Abstract: Aimed at the drawback of the multifocus image fusion method using Support Value Transform（SVT）, a new image fusion method using softy-space mapping-based complex SVT is proposed in this paper. This method maps the image information on the real number field into its softy-space image on the complex number field, and then processes the SVT. It preserves the existing advantages of SVT and increases the image decomposition information, leading to a higher image fusion quality. Experimental results show that the method performs better in both subjective fusion results and objective evaluation indexes when compared with the results of SVT.

Key words: image fusion, multifocus image, Support Value Transform（SVT）, softy-space mapping

摘要： 针对支持度变换在多聚焦图像融合技术方面存在的不足，提出了基于软空间映射的复支持度变换的图像融合方法，该方法将图像信息（实数域）映射到其软空间的象（复数域），在此基础上进行支持度变换，既保留支持度变换已有的优点，又增加了图像的分解信息量，进一步提高了图像融合质量。实验结果表明在主观融合效果与客观评价指标方面与支持度变换相比均有一定提高。

关键词: 图像融合, 多聚焦图像, 支持度变换, 软空间映射