In surface defect detection, due to the extreme imbalance in the number of positive and negative samples, positive-samples-based anomaly detection methods have received more and more attention. Specifically, reconstruction-based methods are the most popular. However, existing methods are either difficult to repair abnormal foregrounds or reconstruct clear backgrounds. Therefore, we propose a clear memory-augmented auto-encoder (CMA-AE). At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds. Secondly, a general artificial anomaly generation algorithm (GAAGA) is proposed to simulate anomalies that are as realistic and feature-rich as possible. At last, we propose a novel multi scale feature residual detection method (MSFR) for defect segmentation, which makes the defect location more accurate. Extensive comparison experiments demonstrate that CMA-AE achieves state-of-the-art detection accuracy and shows great potential in industrial applications.
翻译:在地表缺陷检测方面,由于正和负抽样数量极不平衡,正样异常检测方法越来越受到越来越多的关注。具体地说,以重建为基础的方法最为流行。然而,现有的方法要么难以修复异常的前台,要么难以重建清晰的背景。因此,我们提出一个清晰的内存强化自动编码器(CMA-AE),首先,我们提出一个新的清晰的内存强化模块(CAMM),该模块将编码和内存编码结合起来,从而可以遗忘和输入,从而修复异常的前台和保存清晰的背景。第二,建议采用一般的人工异常生成算法(GAAGAGA)来模拟尽可能现实和丰富特征的异常。最后,我们提议采用新的多尺度特征残余检测法(MSFR)进行缺陷分解,从而使缺陷位置更加准确。广泛的比较实验表明,CMA-AE达到了最先进的检测准确度,并显示出工业应用的巨大潜力。