Stepwise reconstruction of high-resolution facial image based on interpolated morphable face model

Authors:
Jeong-Seon Park;Seong-Whan Lee
Affiliations:
Center for Artificial Vision Research, Department of Computer Science and Engineering, Korea University, Seoul, Korea;Center for Artificial Vision Research, Department of Computer Science and Engineering, Korea University, Seoul, Korea
Venue:
AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication
Year:
2005

Citing 7
Cited 1

Limits on Super-Resolution and How to Break Them

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstruction of Partially Damaged Face Images Based on a Morphable Face Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Example Based Image Analysis and Synthesis

Example Based Image Analysis and Synthesis
Face Recognition Based on Fitting a 3D Morphable Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Resolution enhancement of facial image using an error back-projection of example-based learning

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Fast impulsive noise removal

IEEE Transactions on Image Processing
Resolution enhancement of monochrome and color video using motion compensation

IEEE Transactions on Image Processing

Rapid and Brief communication: Low resolution face recognition based on support vector data description

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new method for reconstructing a high-resolution facial image from a low-resolution facial image using stepwise reconstruction based on the interpolated morphable face model. First, we defined an interpolated morphable face model that an interpolated face is composed of a low-resolution face, its interpolated high-resolution face from a low-resolution one, and its original high-resolution one. We also proposed a stepwise reconstruction method for preventing over reconstruction caused by direct reconstruction of a high-resolution image from a low-resolution facial image. The encouraging results show that our proposed method can be used to improve the performance of face recognition systems, specifically in resolution enhancement of facial images captured on visual surveillance systems.