Abstract: A new image fusion method based on Curvelet transfrom and feature product is presented. Multiresolution decomposition of source images is obtained by Curvelet transform. The corresponding subband images by using different rules are fused, that is, the method based on average is used in low frequency components while high frequency components are fused by local feature product. The fused image is obtained by inverse Curvelet transform. Gradientbased Structural Similarity(GSSIM), Space Frequency(SF) and Peak Signal to Noise Ratio(PSNR) are used to evaluate the image fusion results. The new method is tested by multifocus images. Experimental results show the method can achieve a better fusion performance and is suitable for human vision system observation.

Key words: image fusion, multifocus, Curvelet transform, feature product

摘要： 提出一种基于Curvelet变换和特征量积的图像融合方法。对2幅图像进行Curvelet变换，低频部分采用加权平均的融合算法，高频采用基于特征量积的加权融合算法，从而实现Curvelet系数的融合，并重构得到融合图像。对多聚焦图像进行实验，利用梯度结构相似度、空间频率、峰值信噪比进行评价，实验结果表明，该方法能够取得较好的效果。

关键词: 图像融合, 多聚焦, Curvelet变换, 特征量积

CLC Number: 

• TP391