Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach - 2017 PROJECT TITLE :Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach - 2017ABSTRACT:We tend to propose a easy however effective structural patch decomposition approach for multi-exposure image fusion (MEF) that is strong to ghosting impact. We have a tendency to decompose a picture patch into three conceptually independent elements: signal strength, signal structure, and mean intensity. Upon fusing these three parts separately, we have a tendency to reconstruct a desired patch and place it back to the fused image. This novel patch decomposition approach advantages MEF in many aspects. Initial, as opposed to most pixel-wise MEF methods, the proposed algorithm will not need post-processing steps to improve visual quality or to reduce spatial artifacts. Second, it handles RGB color channels jointly, and so produces fused images with a lot of vivid color appearance. Third and most importantly, the direction of the signal structure component in the patch vector area provides ideal information for ghost removal. It permits us to reliably and efficiently reject inconsistent object motions with respect to a chosen reference image while not performing computationally expensive motion estimation. We have a tendency to compare the proposed algorithm with 12 MEF methods on 21 static scenes and 12 deghosting schemes on nineteen dynamic scenes (with camera and object motion). Extensive experimental results demonstrate that the proposed algorithm not solely outperforms previous MEF algorithms on static scenes however also consistently produces prime quality fused images with little ghosting artifacts for dynamic scenes. Moreover, it maintains a lower computational value compared with the state-of-the-art deghosting schemes. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Unified Discriminative and Coherent Semi-Supervised Subspace Clustering - 2018 Beyond A Gaussian Denoiser: Residual Learning Of Deep Cnn For Image Denoising - 2017