While visual inspection systems have been widely used in many industries, their use in the food and optical equipment industries has been limited. Transparent and reflective materials are often used in these applications, but existing anomaly detection (AD) systems have low accuracy in their detection due to low visibility. Here, we developed an AD system using a polarization camera for reflective and transparent target objects. Two new techniques are developed. First is the polarized image fusion (PIF) technique which suppresses glare from reflective surfaces while highlighting transparent foreign objects. In PIF, four captured polarized images are fused to synthesize a high-quality image according to calculated weight coefficients. The second new technique is an ArcObj-based deep metric learning technique to improve AD accuracy. The proposed system was evaluated in experiments on three datasets: cookie samples wrapped in transparent plastic bags; transparent plastic bottles; and transparent lenses. High AD accuracies in terms of the area under the receiver operating characteristic curve (AUC) were achieved: 0.88 AUC for the cookie dataset; 0.87 AUC for the bottle dataset; and 0.98 AUC for the lens dataset. Compared to the state-of-the-art AD algorithm (Patchcore), the proposed method improved AD accuracy by 0.09 AUC.

中文翻译：

---

使用偏振图像融合的基于深度度量学习的透明物体异常检测系统

虽然视觉检测系统已广泛应用于许多行业，但其在食品和光学设备行业的使用受到限制。这些应用中经常使用透明和反光材料，但现有的异常检测 (AD) 系统由于能见度低，检测精度较低。在这里，我们开发了一种使用偏振相机的 AD 系统，用于反射和透明目标物体。开发了两项新技术。首先是偏振图像融合（PIF）技术，可抑制反射表面的眩光，同时突出显示透明异物。在PIF中，根据计算的权重系数融合四张捕获的偏振图像以合成高质量图像。第二项新技术是基于 ArcObj 的深度度量学习技术，用于提高 AD 准确性。该系统在三个数据集的实验中进行了评估：透明塑料袋包裹的饼干样本；透明塑料瓶；和透明镜片。就受试者工作特征曲线下面积 (AUC) 而言，AD 精度很高：cookie 数据集为 0.88 AUC；瓶子数据集的 AUC 为 0.87；镜头数据集的 AUC 为 0.98。与最先进的 AD 算法（Patchcore）相比，该方法将 AD 精度提高了 0.09 AUC。镜头数据集的 AUC 为 98。与最先进的 AD 算法（Patchcore）相比，该方法将 AD 精度提高了 0.09 AUC。镜头数据集的 AUC 为 98。与最先进的 AD 算法（Patchcore）相比，该方法将 AD 精度提高了 0.09 AUC。