• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2012, Vol. 34 ›› Issue (10): 104-107.

• 论文 • 上一篇    下一篇

一种新的血管造影图像Hessian矩阵增强算法

康长青,袁 磊,华 丽,曹文平   

  1. (湖北文理学院数学与计算机科学学院,湖北 襄阳 441053)
  • 收稿日期:2012-04-25 修回日期:2012-07-10 出版日期:2012-10-25 发布日期:2012-10-25
  • 基金资助:

    国家自然科学基金资助项目(61172084);襄樊学院科研项目(2009YA011)

A Novel Hessian Matrix Enhancement Algorithm for Angiography Images

KANG Changqing,YUAN Lei,HUA Li,CAO Wenpin   

  1. (Faculty of Mathematics and  Computer Science,Hubei University of Arts and Science,Xiangyang 441053,China)
  • Received:2012-04-25 Revised:2012-07-10 Online:2012-10-25 Published:2012-10-25

摘要:

针对实际血管造影图像存在的噪声和光照不均,本文提出一种新的Hessian矩阵增强算法来提取血管图像。算法主要通过无抽样方向滤波器组进行血管方向图分解、同态滤波器滤波、Hessian特征矩阵和血管方向图合成。实验表明,与传统Hessian算法相比,提出的算法能够连续提取血管的精细结构,对噪声不敏感,处理的图像质量更高。

关键词: 图像增强, Hessian矩阵, 分解合成

Abstract:

A novel Hessian matrix algorithm is presented to enhance angiography images considering their noise and nonuniform illumination.The algorithm is performed in four steps:decimationfree directional filter bank decomposing,homomorphic filtering,Hessian eigenvalues matrix, and directional image reconstruction. Experimental results show that the proposed algorithm can detect filamentous image structures continuously,and has great advantages of both noise insensitioity and image visual quality,in comparison to the traditional Hessian algorithms.

Key words: image enhancement;Hessian matrix;decomposition and reconstruction