北京生物醫(yī)學工程

基于混合優(yōu)化算法的醫(yī)學圖像配準方法

A medical image registration algorithm based on hybrid optimization algorithm

作者：別術(shù)林劉杰唐子淑邱禧荷

單位：北京交通大學生物醫(yī)學工程系（北京100044）

關(guān)鍵詞：互信息；Powell算法；遺傳算法

分類號：

出版年·卷·期（頁碼）：2015·34·3（234-238）

摘要：

基于互信息的圖像配準算法計算復(fù)雜度高，配準速度慢。針對這一問題，本文提出一種基于改進遺傳算法和Powell算法相結(jié)合的醫(yī)學圖像配準方法。首先針對傳統(tǒng)遺傳算法收斂速度慢、易早熟的缺陷，本文對遺傳操作中的交叉運算過程提出了改進策略，并將改進的遺傳算法與Powell算法相結(jié)合，充分利用遺傳算法的全局搜索能力與Powell算法的局部搜索能力。與Powell算法和未改進的遺傳算法相比，本文提出的算法極大地縮短了圖像配準所用的時間,同時提高了算法的抗噪性。

Image registration algorithm based on mutual information has high complexity and low speed. To solve the problem, a new image registration method based on improved genetic algorithm and Powell algorithm is proposed in this paper. Considering the shortages of the standard genetic algorithm, such as prematurity and slow convergence that may result in mismatching, in this paper, we improve the crossover operation of the genetic operations. At the same time, we combine the improved genetic algorithm and Powell algorithm. The method makes full use of the global search capability of genetic algorithm and the local search capability of Powell algorithm. Compared with Powell algorithm and the traditional genetic algorithm, this algorithm we proposed can effectively improve the image registration velocity and noise immunity.

參考文獻：

［1］鄭瑩, 李光耀. 區(qū)域和局部信息結(jié)合的雙向醫(yī)學圖像配準［J］. 中國圖象圖形學報, 2011,16(1): 90-96.

Zheng Ying，Li Guangyao. Bilateral medical image registration based on regional and local information［J］. Journal of Image and Graphics, 2011,16(1):90-96.

［2］楊金寶, 劉長春, 胡順波. 廣義信息熵在醫(yī)學圖像配準中的應(yīng)用［J］.計算機工程與應(yīng)用, 2008,44(8):34-36.

Yang Jinbao, Liu Changchun, Hu Shunbo. Medical image registration based on generalized entropy measures［J］. Computer Engineering and Applications, 2008,44(8):34-36.

［3］Lu G, Yan J. Image registration based on criteria of feature point pair mutual information［J］.IET Image Process,2011,6(5):560-566.

［4］沈小衛(wèi), 何明一. 一種基于混合優(yōu)化算法的醫(yī)學圖像配準方法［J］. 計算機應(yīng)用研究, 2010,27(8):3159-3161.

Shen Xiaowei, He Mingyi. Medical image registration based on hybrid optimization algorithm［J］. Application Research of Computers, 2010,27(8):3159-3161.

［5］馮雪芳, 吳錫生. 一種混合搜索策略的圖像配準方法研究［J］.計算機仿真，2012,29(9):274-277.

Feng Xuefang, Wu Xisheng. Hybrid search optimization strategy of image registration method research［J］. Computer Simulation, 2012,29(9):274-277.

［6］Viola PA, Wells WM. Alignment by Maximization of Mutual Information［C］. Boston, MA：Proc of the 5th Int Conf Computer Vision, 1995:16-23.

［7］Thevenaz P, Unser M. Optimization of mutual information for multiresolution image registration［J］.IEEE Trans Image Processing, 2000,9(12):2083-2099.

［8］Meng FL, Wu SX. Research of genetic algorithm in function optimizer based on HCI［C］//Proceedings of the IEEE International Symposium on IT in Medicine and Education. Piscataway. NJ:IEEE Press, 2008,1:1049-1052.

［9］滕皓, 曹愛增. 一種改進變尺度混沌優(yōu)化的模糊量子遺傳算法［J］.計算機工程, 2010,36(13):175-177.

Teng Hao, Cao Aizeng. A meliorated mutative scale chaos optimization fuzzy quantum genetic algorithm［J］.Computer Engineering,2010, 36(13): 175-177.

［10］周其慧, 宋余慶. 基于多分辨率和Powell算法的醫(yī)學圖像配準［J］. 計算機應(yīng)用研究, 2013,30(4):1256-1258.

Zhou Qihui, Song Yuqing. Medical image registration based on multi-resolution and Powell algorithm［J］. Application Research of Computers, 2013,30(4):1256-1258.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频