A fast color image fusion algorithm for merging infrared and visible images is presented

which is named Architecture Optimized Version Color Transfer Based Fusion Method.The method directly uses the grayscale fused image and the difference signals of the input multiband images to construct the source YC

B

C

R

components

then uses statistical color transfer technique in YC

B

C

R

space to form a color fused image with similar color appearance as the target image.The paper mathematically proves that color spaces conforming to the general YC

B

C

R

space framework

such as YUV space

can be used as an alternative to YC

B

C

R

space in the proposed method.The ap

proach is not only limited to fuse infrared and visible images

but also suitable for merging other dual-band image types.Experimental results show that the proposed color image fusion algorithm can effectively produce a natural appearing daytime-like color fused image

and even using the pixel averaging fusion scheme to implement the grayscale fusion can also provide a satisfactory result.