基于图像重构与语义差异识别的表面异常检测  

Surface Anomaly Detection Based on Image Reconstruction and Semantic Difference Discrimination

作　　者：王尚尚 金城[1] WANG Shangshang;JIN Cheng(School of Computer Science,Fudan University,Shanghai 200438,China)

机构地区：[1]复旦大学计算机科学技术学院,上海200438

出　　处：《计算机科学》2023年第11期151-159,共9页Computer Science

基　　金：国家重点研发计划(2019YFB2102800)。

摘　　要：基于图像重构的方法是表面异常检测中一类广泛使用的方法。该类方法仅期望模型较好地重构正常模式,并通过异常区域较大的重构误差来检测和定位异常。已有方法一方面易出现“泛化”过好的现象,异常区域也被高保真地重构了出来;另一方面仅在图像空间度量重构误差,并没有真正捕捉到原图和重构图之间的语义差异。为了解决上述问题,文中提出了由重构网络和识别网络组成的表面异常检测框架,其中重构网络嵌入了多尺度位置增强动态原型单元,强化了对正常模式的学习;识别网络进行了输入图和重构图的多尺度深度特征融合,从多个尺度利用了重构前后的语义差异信息,强化了对重构差异的识别。在MVTec数据集上,所提方法在异常检测任务上取得了99.5%的AUROC,在异常定位任务上取得了98.5%的AUROC,以及95.0%的RPO检测表现,与之前基于重构的表面异常检测方法相比取得了较大提升。Reconstruction-based methods are widely used for surface anomaly detection.These methods are expected to only reconstruct normal patterns well and detect and localize anomalies by the larger reconstruction error in anomalous areas.Previous methods either tend to“generalize”too well,resulting in high fidelity reconstruction of anomalies,or measure reconstruction differences in image space,which doesn’t really capture the semantic differences.To tackle these problems,this paper proposes a model consisting of a reconstruction network and a discrimination network.In the reconstruction network,we design a multiscale location-augmented dynamic prototype unit to reinforce the learning of normal patterns.In the discrimination network,we fuse the multiscale deep features of the input image and its anomaly-free reconstruction to utilize the multiscale semantic difference information before and after reconstruction,which reinforces the discrimination of semantic differences.On the MVTec dataset,our method reaches 99.5%AUROC in the detection task,and 98.5%AUROC,95.0%PRO in the location task,outperforms pre-vious reconstruction-based methods by a large margin.

关 键 词：图像重构 表面异常检测 多尺度位置增强动态原型单元 语义差异识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]