Nowadays, there is a trend towards higher physical size and resolution in LCD TV production. However, there are still undesired situations such as pixel defects in spite of developing manufacturing technologies. In this study, an adaptive thresholding based pixel defect detection method is proposed. The system, which is evaluated by the F1-score criterion, shows that it can be an alternative to human controlled approaches with its high detection performance. When compared with a machine learning based method in the literature, the proposed method stands out with its working time and detection performance.