원문정보
초록
영어
This paper compares various defogging techniques such as Dark Channel Prior (DCP), Improved Dark Channel Prior (IDCP), IDCP with guided filter, IDCP with histogram specification, Tarel method, Anisotropic diffusion and Adaptive defogging in HSV color plane. For the purpose of comparison these techniques were implemented on MATLAB-09. The result shows that Adaptive defogging technique has highest value of PSNR among all the techniques having lowest MSE, NCD and MAE value. The computation time for removal of fog is found to follow the trend from low to high is: Anisotropic diffusion, Tarel method, DCP, IDCP, IDCP with guided filter, IDCP with histogram specification and Adaptive defogging.
목차
1. Introduction
2. Literature Survey of Defogging Strategies:
2.1. Removal of Fog by Polarization Filters:
2.2. Dark Channel Prior Technique
2.3. Improved Single Image Dehazing using Dark Channel Prior
2.4. Improved Haze Removal Algorithm using Dark Channel Prior (based on Guided Filter)
2.5. An Improved Single Image Haze Removal Algorithm Based on Dark Channel Prior and Histogram Specification
2.6. Adaptive Defogging Algorithm
2.7. Anisotropic Diffusion Algorithm
2.8. Tarel Method:
3. Simulation Setup Parameters
4. Performance Metrics:
4.1. Mean Square Error (MSE):
4.2. Peak Signal to Noise Ratio (PSNR):
4.3. Mean Absolute Error (MAE):
4.4. Normalized Colour Difference (NCD):
4.5. Computation Time:
4.6. Histogram:
5. Results
5.1. Snapshots of Image
5.2. Results of MAE
5.3. Results of MSE and PSNR
5.4. Results of NCD:
5.5. Results of Time Complexity:
6. Conclusion
References
