基于合成缺陷的偏光片外观对抗异常检测方法  

Anomaly Detection Method of Polarizer Appearance Based on Synthetic Defects

作　　者：钟小品[1] 朱俊玮 列智豪 邓元龙 Zhong Xiaopin;Zhu Junwei;Lie Zhihao;Deng Yuanlong(College of Mechatronics and Control Engineering,Shenzhen University,Shenzhen 510086,Guangdong,China;Shenzhen Institute of Technology,Shenzhen 518116,Guangdong,China)

机构地区：[1]深圳大学机电与控制工程学院,广东深圳510086 [2]深圳技师学院,广东深圳518116

出　　处：《激光与光电子学进展》2023年第14期290-299,共10页Laser & Optoelectronics Progress

基　　金：国家自然科学基金面上项目(62171288);深圳市科技创新计划(JCYJ20190808143415801)。

摘　　要：目前的自动光学检测技术受到以下两方面的挑战:难以获取足够数量的缺陷样本,且种类极不平衡;外观缺陷形态多样,种类复杂。上述问题严重影响偏光片外观缺陷的检测精度和效率。基于此,提出一种无需真实缺陷样本的深度对抗异常检测方法。采用编码器捕获条纹结构光缺陷图像的规律性特征,并通过解码器重建出无缺陷图像,再通过一个编码器模块构成无监督对抗网络,最后根据重建图像与样本图像的差异计算异常得分。在训练阶段加入合成缺陷,同时改进目标潜在损失函数,进一步提高检测精度。在一个考虑光照不均衡、噪声、相机畸变等因素的偏光片外观缺陷数据集上的实验结果表明,所提方法测试结果的area under curve达到97.9%,单张图像平均检测时间为19.2 ms,检测准确率为94.6%,均优于GANomaly等方法,验证了其有效性与鲁棒性。The current automatic optical detection technology is challenged by the following two aspects:it is difficult to obtain enough defect samples,and the types are extremely unbalanced;the appearance defects are diverse and complex.The above problems seriously affect the detection accuracy and efficiency of the appearance defects of polarizers.Considering these issues,a new depth antagonism method of anomaly detection without real defect samples is proposed.An encoder is used to capture the regular characteristics of the stripe-structured light defect image and a decoder is used to reconstruct the defect-free image.An encoder module is then used to form an unsupervised countermeasure network.Finally,the abnormal score is calculated according to the difference between the reconstructed image and the sample image.In the training phase,synthetic defects are added,and the target potential loss function is improved to further increase the detection accuracy.The experimental results for a polarizer appearance defect data set-considering factors such as light imbalance,noise,and camera distortion-show that the area under curve of the test results of the proposed method reaches 97.9%,the average detection time of a single image is 19.2 ms,and the detection accuracy is 94.6%,which is superior to other methods such as GANomaly.The effectiveness and robustness of the proposed method are verified.

关 键 词：机器视觉 偏光片 结构光成像 生成对抗网络 异常检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]