automatic defect recognition system. We combine theories of digital image processing techniques, statistic textured feature extraction, and neural network, and propose a “Defect Recognition System for the Lithography Process Inspection in the PE(Pixel Electrode)Mask”. This system is able to automatically classify six common defects, providing a real-time automatic defect classification.
|