Wavelet-based eigentransformation for face super-resolution

Authors:
Hui Zhuo;Kin-Man Lam
Affiliations:
Centre for Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong;Centre for Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
Venue:
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
Year:
2010

Citing 4
Cited 2

Example-Based Super-Resolution

IEEE Computer Graphics and Applications
Example-based image super-resolution with class-specific predictors

Journal of Visual Communication and Image Representation
Approximation power of biorthogonal wavelet expansions

IEEE Transactions on Signal Processing
Hallucinating face by eigentransformation

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Eigentransformation-based face super-resolution in the wavelet domain

Pattern Recognition Letters
Human face super-resolution based on NSCT

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a new approach to human face hallucination based on eigentransformation. In our algorithm, a face image is decomposed into different frequency bands using wavelet transform, so that different approaches can be applied to the low-frequency and high-frequency contents for increasing the resolution. The interpolated LR images are decomposed by the forward wavelet transform, whereby the low-frequency content is simply interpolated, while the wavelet coefficients of the three highfrequency bands are used to estimate the corresponding ones of the HR image by using eigentransformation. The approximation coefficients are reconstructed directly based on the content of the interpolated LR image. The reconstructed image can be synthesized by the inverse wavelet transform with all the estimated coefficients.