Boundary Extraction in Natural Images Using Ultrametric Contour Maps
Boundary Extraction in Natural Images Using Ultrametric Contour Maps
复制标题
DOI：
10.1109/cvprw.2006.48
复制
发表时间：
2006-06
期刊：
影响因子：
--
通讯作者：
Pablo Arbeláez
中科院分区：
文献类型：
--
作者：
Pablo Arbeláez
本文提出了一个低层次的自然图像边界提取和分割系统，并对其性能进行了评价。我们研究的层次分类的框架中的问题，其中图像的几何结构可以表示由超度量轮廓图，软边界图像相关联的一个家庭的嵌套分割。我们定义通用超度量的距离，通过整合局部轮廓线索沿着区域边界，并结合这些信息与区域属性。然后，我们定量评估我们的结果与地面实况分割数据，证明我们的系统优于两个广泛使用的分层分割技术，以及最先进的局部边缘检测。
This paper presents a low-level system for boundary extraction and segmentation of natural images and the evaluation of its performance. We study the problem in the framework of hierarchical classification, where the geometric structure of an image can be represented by an ultrametric contour map, the soft boundary image associated to a family of nested segmentations. We define generic ultrametric distances by integrating local contour cues along the regions boundaries and combining this information with region attributes. Then, we evaluate quantitatively our results with respect to ground-truth segmentation data, proving that our system outperforms significantly two widely used hierarchical segmentation techniques, as well as the state of the art in local edge detection.