Abstract. Solutions for the quality control of metallic surfaces are proposed. Specifically, we study a deflectometric apparatus based on coaxial structured light and the related algorithmic procedure, which is able to detect the faulty surface of a sample captured by a video sequence. First, by considering the metallic surface a dynamic scene illuminated under different light conditions, we develop the descriptor residuals of linear evolution of light (RLEL) that extracts the defectiveness information starting from the movement of the object without explicitly considering the physical characteristics of the light structure. Then, leveraging on RLEL, we present a hybrid learning (HL) technique capable of overcoming the data-driven approach used in classic deep learning (DL). By exploiting a multisteps training process, we combine the model-based descriptor RLEL and a classical data-driven convolutional neural network (CNN) to obtain an unconventional gray-box CNN, which exceeds the performance of popular DL solutions such as 3-D-inception and 3-D-residual DL networks. Remarkably, HL also shows its validity in comparing the performance of the same network structures trained not in a hybrid way, namely without the injection of the model-based information given by RLEL.

中文翻译：

---

多步混合学习：由时空特征驱动的 CNN 用于金属表面的故障检测

摘要。提出了金属表面质量控制的解决方案。具体来说，我们研究了一种基于同轴结构光和相关算法程序的偏转仪，它能够检测视频序列捕获的样本的缺陷表面。首先，通过将金属表面视为在不同光照条件下照明的动态场景，我们开发了光线性演化 (RLEL) 的描述符残差，该描述符残差从物体的运动开始提取缺陷信息，而无需明确考虑光的物理特性结构体。然后，利用 RLEL，我们提出了一种混合学习 (HL) 技术，能够克服经典深度学习 (DL) 中使用的数据驱动方法。通过利用多步骤训练过程，我们结合了基于模型的描述符 RLEL 和经典的数据驱动卷积神经网络 (CNN) 来获得非常规的灰盒 CNN，其性能超过了 3-D-inception 和 3-D-residual 等流行 DL 解决方案的性能深度学习网络。值得注意的是，HL 在比较非混合方式训练的相同网络结构的性能时也显示了其有效性，即没有注入 RLEL 给出的基于模型的信息。