xushengjun
- Associate professor
- Supervisor of Master's Candidates
- Name (Pinyin):xushengjun
- School/Department:信息与控制工程学院
- Education Level:With Certificate of Graduation for Doctorate Study
- Degree:Doctoral Degree in Engineering
- Professional Title:Associate professor
- Status:Employed
- Academic Titles:硕士生导师
- Other Post:兼任陕西省自动化学会理事,陕西省仪器仪表学会理事,西安市建筑制造智动化技术重点实验室副主任,西安建筑科技大学人工智能与机器人研究所所长
- Alma Mater:西安交通大学
- Teacher College:信息与控制工程学院
- Discipline:Control Science and Engineering
Other Contact Information
- Email:
- Paper Publications
Image segmentation using adaptive loopy belief propagation
Release time:2024-08-09 Hits:
- Affiliation of Author(s):信息与控制工程学院
- Journal:International Journal for Light and Electron Optics
- Key Words:中文关键字:自适应循环置信度传播;马尔可夫随机场;局部交互区域MRF;消息自收敛;标号修剪,英文关键字:Adaptive loopy belief propagation;Markov random fi
- Abstract:Loopy belief propagation (LBP) algorithm over pairwise-connected Markov random fields (MRFs) has become widely used for low-level vision problems. However, Pairwise MRF is often insufficient to capture the statistics of natural images well, and LBP is still extremely slow for application on an MRF with large discrete label space. To solve these problems, the present study proposes a new segmentation algorithm based on adaptive LBP. The proposed algorithm utilizes local region information to construct a local region model, as well as a local interaction region MRF model for image segmentation. The adaptive LBP algorithm maximizes the global probability of the proposed MRF model, which employs two very important strategies, namely, “message self-convergence” and “adaptive label pruning”. Message selfconvergence can improve the reliability of a pixel in choosing a label in local region, and label pruning can dismiss impossible labels for every pixel. Thus, the most reliable information messages transfer through the LBP algorithm. The experimental results show that the proposed algorithm not only obtains more accurate segmentation results but also greater speed.
- Note:徐胜军
- Co-author:韩九强,于军棋
- First Author:zhaoliang,xushengjun
- Indexed by:Journal paper
- Volume:卷:124
- Issue:期:22
- Page Number:页:5732– 5738
- Translation or Not:no
- Date of Publication:2013-11-01