Affiliation:
1. Usha Rama College of Engineering and Technology
2. Seshadri Rao Gudlavalleru Engineering College
Abstract
One of the key components of computer vision applications like satellite and remote sensing and medical diagnosis is multi-modal image fusion. There are various multi-modal image fusion techniques, and each has advantages and disadvantages of its own. This paper proposes a new method based on multi-scale guided filtering. Initially, each source image is divided into coarse and fine layers at various scales using a guided filter. In order to fuse coarse and fine layers, two different saliency maps are used: an energy saliency map to coarse layers and a modified spatial frequency energy saliency map to fine levels. According to the simulation results, the suggested technique performs better in terms of quantitative evaluations of quality than other state-of-the-art techniques. All the simulation results are carried on a standard brain atlas database.
Reference23 articles.
1. Anderson, C. H. (1988). Filter-Subtract-Decimate
Hierarchical Pyramid Signal Analyzing and Synthesizing
Technique, U.S. Patent No. 4,718,104. U.S. Patent and
Trademark Office, Washington, DC.
2. Medical image denoising using adaptive fusion of curvelet transform and total variation
3. Multimodal Medical Image Sensor Fusion Framework Using Cascade of Wavelet and Contourlet Transform Domains
4. Directive Contrast Based Multimodal Medical Image Fusion in NSCT Domain
5. Burt, P. J. (1992). A gradient pyramid basis for patternselective
image fusion. SID International, Symposium (pp.
467-470).