A New Algorithm for Image Fusion to reduce computational Time
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2016, Vol 15, Issue 4
Abstract
Image fusion is a process to combine two or more images so that fused image becomes more informative than input images. Fusion process provides the spectral and spatial information of image. But main problem occurs of computational time when high resolution images are fused. So this paper describe a new algorithm that is based on wavelet transform in which transform is applied after forming the image into different blocks. This algorithm divides the complete image into different blocks andthen comparing the images by finding the mean square error.By using the threshold value wavelet transform is applied to require block. The transformed blocks are fused by using different fusion algorithms like averaging method, maximum or minimum pixel replacement fusion algorithm. By applying inverse of wavelet transform fused image is constructed which is more informative than the input images. The quality of fused image is find out by comparing the fused image by the original image by finding mean square error and peak signal to noise ratio. The whole process of fusion is applied on the complete image and also by using blocking method then by finding the time parameters it can be conclude that the proposed algorithm reduces the computational time by 10 times to the existence method.
Authors and Affiliations
Navjot kaur, Navneet kaur
Keywords
Related Articles
- EP ID EP650821
- DOI 10.24297/ijct.v15i4.3979
- Views 103
- Downloads 0
CUSTOMERS PERCEPTIONS OF MOBILE BANKING USING THE TECHNOLOGY ACCEPTANCE MODEL FOR SELECTED BANKING OUTLETS IN GAUTENG, SOUTH AFRICA
Much of the available literature that has examined the diffusion of mobile banking has tended to focus on the developed societies where these innovations had initially been introduced. As such, there is a paucity of stud...
An Instance Selection Algorithm Based On Reverse k Nearest Neighbor
Classification is one of the most important data mining techniques. It belongs to supervised learning. The objective of classification is to assign class label to unlabelled data. As data is growing rapidly, handling it...
Reversible data hiding based on histogram modification of difference images by s-type and Hilbert curve scanning
Reversible data hiding technology has currently attracted great attention recently. Using reversible data hiding methods, original cover images can be recovered losslessly from the cover image embedded information. In t...
MODELING OF AN E-BUSINESS SYSTEM
Always before we start creating or accessing a particular system, it is more than necessary to have a clearer picture of how to create, respectively, how to approach a certain system, in this case of a e-business system....
Forecasting based on Bayesian type models
A review of some Bayesian data analysis models is proposed, namely the models with one and several parameters. A methodology is developed for probabilistic models construction in the form of Bayesian networks using stati...