Image fusion algorithm based on gradient similarity filter
| Autor: | Mao Linghua, Zhao Yufei, Fu Zhizhong, Xu Jin |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Fusion
Image fusion Computer science business.industry Pattern recognition 02 engineering and technology Filter (signal processing) 01 natural sciences 010309 optics Amplitude Robustness (computer science) Computer Science::Computer Vision and Pattern Recognition 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Medical imaging 020201 artificial intelligence & image processing Vector field Artificial intelligence business Image gradient |
| Zdroj: | APSIPA |
| DOI: | 10.1109/apsipa.2017.8282037 |
| Popis: | The gradient based image fusion methods are one kind of state-of-the-art image fusion methods. However, the existing gradient based image methods suffer from various problems such as inaccuracy of the fused image gradient direction, low amplitude of fused gradient and low robustness of fusion weight. To address such issues, we propose an improved gradient based image fusion method which makes use of the similarity of the image gradient to improve the accuracy of both the direction and amplitude of the fused gradient. Specifically, an image gradient similarity metric is first defined. Then, the gradient field of the fused image is filtered according to the neighborhood similarity of the gradient field. Subsequently, the fused image can be obtained based on the filtered gradient field. The experimental results show that compared to both the existing gradient based and the decomposition based methods, the proposed method can significantly improve both the objective and subjective performance of the fused images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|