计算机工程 ›› 2009, Vol. 35 ›› Issue (10): 203-205.doi: 10.3969/j.issn.1000-3428.2009.10.067

• 图形图像处理 • 上一篇    下一篇

基于鞍点搜索的粘连对象图像分割方法

汪一聪,陈 恳   

  1. (宁波大学信息科学与工程学院,宁波 315211)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-05-20 发布日期:2009-05-20

Image Segmentation Method of Touching Objects Based on Saddle-point Search

WANG Yi-cong, CHEN Ken   

  1. (College of Information Science and Engineering, Ningbo University, Ningbo 315211)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-05-20 Published:2009-05-20

摘要: 针对图像中不规则形状物体接触的分割问题,提出一种采用Hessian矩阵来判断分割点(即鞍点)进行粘连对象分割的方法。根据对图像进行腐蚀操作得到的三维地貌图,结合鞍点的数学特性,运用Hessian矩阵的特征值对鞍点进行搜索定位,沿经过鞍点的最大梯度路径分割粘连对象。与目前已有的几种分割算法相比,该方法具有算法简捷、分割效果好以及易于实现的特点。

关键词: 鞍点, Hessian矩阵, 特征值

Abstract: Aiming at the problem of segmenting the touching anomalous objects in an image, this paper proposes a method based on saddle-point detection using Hessian matrix. The image is converted to its 3D topographic counterpart by sequential erosion, followed by searching the saddle-point utilizing Hessian matrix determination approach. The segmentation is performed at the identified saddle-point by tracking the maximal gradient path. Compared with other conventional segmentation algorithms, this method is more practical for implementation, and shows its superiority in execution speed.

Key words: saddle-point, Hessian matrix, eigenvalue

中图分类号: