一种基于图割和支持向量机的彩色遥感图像分割  

A Color Remote Sensing Image Segmentation Algorithm Based on Graph Cut and Support Vector Machine

作　　者：张满[1] 颜普[1] ZHANG Man,YAN Pu （Key Lab Intelligent Computing ＆ Signal Ministry of Education,Anhui University, Hefei 230039,China）

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230039

出　　处：《电脑知识与技术》2012年第6期3958-3961,共4页Computer Knowledge and Technology

摘　　要：该文提出了一种基于图割和支持向量机（SVM）的彩色遥感图像分割算法，首先针对在RGB空间中很难有效区分颜色相似性的问题，通过选择更加符合颜色视觉特性的HSI颜色空间进行图像处理与分析，然后利用图割算法定义一个能量函数来判断图像中像素是属于图像前景还是图像背景，从而有选择的提取前景种子节点与背景种子节点。最后以前景种子节点与背景种子节点为SVM算法的训练集对遥感图像进行训练分类，完成图像的分割。实验表明此方法是一种有效的彩色遥感图像分割方法。A color remote sensing image segmentation algorithm based on graph cut and support vector machine is proposed in this paper. Firstly, because it is difficulty to evaluate the similarity of two colors from their distance in RGB color space, color image processing is implemented in Hue Saturation Intensity （HSI） space which reflects the features of human vision. Secondly, An energy function is defined by graph cut algorithm for determining the image pixels belongs to the image background image and the prospects,then prospects seed nodes and background seed nodes are used as training set of SVM.FinaUy, remote sensing image are classified using SVM. A color remote sensing image segmentation is completed. Experiments show the efficiency of the proposed algorithm on color remote sensing images.

关 键 词：图像分割 支持向量机 图割图论 HIS 

分 类 号：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]