Graph Based Image Segmentation: A modern approach
Graph Based Image Segmentation: A modern approach
复制标题
DOI：
--
复制
发表时间：
2008-12
期刊：
影响因子：
--
通讯作者：
Jingdong Wang
中科院分区：
文献类型：
--
作者：
Jingdong Wang
图像分割是指将图像划分为有意义的不相交区域的过程。这个过程是计算机视觉的基础，因为许多应用，如图像检索，视觉摘要，基于图像的建模等，都可以从它中受益。这个过程也是具有挑战性的，因为分割通常是主观的，计算成本很高。这本书反过来开发了成对图方法的先验模型，该方法是从多个线索定义的，一种基于超图的方法，该方法对数据点之间的多个明智的关系进行建模，以及一种基于树结构图的方法，该方法导致了规范化切割标准的高效和有效的解决方案。这些方法在多视图、交互式和自动图像分割问题中得到了验证。本书适合于图像处理、计算机视觉、模式识别和机器学习领域的学生和研究人员。
Image segmentation refers to a process of dividing the image into disjoint regions that were meaningful. This process is fundamental in computer vision in that many applications, such as image retrieval, visual summary, image based modeling, and so on, can essentially benefit from it. This process is also challenging because the segmentation is usually subjective and the computation is highly costly. This book develops in turn the prior model for the pairwise graph approaches which is defined from multiple cues, a hyper graph based method which models multiple wise relations among the data points, and a tree structured graph based method which leads to an efficient and effective solution to the normalized cuts criterion. These approaches are demonstrated in multiple view, interactive and automatic image segmentation problems. This book is suitable for students and researchers in image processing, computer vision, pattern recognition and machine learning.