Multi-exposure image fusion using structural weights and visual saliency map

Multi Exposure Image Fusion (MEIF) represents a procedure for combining multiple images with various exposure levels into a single image for good visual perception. The traditional techniques often suffer from spatial inconsistency, visual distortion, noisy weights maps, losing of vivid colour information. To addresses these issues, in this article we proposed a MEIF using structural weights and a visual saliency map. Source images are decomposed into contrast, structure and intensity features to find the its detail layers. To preserve the edge information for better spatial consistent structures, base layers of source images will be generated through Rolling Guided Filter (RGF). To retain vivid colours and avoid visual distortion we used saliency maps of source images. A weight map generator compares the base layers and saliency maps in order to avoid noisy weight maps. Finally fused image will be generated through fused base and detail layers. The effectiveness of the proposed MEIF method has been evaluated both objectively and subjectively, and the results show that it is superior to a subset of already available solutions.