RGB-NIR image fusion
Image processing techniques, such as linear filters and non-linear filters were studied and gaussian filter was used. Various Convolutional Neural Networks variants were also introduced and evaluated based on their ability in feature extraction. A pre-trained VGG-19 network using ImageNet weig...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2021
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/148972 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Image processing techniques, such as linear filters and non-linear filters were studied and
gaussian filter was used. Various Convolutional Neural Networks variants were also
introduced and evaluated based on their ability in feature extraction. A pre-trained
VGG-19 network using ImageNet weights was chosen for this project. Past Image Fusion
methods were also studied. A fusion strategy was then proposed. Lastly, the proposed
solution was evaluated against other image fusion methods using several quality metrics,
where the proposed solution showed positive results on par with more recent methods
such as DenseFuse and IFCNN |
|---|