Learning-based super-resolution system using single facial image and multi-resolution wavelet synthesis

Authors:
Shu-Fan Lui;Jin-Yi Wu;Hsi-Shu Mao;Jenn-Jier James Lien
Affiliations:
Robotics Laboratory, Dept. of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan;Robotics Laboratory, Dept. of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan;Robotics Laboratory, Dept. of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan;Robotics Laboratory, Dept. of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan
Venue:
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Year:
2007

Citing 9
Cited 1

Improved resolution from subpixel shifted pictures

CVGIP: Graphical Models and Image Processing
Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Example-Based Super-Resolution

IEEE Computer Graphics and Applications
Limits on Super-Resolution and How to Break Them

IEEE Transactions on Pattern Analysis and Machine Intelligence
Wavelet Algorithms for High-Resolution Image Reconstruction

SIAM Journal on Scientific Computing
Hallucinating Faces

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Least Squares Image Restoration Using Spline Basis Functions

IEEE Transactions on Computers
Extraction of high-resolution frames from video sequences

IEEE Transactions on Image Processing
Fast and robust multiframe super resolution

IEEE Transactions on Image Processing

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

A learning-based super-resolution system consisting of training and synthesis processes is presented. In the proposed system, a multiresolution wavelet approach is applied to carry out the robust synthesis of both the global geometric structure and the local high-frequency detailed features of a facial image. In the training process, the input image is transformed into a series of images of increasingly lower resolution using the Haar discrete wavelet transform (DWT). The images at each resolution level are divided into patches, which are then projected onto an eigenspace to derive the corresponding projection weight vectors. In the synthesis process, a low-resolution input image is divided into patches, which are then projected onto the same eigenspace as that used in the training process. Modeling the resulting projection weight vectors as a Markov network, the maximum a posteriori (MAP) estimation approach is then applied to identity the best-matching patches with which to reconstruct the image at a higher level of resolution. The experimental results demonstrate that the proposed reconstruction system yields better results than the bi-cubic spline interpolation method.