论文标题
一种用于工业质量检查的多尺度异常检测方法
A Contrario multi-scale anomaly detection method for industrial quality inspection
论文作者
论文摘要
异常可以定义为偏离正态性的任何非随机结构。文献中报道的异常检测方法众多且多种多样，因为被认为异常的情况通常取决于特定的情况和应用。在这项工作中，我们提出了一个逆势框架，以检测图像中使用统计分析以通过卷积获得的图形图的异常。我们通过贴片PCA，GABOR过滤器和从预先训练的深神经网络（RESNET）获得的特征图从分析的图像中学到的过滤器。所提出的方法是多尺度和完全无监督的，能够在各种情况下检测异常。尽管这项工作的最终目标是对汽车行业皮革样本中细微的缺陷的检测，但我们表明，同一算法可以实现最先进的算法，从而导致公共异常数据集。
Anomalies can be defined as any non-random structure which deviates from normality. Anomaly detection methods reported in the literature are numerous and diverse, as what is considered anomalous usually varies depending on particular scenarios and applications. In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions. We evaluate filters learned from the image under analysis via patch PCA, Gabor filters and the feature maps obtained from a pre-trained deep neural network (Resnet). The proposed method is multi-scale and fully unsupervised and is able to detect anomalies in a wide variety of scenarios. While the end goal of this work is the detection of subtle defects in leather samples for the automotive industry, we show that the same algorithm achieves state-of-the-art results in public anomalies datasets.
