自適應遺傳算法在多模圖像配準中的應用

全文約5000字 論述翔實

摘要：本文提出了一種改進的自適應遺傳算法并應用到多模圖像配準的優(yōu)化過程中，該方法采用進化前后期分別調(diào)整交叉概率和變異概率、二次交叉以及移民策略等來克服傳統(tǒng)遺傳算法容易陷入局部最優(yōu)的缺點。實驗結(jié)果表明了該算法的可行性和有效性。

關(guān)鍵字：遺傳算法；圖像配準；交叉；變異

Application of Adaptive Genetic Algorithm in Multimodality Image Registration

Abstract: An improved adaptive genetic algorithm is proposed, and the method is applied to the optimization process of multimodality image registration. This method includes adjusting the probability of crossover and mutation in the evolutionary process, second crossover and emigration strategies. The method can overcome the disadvantage of traditional genetic algorithm that is easy to get into a local optimum answer. The experiment indicates the validity and feasibility of this algorithm.
Key words: Genetic algorithm; Image registration, Crossover, Mutation.

部分參考文獻

[4] C.Studholme, D.L.G.Hill, D.J.Hawkes, An overlap invariant entropy measure of 3D medical image alignment[J]. Pattern Recognition, 1999, 32(1):71-86.
[5] 嚴峻. 一種改進的基于成熟前收斂判斷的自適應遺傳算法[J]. 南京郵電學院學報,1993,19(1):35-38.
[6] 樊叔維,汪國梁,謝衛(wèi). 遺傳算法在電力變壓器優(yōu)化設計中的應用研究[J]. 中國電機工程學報,1996,16(5):346-348.
[7] 劉志剛,耿英三,王建華等. 基于改進自適應遺傳算法的空心串聯(lián)電抗器優(yōu)化設計[J].中國電機工程學報,2003,23(9):103-106.