Multi-Scale Bidirectional FCN for Object Skeleton Extraction

by Fan Yang, Xin Li, Hong Cheng, Yuxiao Guo, Leiting Chen and Jianping Li

Introduction

This repository is for 'Multi-Scale Bidirectional FCN for Object Skeleton Extraction'.

Installation

For installation, please follow the instructions of Caffe.

The code has been tested successfully on Ubuntu 14.04 with CUDA 8.0.

Usage

1. Clone the repository:

   git clone https://github.com/fanyang587/MSB-FCN.git

2. Build Caffe and pycaffe:

   cd caffe-master
   cp Makefile.config.example Makefile.config
   vim Makefile.config
   make -j8 && make pycaffe

ps: You should uncomment 'WITH_PYTHON_LAYER := 1' in Makefile.config before compiling.

3. Test:

   • Test code is in folder 'test'.
   • Download the following pre-trained models and put them in folder 'test/models':
   • Sym-PASCAL dataset: BaiduYun or GoogleDrive
   • SK506 dataset: BaiduYun or GoogleDrive
   • SK1491 dataset: BaiduYun or GoogleDrive
   • WH-SYMMAX dataset: BaiduYun or GoogleDrive
   • Put the test images in folder 'images', and run

   python test.py

   -After that, the results will be genrated in folder 'result'.

Citation

If MSB-FCN is useful for your research, please consider citing:

 @inproceedings{Yang_2018_AAAI,
    author = {Yang, Fan and Li, Xin and Cheng, Hong and Guo, Yuxiao and Chen, Leiting and Li, Jianping},
    title = {Multi-Scale Bidirectional FCN for Object Skeleton Extraction},
    booktitle = {AAAI},
    month = {February}
    year = {2018}
  }

Question

Please contact 'fanyang_uestc@hotmail.com'