Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation
Existing infrared (IR)-visible (VIS) image fusion algorithms demand source images with the same resolution levels. However, IR images are always available with poor resolution due to hardware limitations and environmental conditions. In this correspondence, we develop a novel image fusion model that...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/18/3389 |
| _version_ | 1827659132374614016 |
|---|---|
| author | Gunnam Suryanarayana Vijayakumar Varadarajan Siva Ramakrishna Pillutla Grande Nagajyothi Ghamya Kotapati |
| author_facet | Gunnam Suryanarayana Vijayakumar Varadarajan Siva Ramakrishna Pillutla Grande Nagajyothi Ghamya Kotapati |
| author_sort | Gunnam Suryanarayana |
| collection | DOAJ |
| description | Existing infrared (IR)-visible (VIS) image fusion algorithms demand source images with the same resolution levels. However, IR images are always available with poor resolution due to hardware limitations and environmental conditions. In this correspondence, we develop a novel image fusion model that brings resolution consistency between IR-VIS source images and generates an accurate high-resolution fused image. We train a single deep convolutional neural network model by considering true degradations in real time and reconstruct IR images. The trained multiple degradation skilled network (MDSNet) increases the prominence of objects in fused images from the IR source image. In addition, we adopt multi-resolution singular value decomposition (MRSVD) to capture maximum information from source images and update IR image coefficients with that of VIS images at the finest level. This ensures uniform contrast along with clear textural information in our results. Experiments demonstrate the efficiency of the proposed method over nine state-of-the-art methods using five image quality assessment metrics. |
| first_indexed | 2024-03-09T23:14:19Z |
| format | Article |
| id | doaj.art-0d489879f4e64e0bb0d0556b753280ed |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T23:14:19Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-0d489879f4e64e0bb0d0556b753280ed2023-11-23T17:37:55ZengMDPI AGMathematics2227-73902022-09-011018338910.3390/math10183389Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD UpdationGunnam Suryanarayana0Vijayakumar Varadarajan1Siva Ramakrishna Pillutla2Grande Nagajyothi3Ghamya Kotapati4Department of Electronics and Communications, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada 520007, IndiaDepartment of Computer Science Engineering, The University of New South Wales, Sydney, NSW 2052, AustraliaSchool of Electronics Engineering, VIT-AP University, Amaravati 522237, IndiaDepartment of Electronics and Communications, Golden Valley Integrated Campus, Madanapalli 517325, IndiaDepartment of Computer Science Engineering, Sree Vidyanikethan Engineering College, Tirupati 517102, IndiaExisting infrared (IR)-visible (VIS) image fusion algorithms demand source images with the same resolution levels. However, IR images are always available with poor resolution due to hardware limitations and environmental conditions. In this correspondence, we develop a novel image fusion model that brings resolution consistency between IR-VIS source images and generates an accurate high-resolution fused image. We train a single deep convolutional neural network model by considering true degradations in real time and reconstruct IR images. The trained multiple degradation skilled network (MDSNet) increases the prominence of objects in fused images from the IR source image. In addition, we adopt multi-resolution singular value decomposition (MRSVD) to capture maximum information from source images and update IR image coefficients with that of VIS images at the finest level. This ensures uniform contrast along with clear textural information in our results. Experiments demonstrate the efficiency of the proposed method over nine state-of-the-art methods using five image quality assessment metrics.https://www.mdpi.com/2227-7390/10/18/3389multiple degradation modeldeep networksimage fusionmulti-resolution singular value decomposition |
| spellingShingle | Gunnam Suryanarayana Vijayakumar Varadarajan Siva Ramakrishna Pillutla Grande Nagajyothi Ghamya Kotapati Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation Mathematics multiple degradation model deep networks image fusion multi-resolution singular value decomposition |
| title | Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation |
| title_full | Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation |
| title_fullStr | Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation |
| title_full_unstemmed | Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation |
| title_short | Multiple Degradation Skilled Network for Infrared and Visible Image Fusion Based on Multi-Resolution SVD Updation |
| title_sort | multiple degradation skilled network for infrared and visible image fusion based on multi resolution svd updation |
| topic | multiple degradation model deep networks image fusion multi-resolution singular value decomposition |
| url | https://www.mdpi.com/2227-7390/10/18/3389 |
| work_keys_str_mv | AT gunnamsuryanarayana multipledegradationskillednetworkforinfraredandvisibleimagefusionbasedonmultiresolutionsvdupdation AT vijayakumarvaradarajan multipledegradationskillednetworkforinfraredandvisibleimagefusionbasedonmultiresolutionsvdupdation AT sivaramakrishnapillutla multipledegradationskillednetworkforinfraredandvisibleimagefusionbasedonmultiresolutionsvdupdation AT grandenagajyothi multipledegradationskillednetworkforinfraredandvisibleimagefusionbasedonmultiresolutionsvdupdation AT ghamyakotapati multipledegradationskillednetworkforinfraredandvisibleimagefusionbasedonmultiresolutionsvdupdation |