遗传算法在医学图像自适应融合中的应用

为了解决现有融合方法间的优点不易综合,以及融合规则不易根据图像后续处理的要求自适应地调整的问题,提出一种基于遗传算法的医学图像融合方法。分别利用形态学金字塔和平移不变性小波变换方法产生初始图像,构造由图像评价组成的目标函数,再利用遗传算法来优化目标函数从而获取最终的结果图像。通过实验,从主观视觉和标准方差、平均梯度、熵、空间频率、均方交叉熵等定量指标两方面,证明了该方法的有效性。

Application of Genetic Algorithm in adaptive medical image fusion

Images obtained via existed image fusion methods can not be adjusted adaptively according to successive image processing steps,and it is hard to integrate advantages of different fusion algorithms.In order to solve these problems,a medical image fusion method based on Genetic Algorithm（GA） is presented.The initial images are obtained by employing the morphological pyramid and shift-invariant wavelet transform.Then,the GA using a weight sum of several image quality indexes as the objective function,is used to obtain a proper image.Two experiments verify the feasibility of the method in terms of visual quality and objective evaluation criteria,standard deviation,gradient,entropy,spatial frequency,mean-square cross entropy,etc.