基于小波变换多尺度积的图像融合算法  

Image fusion method based on the multiscale products of wavelet transform

作　　者：黄世亮[1] 裘鉴卿[1] 

机构地区：[1]中国科学院武汉物理与数学研究所波谱与原子分子物理国家重点实验室

出　　处：《红外与激光工程》2007年第3期391-394,共4页Infrared and Laser Engineering

基　　金：国家自然科学基金重点资助项目(10234070)

摘　　要：图像融合是图像处理中的关键技术之一。它在军事和民用图像处理领域获得了广泛的应用。提出了一种新的基于小波变换多尺度积的图像融合算法,小波变换多尺度积具有放大信号边缘特征和降低信号噪声的特点,有利于在融合图像中保持图像的细节特征。利用统计分析的评判准则,如熵、标准偏差评价图像的融合效果。实验结果表明该方法提高了图像的熵和标准偏差。在保留原图像信息的情况下增强了融合图像的细节信息。Image fusion is the one of the key technologies in image processing. It can be used widely in the field of image processing of modem military and civilian. In this paper, a novel image fusion algorithm based on multiscale products of wavelet transform is proposed. The multiscale products of wavelet transform can magnify edge structure features and supress noises. It is beneficial to preserve detail of fusion image by using multiscale products.Entropy and standard deviation are used to evaluate image fusion performance. The results show the effectiveness of the method, which preserves the information of the original images and enhances their detail.

关 键 词：小波变换 多尺度积 图像融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]