Single image dehazing using non-symmetry and anti-packing model based decomposition and contextual regularization
| Autor: | Zhenfeng Xie, Yunping Zheng, Changting Cai |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Context model
Computer science business.industry 0202 electrical engineering electronic engineering information engineering 020206 networking & telecommunications 020201 artificial intelligence & image processing Computer vision 02 engineering and technology Artificial intelligence Single image business Regularization (mathematics) Visualization |
| Zdroj: | ICNC-FSKD |
| Popis: | As the need of people pursuing the good quality of photos is growing faster in these days, there are lots of effects which have been done to improve the visual of the picture taken in bad weather, such as the fog. In this paper, a scheme of improved single image dehazing based on NAM (Non-symmetry and Anti-packing Model)-based decomposition and contextual regularization is proposed. Firstly, we introduced the basic idea of the Non-symmetry and Anti-packing Model. And then the foggy image is decomposed using NAM for the dehazing process. Finally, the boundary constraint and contextual regularization are used for the scene transmission. The experimental results presented in this paper showed the improvement of the dehazing effect by our proposed method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|