基于双树复小波变换彩色多聚焦图像融合方法

Color multi-focus image fusion method based on dual-tree complex wavelet transform

针对离散小波变换图像融合算法在特征表达上存在的不足,将双树复数小波变换引入到彩色多聚焦图像融合中。对彩色图像的三个通道分别进行融合处理,并采用基于多测度的融合策略:各通道小波变换后低频子带采用区域清晰度的方法;高频子带采用区域标准差的方法。融合效果评价除使用传统方法的熵、交叉熵外,还使用了通用的主观与客观相结合的方法。通过对实验结果的主客观性能分析,验证了该方法得到的融合图像效果较好,优于离散小波变换融合算法。

The dual-tree complex wavelet transform is introduced in color multi-focus image fusion,aiming at the deficiencies of existing discrete wavelet transform based algorithms in characteristics representation.Three channels of the source color images are fused respectively by multi-measurement fusion scheme.The local definition is applied in low frequency bands,and the local standard deviation is applied in high frequency bands,after the wavelet transform of every channel of source images.Besides the taditional performance evaluating methods of entropy and cross entropy,the universal measures which combine objective and subjective factors are also used.The experimental results show that the fused image obtained by proposed method has good effect, and the proposed method is superior to the discrete wavelet transform fusion based algorithms.