Although the production process of liquid crystal display model has been automated, the quality detection still depends on manual work. Mura defect is one of the common defects appearing in TFT-LCD modules. Since mura defect is not significantly different from the common background, it is difficult to detect. This paper presents a deep channel attention-based classification network (DCANet), which acts as a powerful feature extractor for object detectors, and proposes an antagonistic training algorithm based on convolution neural network. By the proposed training approach, the deep learning-based object detectors can achieve high accuracy even with a small number of training samples of mura defect. The experimental results show that compared to vanilla training method, the deep learning-based detectors trained by our proposed method could significantly improve their performance on mura defect detection with a few training samples. Even trained on only 600 samples, the mistake rate and miss rate are only 8.08% and 0.267% respectively, which can completely fulfill the enterprise’s requirements of 10% and 0.3%.

虽然液晶显示模型的生产过程已经实现了自动化，但质量检测仍然依赖于人工。Mura缺陷是TFT-LCD模块中常见的缺陷之一。由于 Mura 缺陷与常见背景没有显着差异，因此难以检测。本文提出了一种基于深度通道注意力的分类网络（DCANet），它作为目标检测器的强大特征提取器，并提出了一种基于卷积神经网络的对抗训练算法。通过所提出的训练方法，基于深度学习的目标检测器即使在少量的 mura 缺陷训练样本的情况下也能实现高精度。实验结果表明，与普通训练方法相比，通过我们提出的方法训练的基于深度学习的检测器可以通过少量训练样本显着提高其在 mura 缺陷检测方面的性能。即使只训练了 600 个样本，错误率和未命中率也分别只有 8.08% 和 0.267%，完全可以满足企业 10% 和 0.3% 的要求。