| 基于快速谱聚类的图像分割算法 |
| |
| 引用本文： | 李纯,卢志茂,杨朋.基于快速谱聚类的图像分割算法[J].应用科技,2012(2):26-30. |
| |
| 作者姓名： | 李纯 卢志茂 杨朋 |
| |
| 作者单位： | 1. 哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001
2. 中国人民解放军91685部队,海南陵水572424 |
| |
| 基金项目： | 国家自然科学基金资助项目(60975042) |
| |
| 摘 要： | 设计了一种基于快速谱聚类的图像分割算法,该算法利用余弦相似度构造相似度矩阵,避免了传统谱聚类算法中尺度因子的精确设置问题,提高了算法效率.在谱映射的过程中,该算法采用了Nystrm逼近策略,降低了谱聚类算法的复杂度和内存消耗.在Berkeley图像库上的图像分割实验证明了算法的有效性.
|
| 关 键 词： | 图像分割 谱聚类 余弦相似度 Nystrm逼近 |
Image segmentation based on fast spectral clustering algorithm |
| |
| LI Chun,LU Zhimao,YANG Peng.Image segmentation based on fast spectral clustering algorithm[J].Applied Science and Technology,2012(2):26-30. |
| |
| Authors: | LI Chun LU Zhimao YANG Peng |
| |
| Institution: | 1.College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China 2.No.91685 Unit of PLA,Lingshui 572424,China |
| |
| Abstract: | An image segmentation approach based on a fast spectral clustering algorithm is proposed,in which cosine similarity is used to attain similarity matrix.As a result,the problem of accurately setting the scale factor in the traditional spectral clustering algorithm is avoided,and the efficiency of the algorithm is improved.To efficiently apply the algorithm to image segmentation,Nystrm approximation strategy is used in the course of spectral mapping to reduce the computation complexity and memory consumption.Experimental results on Berkeley image database show the validity of the algorithm. |
| |
| Keywords: | image segmentation spectral clustering cosine similarity Nystrm approximation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
