In the manufacturing process of LCD/OLED, defects on display panels need to be localized and classified according to certain criterion. Recent triumph of deep learning model in defects detection on LCD/OLED panels greatly reduce the miss and mistake rate of defects while depends tightly on the industrial training data. These image data, acquired from the industrial display pipelines, show great imbalance with the positive sample way surpassing negative defective ones. Despite data imbalance, the diversity in the negative samples make the data preparation trick and certainly impossible to exhaust all kinds of negative samples for training. Based on the above observation, it would be enormously beneficial if the anomaly detection on display panels can be purely based on the overwhelming positive samples with enough variations. This insight serves as our motivation for GAN‐based anomaly detection on LCD/OLED display panels. In this paper, we propose the utilization of one specific anomaly GAN to the real time anomaly detection of display panels online and also automatic data labeling offline. The result shows its efficiency in detecting all kinds of prominent anomalies.

No abstract

This paper proposes a novel LSTM model for precise prediction of initial register value in OLED Gamma tuning. Usually the bottleneck of Gamma tuning speed depends on the accuracy of initial register value prediction in IC modules for each bind point. By utilizing the long short‐term memory character of LSTM, high prediction accuracy is achieved which greatly shrink the search time for register value, thus reducing the overall average tuning time for each bind point of OLED screens and enhancing the amounts of adjusted screens per unit time in autonomous pipelines.