卢湖川

个人信息Personal Information

教授

博士生导师

硕士生导师

主要任职:未来技术学院/人工智能学院执行院长

性别:男

毕业院校:大连理工大学

学位:博士

所在单位:信息与通信工程学院

学科:信号与信息处理

办公地点:大连理工大学未来技术学院/人工智能学院218

联系方式:****

电子邮箱:lhchuan@dlut.edu.cn

扫描关注

论文成果

当前位置: 中文主页 >> 科学研究 >> 论文成果

Spectral Segmentation via Midlevel Cues Integrating Geodesic and Intensity

点击次数:

论文类型:期刊论文

发表时间:2013-12-01

发表刊物:IEEE TRANSACTIONS ON CYBERNETICS

收录刊物:SCIE、EI、Scopus

卷号:43

期号:6

页面范围:2170-2178

ISSN号:2168-2267

关键字:Geodesic; PR curve; spectral clustering; superpixel; unsupervised segmentation

摘要:Image segmentation still remains as a challenge in image processing and pattern recognition when involving complex natural scenes. In this paper, we present a new affinity model for spectral segmentation based on midlevel cues. In contrast to most existing methods that operate directly on low-level cues, we first oversegment the image into superpixel images and then integrate the geodesic line edge and intensity cue to form the similarity matrix W so that it more accurately describes the similarity between data. The geodesic line edge could avoid strong boundary and represent the true boundary between two superpixels while the mean red green blue vector could describe the intensity of superpixels better. As far as we know, this is a totally new kind of affinity model to represent superpixels. Based on this model, we use the spectral clustering in the superpixel level and then achieve the image segmentation in the pixel level. The experimental results show that the proposed method performs steadily and well on various natural images. The evaluation comparisons also prove that our method achieves comparable accuracy and significantly performs better than most state-of-the-art algorithms.