| Paper Details: | Downloads: 2063 |
| Serial Number: | P1151605465
|
| Title: | Image Fusion using HVS in Discrete Wavelet Transform domain
|
| Authors: | Radhika Vadhi and K.Veera Veeraswamy and S. Srinivas Kumar,
|
| Abstract: | The aim of image fusion is to generate high-quality images using the information collected from the source images. The fused image contains more information than any of its source images. Image fusion using transform method is more efficient than spatial method. The characteristics of the Human visual system (HVS) are explored in the discrete wavelet transform (DWT) domain. In this paper, we have used HVS weightage matrix in the transform domain to select appropriate information from multiple images to obtain a fused image. Two steps are involved to obtain high quality fused image. The first step involves the application of the DWT to the source images. The second step is to identify the important sub bands using the HVS weights. Hence, the perceptual important information is selected from different source images to form the fused image. Finally, qualitative and quantitative information is considered for image fusion. This technique is more useful for the images processed by using JPEG2000 technique. It is time saving and simpler when the fused image desires to be saved or transmitted in JPEG2000 format. The proposed algorithm is assessed by mutual information (MI), edge strength and orientation preservation (ESOP), feature similarity (FSIM) index, and normalized cross correlation (NCC). The experimental results establish the superiority of our proposed method over other state-of-the-art techniques for image fusion.
|
| Keywords: | Human Visual System, Contrast Sensitivity Function, Discrete Wavelet Transform, Image Fusion.
|
| Journal/Conference: | International Journal of Graphics, Vision and Image Processing
|
| Volume: | 16
|
| Issue: | 2
|
| Submission Date: | 1/26/2016 12:00:00 AM
|
| Review Date: | 2/21/2016 12:00:00 AM
|
| Publishing Date: | 3/21/2016 12:00:00 AM
|
| Article Downloads: | 2063
|
| Download: |
|