Abstract
Defect detection has been considered an efficient way to increase the yield rate of panels in thin film transistor liquid crystal display (TFT-LCD) manufacturing. In this study we focus on the array process since it is the first and key process in TFT-LCD manufacturing. Various defects occur in the array process, and some of them could cause great damage to the LCD panels. Thus, how to design a method that can robustly detect defects from the images captured from the surface of LCD panels has become crucial. Previously, support vector data description (SVDD) has been successfully applied to LCD defect detection. However, its generalization performance is limited. In this paper, we propose a novel one-class machine learning method, called quasiconformal kernel SVDD (QK-SVDD) to address this issue. The QK-SVDD can significantly improve generalization performance of the traditional SVDD by introducing the quasiconformal transformation into a predefined kernel. Experimental results, carried out on real LCD images provided by an LCD manufacturer in Taiwan, indicate that the proposed QK-SVDD not only obtains a high defect detection rate of 96%, but also greatly improves generalization performance of SVDD. The improvement has shown to be over 30%. In addition, results also show that the QK-SVDD defect detector is able to accomplish the task of defect detection on an LCD image within 60 ms.
Highlights
Over the past decade, thin film transistor liquid crystal display (TFT-LCD) has become a very popular flat panel display in our daily life due to its advantages over the CRT monitor such as lower power consumption and smaller volume
The collected data set for training would be imbalanced if a two-class classification approach is adopted, the support vector machine (SVM) by Vapnik [4] for example, the class imbalance problem occurs
This paper focuses on the support vector data description (SVDD) since it has been applied to the same application in the works of [7] and [10], and has shown to be effective in detecting defective pixel regions (PRs)
Summary
TFT-LCD has become a very popular flat panel display in our daily life due to its advantages over the CRT monitor such as lower power consumption and smaller volume. Liu et al [7] have recently applied the one-class classification strategy to the defect detection in LCD array process, and achieved a high defect detection rate on the images in GE engineering. Their system is based on the locally linear embedding (LLE) [8] and the support vector data description (SVDD) [9], where LLE is used for dimensionality reduction and feature extraction, and SVDD serves as the defect detector. If a test PR pattern falls inside of the boundary, it is accepted as a normal PR; otherwise it is rejected as a defective PR While this SVDD-based decision making strategy is simple, it suffers from two critical problems related to testing time complexity and generalization performance. Remarkable improvement in generalization performance has been indicated by our experimental results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
