首页 | 本学科首页   官方微博 | 高级检索  
     

区域轮廓的快速等级提取
引用本文:赵会彦,曹永锋.区域轮廓的快速等级提取[J].光电工程,2005,32(12):43-46,50.
作者姓名:赵会彦  曹永锋
作者单位:1. 武汉工业学院,土木工程系,湖北,武汉,430023
2. 武汉大学,电子信息学院通信系,湖北,武汉,430079
摘    要:模式识别应用常需要不同约束下的多个图像分割结果。提出了一种区域轮廓的快速等级提取方法。该方法计算图像中所有可能轮廓点的显著性,利用简单阈值操作即可得到不同显著性等级的单像素宽度闭合区域轮廓。当计算轮廓点显著性时,融合流域变换、盆地动力学(Basindynamics)和弧段动力学三个过程为一个过程,消除了它们单独运行造成的冗余计算,提高了算法效率。实验结果表明,该算法可得到理想的等级轮廓输出,比现存的类似算法提高效率1.25倍。

关 键 词:轮廓提取  等级分割  盆地动力学  弧段动力学
文章编号:1003-501X(2005)12-0043-04
收稿时间:2005-01-26
修稿时间:2005-01-262005-06-06

Fast method for detecting hierarchical field contours
ZHAO Hui-yan,CAO Yong-feng.Fast method for detecting hierarchical field contours[J].Opto-Electronic Engineering,2005,32(12):43-46,50.
Authors:ZHAO Hui-yan  CAO Yong-feng
Affiliation:1, Civil Engineering Department, Wuhan Polytechnic University, Wuhan 430023, China; 2. School of Electronic Information, Wuhan University, Wuhan 430079, China
Abstract:For pattern recognition, different segmentations of an image under different constrains are often needed. A fast hierarchical contours detection method is proposed. This method calculates the saliency value of all possible field contours. With different thresholds, one-pixel-width close contours of different saliency level can easily be detected. Three processes, watershed transformation, basin dynamics and arc dynamics are integrated into one process so that the redundant calculation is removed. Experimental results prove that the efficiency of the proposed method is 1.25 times higher than that of existed similar methods.
Keywords:Contours detection  Multi-level segmentation  Basin dynamics  Arc dynamics
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号