IR and VI Fusion using Hybrid VSM and Swarm Optimization
Vijayakumar. R1, Karthikeyan. K2
1Vijayakumar. R, Research scholar, Dr. SNS Rajalakshmi college of Arts and Science, Coimbatore ,Tamilnadu, India.
2Dr. Karthikeyan. K, Assistant Professor & Head2 Government Arts and Science College, Palladam, Tamilnadu, India.
Manuscript received on September 22, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 2414-2421 | Volume-9 Issue-1, October 2019 | Retrieval Number: F8238088619/2019©BEIESP | DOI: 10.35940/ijeat.F8238.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the current era, usage of Infrared (IR) sensors, in the real world has been increased because of decrease in their cost. Many recent applications of IR images are included in the field of defence, medicine, astronomy, meteorology, industry and science. One of the main applications in the field of defence is person detection. However, IR images have unique challenges. Image fusion based on DWT superior things because it is a multiresolution approach, it allows picture disintegration in various parameters and provides directional information. Most of the existing methods used two or three different quality measures to measure the performance of the fused system. The present study used the ten quality metrics on all derived approaches and noted down various qualitative conclusions. Proposed system the base layers obtained and Further the proposed work found that, the methods based on wavelet transforms have compactness, directional selectivity and orthogonality. Due to these, DWT based fusion methods are used in literature when compared to pyramid decomposition based fusion methods.
Keywords: Visual Saliency Map, chicken swarm optimization, Multi-scale decomposition (MSD), Rolling-guidance-filter (RGF), fingerprint_iris, multi-biometric system, , match_level fusion.