| Paper: | IMDSP-P15.11 | ||
| Session: | Image Restoration and Denoising | ||
| Time: | Friday, May 19, 10:00 - 12:00 | ||
| Presentation: | Poster | ||
| Topic: | Image and Multidimensional Signal Processing: Restoration and Enhancement | ||
| Title: | Local Image Fusion using Dispersion Minimisation | ||
| Authors: | Qi Li, Tania Stathaki, Imperial College London, United Kingdom | ||
| Abstract: | Image fusion aims to provide an enhanced image by merging information of source images that capture the same scene from different sensors. In spatial domain, the contribution of each pixel in source images to the fused image is termed as \textit{fusion weight} and can be estimated based on the local information around each pixel. Combining fusion weights with source images yields the fused result with improved visual perception. The main contribution of the paper is to find the optimal weights by minimising a Constant-Modulus (CM) cost function that describes the dispersion of the fused image. Experimental results indicate that the new scheme provides an improved performance on fusing multi-focus images, comparable to other methods, such as PCA and wavelet methods. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012