Using contours to detect and localize junctions in natural images
Using contours to detect and localize junctions in natural images
复制标题
DOI：
10.1109/cvpr.2008.4587420
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
M. Maire;Pablo Arbeláez;Charless C. Fowlkes;Jitendra Malik
中科院分区：
文献类型：
--
作者：
M. Maire;Pablo Arbeláez;Charless C. Fowlkes;Jitendra Malik
轮廓和连接是知觉组织和形状识别的重要线索。局部检测结点已经被证明是有问题的，因为图像强度表面在结点附近是混乱的。边缘检测器在交界处附近也不能很好地工作。目前主要的结点检测方法，例如Harris算子，都是基于强度信号的2D变化。然而，该策略的一个缺点是它混淆了纹理区域和连接点。我们认为，正确的交汇点检测方法应该利用在交叉点入射的轮廓；轮廓本身可以通过使用更全局方法的过程来检测。在本文中，我们开发了一种新的结合局部和全局线索的高性能轮廓检测器。该轮廓检测器在Berkeley分段数据集(BSD)基准上提供了迄今为止最好的性能(F=0.70)。从得到的轮廓线，我们检测和定位候选交汇点，同时考虑轮廓显著和几何构型。我们表明，我们的轮廓模型的改进导致了更好的连接。我们的轮廓和连接检测器都提供最先进的性能。
Contours and junctions are important cues for perceptual organization and shape recognition. Detecting junctions locally has proved problematic because the image intensity surface is confusing in the neighborhood of a junction. Edge detectors also do not perform well near junctions. Current leading approaches to junction detection, such as the Harris operator, are based on 2D variation in the intensity signal. However, a drawback of this strategy is that it confuses textured regions with junctions. We believe that the right approach to junction detection should take advantage of the contours that are incident at a junction; contours themselves can be detected by processes that use more global approaches. In this paper, we develop a new high-performance contour detector using a combination of local and global cues. This contour detector provides the best performance to date (F=0.70) on the Berkeley Segmentation Dataset (BSDS) benchmark. From the resulting contours, we detect and localize candidate junctions, taking into account both contour salience and geometric configuration. We show that improvements in our contour model lead to better junctions. Our contour and junction detectors both provide state of the art performance.