基于进化规划的医学图像恢复方法研究  

A Restoration approach of medical Image using evolutionary programming

作　　者：潘中良[1] 陈翎[1] 张光昭[2] 

机构地区：[1]华南师范大学物理与电信工程学院,广州510006 [2]中山大学电子与通信工程系,广州510275

出　　处：《激光杂志》2007年第6期51-52,共2页Laser Journal

基　　金：国家自然科学基金项目(60006002);广东省教育厅自然科学研究项目(02019)资助;广东省自然科学基金资助(7005833)。

摘　　要：图像模糊对图像中特定目标的检测以及特征的提取等都会造成影响,采用图像恢复可以改善图像的质量。本文提出了一种基于进化规划的图像恢复方法,该方法把图像的可行解用个体表示,由多个个体构成种群,通过种群的进化而获得质量较优的图像。这种方法可以应用于医学图像的处理。首先分析了图像恢复的原理,然后给出了方法的详细实现步骤和相关的实验结果。The image blur will produce effects on the detecting for the specific objects and the extracting for image features, the image restoration can enhance the quality of image. An image restoration approach based on evolutionary programming is presented in this paper. An image is represented by an individual. The population consists of a lot of individuals. The image with better quality is obtained by the evolutions of populations. This approach can be applied to the processing of medical images. First of all, the principle of image restoration is discussed. Secondly, the implementation of the approach proposed and some experimental resuits are given in detail.

关 键 词：图像恢复 医学图像 进化算法 进化规划 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]