Boundary Learning by Using Weighted Propagation in Convolution Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Wei, Chen, Jiahao, Liu, Chuni, Ban, Xiaojuan, Ma, Boyuan, Wang, Hao, Xue, Weihua, Guo, Yu
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911047936376832
author Liu, Wei
Chen, Jiahao
Liu, Chuni
Ban, Xiaojuan
Ma, Boyuan
Wang, Hao
Xue, Weihua
Guo, Yu
author_facet Liu, Wei
Chen, Jiahao
Liu, Chuni
Ban, Xiaojuan
Ma, Boyuan
Wang, Hao
Xue, Weihua
Guo, Yu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_1905_09226
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Boundary Learning by Using Weighted Propagation in Convolution Network
Liu, Wei
Chen, Jiahao
Liu, Chuni
Ban, Xiaojuan
Ma, Boyuan
Wang, Hao
Xue, Weihua
Guo, Yu
Computer Vision and Pattern Recognition
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.
title Boundary Learning by Using Weighted Propagation in Convolution Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1905.09226