基于Kmeans的遥感图像分割要点详解.docVIP

硕士研究生学位论文 新 疆 大 学 论文题目(中文)：基于K-means的遥感图像分割 论文题目(外文)： Remote Sensing Image Segmentation Based on K-means 研 究 生 姓 名：徐二静 学 科、 专 业：工学 信号与信息处理 研 究 方 向：光信息处理 导师姓名 职称：贾振红 教授 论文答辩日期 2014年 5月 22 日 学位授予日期 2014年 6月 日摘要 开展遥感图像分割的研究，对人们在遥感数据日益增长的需求处理方面有着十分重要的意义,而遥感图像的复杂、多光谱多层次等特性使得遥感图像的分割一直都是遥感图像处理领域的重点难点课题. 虽然随着人们对图像分割的研究已经很广泛且深入成熟，但是由于多方面的原因，图像分割的应用仍然具有很大的挑战,尤其是遥感图像技术的发展更是任重而道远。 本论文针对K-means算法（K-均值聚类算法）、最大类间方差法和水平集算法各自的特点，主要提出了两种遥感图像分割模型，并对实验结果进行了总结分析。本文的主要工作有： 介绍了图像分割相关理论内容，将现有图像分割方法模型大致归成了四大类，并对每一大类都进行了较为系统的阐述，具体引出了本课题研究的目的与意义。 根据最大类间方差算法和K-means聚类算法各自的优缺点，提出了一种将最大类间方差法（Otsu）和K-means算法相结合的遥感图像分割算法。大量的实验结果显示，本文提出的算法不仅克服了经典Otsu算法分割信息不完备的缺陷，增强了Otsu阈值分割算法的鲁棒性，而且还是对K-均值聚类算法Abstract Remote sensing image segmentation has played a vital and significant role in people’s growing demand for remote sensing data processing, while the complex、multi-level、multi-spectrum or other features makes remote sensing image segmentation one of the most important and difficult topics in remote sensing image processing field. Although scholars has did much extensive and in-depth studies in image segmentation，image segmentation applications is still facing great challenge due to various reasons, especially for the development of remote sensing image technology. Based on the principles of the K-means Clustering algorithm、Otsu method and level-set method , two remote sensing image segmentation model are proposed, and the experimental results are summarized analyzed. The main work and contributions of this paper are as follows. First, the theory of image segmentation is introduced, the author classify the existing image segmentation methods into four categories and give them a systematic exposition separately, mainly present the purpose and significance of this research. Second, a new remote sensing image segmentation model combines the Otsu method and K-means clustering algorithm is proposed considering their merits and defects. Several stud