CAJ | 학술논문

针对传统小波变换融合算法对细节信息的丢失问题，提出了一种新的基于平移不变小波变换的医学图像融合算法，采用灰度加权平均法进行低频部分融合；高频部分采用基于梯度能量的加权融合规则。实验结果表明，与传统的小波变换方法相比，文中方法融合效果更加理想，较多地继承了两幅源图像的重要信息，更好地描述了图像的细节部分，更具有实用性。
침대전통소파변환융합산법대세절신식적주실문제，제출료일충신적기우평이불변소파변환적의학도상융합산법，채용회도가권평균법진행저빈부분융합；고빈부분채용기우제도능량적가권융합규칙。실험결과표명，여전통적소파변환방법상비，문중방법융합효과경가이상，교다지계승료량폭원도상적중요신식，경호지묘술료도상적세절부분，경구유실용성。
To solve the problem of losing details in traditional image fusion algorithms based on wavelet transform ,a new algorithm based on translation invariance wavelet transform is proposed in the paper .The gray weighted average method is used to determine the low-frequency component of the fused image while the ggradient energy weighted fusion rule is used to fuse the high-frequency components .The experimental results show that the fused image can inherits the key information of the two original images and describe more details . Being compared with the traditional wavelet transform methods ,it is more practical .