Name
Abstract | ||
|---|---|---|
Sparse representation-based face hallucination approaches proposed so far use fixed ℓ1 norm penalty to capture the sparse nature of face images, and thus hardly adapt readily to the statistical variability of underlying images. Additionally, they ignore the influence of spatial distances between the test image and training basis images on optimal reconstruction coefficients. Consequently, they cannot offer a satisfactory performance in practical face hallucination applications. In this paper, we propose a weighted adaptive sparse regularization (WASR) method to promote accuracy, stability and robustness for face hallucination reconstruction, in which a distance-inducing weighted ℓq norm penalty is imposed on the solution. With the adjustment to shrinkage parameter q , the weighted ℓq penalty function enables elastic description ability in the sparse domain, leading to more conservative sparsity in an ascending order of q . In particular, WASR with an optimal q > 1 can reasonably represent the less sparse nature of noisy images and thus remarkably boosts noise robust performance in face hallucination. Various experimental results on standard face database as well as real-world images show that our proposed method outperforms state-of-the-art methods in terms of both objective metrics and visual quality. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TCSVT.2013.2290574 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
face recognition,ℓq norm,adaptive sparse regularization,sparse representation-based face hallucination,test image,weighted penalty,sparse domain,noisy images,reconstruction coefficients,super-resolution,$ell_{q}$ norm,image reconstruction,compressed sensing,weighted adaptive sparse regularization,training basis images,face images,face hallucination,dictionaries,super resolution,noise,face,image resolution,noise measurement | Iterative reconstruction,Computer vision,Facial recognition system,Face hallucination,Pattern recognition,Computer science,Sparse approximation,Robustness (computer science),Artificial intelligence,Standard test image,Compressed sensing,Penalty method | Journal |
Volume | Issue | ISSN |
24 | 5 | 1051-8215 |
Citations | PageRank | References |
32 | 0.81 | 15 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hongqiang Wang | 1 | 313 | 40.65 |
| Ruimin Hu | 2 | 961 | 117.18 |
| Shi-Zheng Wang | 3 | 77 | 8.39 |
| Junjun Jiang | 4 | 1138 | 74.49 |