Journal
IET IMAGE PROCESSING
Volume 7, Issue 6, Pages 624-632Publisher
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-ipr.2012.0554
Keywords
face recognition; image representation; image resolution; effective two-step method; face hallucination; sparse compensation; over-complete patches; sparse representation; high-resolution training face images; low-resolution training face images; optimal coefflcients; global face image; interpolated training images; high-resolution residual image; local face image; over-complete patch dictionary; sparse representation; residual compensation strategy; balance sparsity parameter; residual compensation; two-step face hallucination methods
Categories
Funding
- National Natural Science Foundation of China [61273273, 61271374]
- Beijing Natural Science Foundation [4112050]
- Research Fund for the Doctoral Program of Higher Education of China [20121101110034]
Ask authors/readers for more resources
Sparse representation has been successfully applied to image d using low- and high-resolution training face images based on sparse representation. In this study, the sparse residual compensation is adopted to face hallucination. Firstly, a global face image is constructed by optimal coefficients of the interpolated training images. Secondly, the high-resolution residual image (local face image) is found by using an over-complete patch dictionary and the sparse representation. Finally, a hallucinated face image is obtained by combining these two steps. In addition, the more details of the face image in high frequency parts are recovered using a residual compensation strategy. In the authors' experimental work, it is observed that balance sparsity parameter () has affected the residual compensation. Further, the proposed algorithm can acquire a high-resolution image even though the number of training image pairs is comparatively smaller. The experiments show that the authors' method is more effective than the other existing two-step face hallucination methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available