Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artif...Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.展开更多
This Letter presents a novel approach to enhance the fringe contrast（visibility） in a digital off-axis hologram digitally, which can save several adjustment procedures. In the approach, we train a pair of coupled di...This Letter presents a novel approach to enhance the fringe contrast（visibility） in a digital off-axis hologram digitally, which can save several adjustment procedures. In the approach, we train a pair of coupled dictionaries from a low fringe contrast hologram and a high one of the same specimen, use the dictionaries to sparse code the input hologram, and finally output a higher fringe contrast hologram. The sparse representation shows good adaptability on holograms. The experimental results demonstrate the benefit of low noise in a three-dimensional profile and prove the effectiveness of the approach.展开更多
文摘Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.
文摘This Letter presents a novel approach to enhance the fringe contrast（visibility） in a digital off-axis hologram digitally, which can save several adjustment procedures. In the approach, we train a pair of coupled dictionaries from a low fringe contrast hologram and a high one of the same specimen, use the dictionaries to sparse code the input hologram, and finally output a higher fringe contrast hologram. The sparse representation shows good adaptability on holograms. The experimental results demonstrate the benefit of low noise in a three-dimensional profile and prove the effectiveness of the approach.
