橦言无忌

一个不想改变世界的程序媛

边缘提取方法

前言

Chen Mingming老师组的三个边缘提取的模型,还有部分数据集,效果不错~

用边缘特征做过一些图像应用哦

1,边缘提取hed

github link

  • 作者
    南开大学程明明
  • 对应文章
    • author = {“Xie, Saining and Tu, Zhuowen”},
    • Title = {Holistically-Nested Edge Detection},
    • Booktitle = “Proceedings of IEEE International Conference on Computer Vision”,
    • Year = {2015},
  • 结果
    BSDS benchmark数据集:
    ODS=.790 and OIS=.808
    BSD500 数据集:
    ODS F-score of .790
    NYU Depth 数据集:
    ODS F-score of .746
    速度: (0.4s per image)

2,边缘提取rcf

pytorch版本:github
caffe版本:github

  • 作者
    南开大学程明明
  • 文章
    title={Richer Convolutional Features for Edge Detection},
    author={Liu, Yun and Cheng, Ming-Ming and Hu, Xiaowei and Bian, Jia-Wang and Zhang, Le and Bai, Xiang and Tang, Jinhui},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year={2019}
  • 特性
    Using VGG16 network;
    BSDS500 benchmark 数据集:
    ODS F-measure of 0.811, speed (8 FPS)
    fast version of RCF 快速版本:
    ODS F-measure of 0.806 with 30 FPS

3,边缘提取dfi

github link

  • 作者
    南开大学程明明
  • 文章
    title={Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton},
    author={Jiang-Jiang Liu and Qibin Hou and Ming-Ming Cheng},
    journal={IEEE Transactions on Image Processing},
    year={2020}
// 代码折叠