Abstract
Deep learning has driven great progress in natural and biological image processing. However, in materials science and engineering, there are often some flaws and indistinctions in material microscopic images induced from complex sample preparation, even due to the material itself, hindering the detection of target objects. In this work, we propose WPU-net that redesign the architecture and weighted loss of U-Net to force the network to integrate information from adjacent slices and pay more attention to the topology in this boundary detection task. Then, the WPU-net was applied into a typical material example, i.e., the grain boundary detection of polycrystalline material. Experiments demonstrate that the proposed method achieves promising performance compared to state-of-the-art methods. Besides, we propose a new method for object tracking between adjacent slices, which can effectively reconstruct the 3D structure of the whole material while maintaining relative accuracy.
Abstract (translated)
深入学习推动了自然和生物图像处理的巨大进步。然而，在材料科学和工程中，由于样品制备的复杂性，材料显微图像往往存在一些缺陷和模糊，甚至由于材料本身的原因，阻碍了对目标物的检测。在这项工作中，我们提出了重新设计U-NET结构和加权损失的WPU网络，以迫使网络整合来自相邻切片的信息，并在边界检测任务中更加注意拓扑结构。然后，将WPU网络应用于典型的材料实例，即多晶材料的晶界检测。实验表明，该方法与现有方法相比，具有良好的性能。此外，我们还提出了一种新的目标跟踪方法，可以在保持相对精度的同时，有效地重建整个材料的三维结构。
URL
https://arxiv.org/abs/1905.09226
