Main Article Content
Due to the development of High Dynamic Range Images, multi-exposure fusion has received a lot of attention in recent years. High dynamic range (HDR) imaging allows for the preservation of natural scenes in the same way that human observers perceive them. Due to the wide dynamic range of natural scenes, significant details in images may be lost when using standard low dynamic range (LDR) capture/display devices. This study proposes an efficient multi-exposure fusion (MEF) approach with a simple yet effective weight extraction method based on principal component analysis, adaptive well-exposedness, and saliency maps to minimise information loss and produce high quality HDRlike images for LDR screens.These weight maps are then refined using a guided filter, and the fusion is performed using a pyramidal decomposition. Experiment results show that the proposed method produces very strong statistical and visual results when compared to existing techniques.