Normalized cuts and image segmentation
Normalized cuts and image segmentation
复制标题
DOI：
10.1109/34.868688
复制
发表时间：
2000-08-01
影响因子：
23.6
通讯作者：
Malik, J
中科院分区：
文献类型：
--
作者：
Shi, JB;Malik, J
我们提出了一种新的方法来解决视觉中的感知分组问题。而不是专注于本地功能和他们的图像数据中的隐藏，我们的方法旨在提取图像的全球印象。我们把图像分割作为一个图分割问题，并提出了一种新的全球标准，规范化切割，分割图。标准化切割准则测量不同组之间的总不相似性以及组内的总相似性。我们表明，一个有效的计算技术的基础上的广义特征值问题，可以用来优化这个标准。我们已经应用这种方法分割静态图像，以及运动序列，并发现结果是非常令人鼓舞的。
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression of an image. We treat image segmentation as a graph partitioning problem and propose a novel global criterion, the normalized cut, for segmenting the graph. The normalized cut criterion measures both the total dissimilarity between the different groups as well as the total similarity within the groups. We show that an efficient computational technique based on a generalized eigenvalue problem can be used to optimize this criterion. We have applied this approach to segmenting static images, as well as motion sequences, and found the results to be very encouraging.