A new wavelet-based approach to image fusion, which is based on HSV color space and addition of wavelet coefficients, is proposed. The new fusion method can keep more spatial information and spectral information. The process is as follows: Converting the multi-spectral image into HSV (Hue, Saturation, and Value) color space by HSV transform; formalizing the V component into two types, one is in the range of [0, 1] the other is in the range of [0, 255], then decomposing these two different V components and panchromatic image by wavelet transform; merging the wavelet coefficients by means of Addition Strategy after decomposition; finally, obtaining the fused image by wavelet reconstruction and inverse HSV transform. Experimental results show that the new method is better than generic wavelet-based fusion rule.