提升静态小波特征对比度多聚焦图像融合算法*

针对多聚焦图像融合问题,提出了一种新的基于提升静态小波变换(lifting stationary wavelet transform,LSWT)的特征对比度图像融合方法。该方法对图像经LSWT分解得到的不同子带系数采用不同的融合方案。在选择低频子带系数时提出了一种基于改进拉普拉斯能量和的视觉特性对比度系数选择方案;而在选择融合图像的高频子带系数时,根据人眼视觉对图像局部对比度变换非常敏感的特性,提出了局部特征对比度的概念,设计了一种基于局部特征对比度的系数选择方案。实验证明,该算法相对于传统图像融合方法,能得到视觉效果更好、量化指标更优的融合图像。

Multifocus image fusion scheme based on features contrast of lifting stationary wavelet

For the fusion problem of the multifocus image,this paper proposed a novel image fusion algorithm based on LSWT and features contrast.In this method,proposed a new image fusion rule based on visual characteristic contrast of sum-modified-Laplacian(SML)and used to select the coefficients of the fused subimage from the clear parts of the lowpass subband.For choosing the highpass subband coefficients,developed local feature contrast according to the characteristic of human vision system which was highly senstive to the local contrast change.Then proposed a novel fusion rule for fusing the highpass subband coefficients.Experimental results demonstrate the proposed image fusion method is effective and can provide better performance in fusing multifocus images than the traditional image fusion methods in both visual quality and objective evaluation criteria.