Automatic Generation and Detection Method of LCD Samples Based on Deep Learning

When the deep learning method is applied to the detection of microscopic defects with uneven brightness on the low-contrast LCD surface, due to the imbalance between the positive samples and negative samples when training the deep learning method, we propose a method to automatically generate samples based on a deep generative network model. First, a small number of defect samples are generated through a generative adversarial network to generate an expanded sample data set, and then the samples in these data sets are manually marked to highlight the defect parts, and the mask of the defect image is obtained for Mask R-CNN detection. The experimental results confirm that LCD image samples can be automatically generated by the proposed method, and the experiments on Mask R-CNN also confirm the effectiveness of our proposed method.