Abstract:
GIF’s local property causes halo artifacts near edges. Recently, a weighted guided image filter (WGIF) with edge-aware weighting was proposed to compensate. Local and global operations improve edge-preserving performance.
These guided filters neglect edge direction, a crucial guidance image property. We propose a new GIF that better leverages edge direction to overcome the drawback. In particular, we use the steering kernel to adaptively learn the direction and use the learning results to improve the filter.
The proposed method preserves edges and reduces halo artifacts. Extensive edge-aware smoothing, detail enhancement, denoising, and dehazing experiments yield similar results.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
