PROJECT TITLE :

Fast multi-exposure image fusion with median filter and recursive filter

ABSTRACT :

This paper proposes a weighted sum primarily based multi-exposure image fusion method that consists of 2 main steps: three image options composed of local distinction, brightness and color dissimilarity are 1st measured to estimate the weight maps refined by recursive filtering. Then, the fused image is made by weighted sum of supply images. The most advantage of the proposed method lies in a recursive filter based mostly weight map refinement step which is in a position to get correct weight maps for image fusion. Another advantage is that a novel histogram equalization and median filter based mostly motion detection technique is proposed for fusing multi-exposure images in dynamic scenes which contain motion objects. Furthermore, the proposed technique is quite fast and therefore can be directly used for most shopper cameras. Experimental results demonstrate the prevalence of the proposed methodology in terms of subjective and objective analysis.