DATA-GUIDED RANDOM WALKS FOR FINE-STRUCTURED OBJECT SEGMENTATION

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	DATA-GUIDED RANDOM WALKS FOR FINE-STRUCTURED OBJECT SEGMENTATION
	Gong, Yongchao; Xiang, Shiming; Pan, Chunhong
	2016-03
会议名称	IEEE International Conference on Acoustics, Speech and Signal Processing
页码	1806-1810
会议日期	2016-3-20 ~ 2016-3-25
会议地点	Shanghai, China
摘要	Random walks (RW) is a popular technique for object segmentation. Apart from the satisfactory performance in various applications, its most appealing advantage is the computational efficiency. However, RW often fails to produce complete and connected results in finestructured (FS) object segmentation. To utilize the high efficiency and overcome the drawbacks in tackling FS objects, we develop a novel approach within the RW framework. Specifically, we propose to introduce labeling preference learned from the image data into the RW model to guide the propagation of random walkers. With the help of the guidance, random walkers are more likely to propagate correctly to the FS regions, thus yielding more accurate results. Similar to RW, this approach also bears properties such as computational efficiency, closed-form solution and unique global optimum. Moreover, it has the capacities of handling disconnected objects and transferring segmentation. Comparative experimental results demonstrate that the proposed approach achieves the state-of-the-art performance in FS object segmentation, with a low requirement of runtime.
关键词	Random Walks Data-guided Random Walks Fine-structured Object Segmentation Labeling Preference
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14492
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
作者单位	National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Gong, Yongchao,Xiang, Shiming,Pan, Chunhong. DATA-GUIDED RANDOM WALKS FOR FINE-STRUCTURED OBJECT SEGMENTATION[C],2016:1806-1810.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Data-Guided Random W（5068KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载