Boundary Learning by Using Weighted Propagation in Convolution Network
This addresses image segmentation for quantitative microstructure analysis in material science, representing an incremental improvement with specific gains.
The paper tackles boundary detection in poly-crystalline microscopic images for material science by proposing a Weighted Propagation Convolution Neural Network based on U-Net (WPU-Net), which reduces the error rate by 7% and outperforms state-of-the-art methods.
In material science, image segmentation is of great significance for quantitative analysis of microstructures. Here, we propose a novel Weighted Propagation Convolution Neural Network based on U-Net (WPU-Net) to detect boundary in poly-crystalline microscopic images. We introduce spatial consistency into network to eliminate the defects in raw microscopic image. And we customize adaptive boundary weight for each pixel in each grain, so that it leads the network to preserve grain's geometric and topological characteristics. Moreover, we provide our dataset with the goal of advancing the development of image processing in materials science. Experiments demonstrate that the proposed method achieves promising performance in both of objective and subjective assessment. In boundary detection task, it reduces the error rate by 7\%, which outperforms state-of-the-art methods by a large margin.