Fusion for visual context enhancement using intensity transformation function of infrared images

An intensity transformation function of infrared images is presented and used for context enhancement of visual images, upon which a new image fusion method in the shift-invariant wavelet domain is developed. The function behaves like a sigmoid function and shifts and expands the range of dark pixels of infrared images. These adjustments can avoid artificial bright pixels introduced in the later enhancing of visual images and the bleaching effect in the final fused images owing to the exponential map of very dark pixels of the infrared images. Experimental results validate the subjective performance of the proposed method, along with objective performance through several suggested quantitative metrics.