An example-based face hallucination method for single-frame, low-resolution facial images

Jeong Seon Park; Seong Whan Lee

doi:10.1109/TIP.2008.2001394

An example-based face hallucination method for single-frame, low-resolution facial images

Jeong Seon Park, Seong Whan Lee

Research output: Contribution to journal › Article › peer-review

138 Citations (Scopus)

Abstract

This paper proposes a face hallucination method for the reconstruction of high-resolution facial images from single-frame, low-resolution facial images. The proposed method has been derived from example-based hallucination methods and morphable face models. First, we propose a recursive error back-projection method to compensate for residual errors, and a region-based reconstruction method to preserve characteristics of local facial regions. Then, we define an extended morphable face model, in which an extended face is composed of the interpolated high-resolution face from a given low-resolution face, and its original high-resolution equivalent. Then, the extended face is separated into an extended shape and an extended texture. We performed various hallucination experiments using the MPI, XM2VTS, and KF databases, compared the reconstruction errors, structural similarity index, and recognition rates, and showed the effects of face detection errors and shape estimation errors. The encouraging results demonstrate that the proposed methods can improve the performance of face recognition systems. Especially the proposed method can enhance the resolution of single-frame, low-resolution facial images.

Original language	English
Pages (from-to)	1806-1816
Number of pages	11
Journal	IEEE Transactions on Image Processing
Volume	17
Issue number	10
DOIs	https://doi.org/10.1109/TIP.2008.2001394
Publication status	Published - 2008

Bibliographical note

Funding Information:
Manuscript received May 4, 2007; revised May 1, 2008. Current version published September 10, 2008. This work was supported by the Ministry of Knowledge Economy, Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2008-C1090-0801-0001) and the Intelligent Robotics Development Program, one of the 21st Century Frontier R&D Programs funded by the Ministry of Commerce, Industry and Energy of Korea. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Dimitri Van De Ville.

Keywords

Error back-projection
Example-based reconstruction
Extended morphable face model
Face hallucination
Face recognition
Region-based reconstruction

ASJC Scopus subject areas

Software
Computer Graphics and Computer-Aided Design

Access to Document

10.1109/TIP.2008.2001394

Cite this

@article{014e314bb5004a25ba211cf184587460,

title = "An example-based face hallucination method for single-frame, low-resolution facial images",

abstract = "This paper proposes a face hallucination method for the reconstruction of high-resolution facial images from single-frame, low-resolution facial images. The proposed method has been derived from example-based hallucination methods and morphable face models. First, we propose a recursive error back-projection method to compensate for residual errors, and a region-based reconstruction method to preserve characteristics of local facial regions. Then, we define an extended morphable face model, in which an extended face is composed of the interpolated high-resolution face from a given low-resolution face, and its original high-resolution equivalent. Then, the extended face is separated into an extended shape and an extended texture. We performed various hallucination experiments using the MPI, XM2VTS, and KF databases, compared the reconstruction errors, structural similarity index, and recognition rates, and showed the effects of face detection errors and shape estimation errors. The encouraging results demonstrate that the proposed methods can improve the performance of face recognition systems. Especially the proposed method can enhance the resolution of single-frame, low-resolution facial images.",

keywords = "Error back-projection, Example-based reconstruction, Extended morphable face model, Face hallucination, Face recognition, Region-based reconstruction",

author = "Park, {Jeong Seon} and Lee, {Seong Whan}",

note = "Funding Information: Manuscript received May 4, 2007; revised May 1, 2008. Current version published September 10, 2008. This work was supported by the Ministry of Knowledge Economy, Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2008-C1090-0801-0001) and the Intelligent Robotics Development Program, one of the 21st Century Frontier R&D Programs funded by the Ministry of Commerce, Industry and Energy of Korea. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Dimitri Van De Ville.",

year = "2008",

doi = "10.1109/TIP.2008.2001394",

language = "English",

volume = "17",

pages = "1806--1816",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - An example-based face hallucination method for single-frame, low-resolution facial images

AU - Park, Jeong Seon

AU - Lee, Seong Whan

N1 - Funding Information: Manuscript received May 4, 2007; revised May 1, 2008. Current version published September 10, 2008. This work was supported by the Ministry of Knowledge Economy, Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2008-C1090-0801-0001) and the Intelligent Robotics Development Program, one of the 21st Century Frontier R&D Programs funded by the Ministry of Commerce, Industry and Energy of Korea. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Dimitri Van De Ville.

PY - 2008

Y1 - 2008

N2 - This paper proposes a face hallucination method for the reconstruction of high-resolution facial images from single-frame, low-resolution facial images. The proposed method has been derived from example-based hallucination methods and morphable face models. First, we propose a recursive error back-projection method to compensate for residual errors, and a region-based reconstruction method to preserve characteristics of local facial regions. Then, we define an extended morphable face model, in which an extended face is composed of the interpolated high-resolution face from a given low-resolution face, and its original high-resolution equivalent. Then, the extended face is separated into an extended shape and an extended texture. We performed various hallucination experiments using the MPI, XM2VTS, and KF databases, compared the reconstruction errors, structural similarity index, and recognition rates, and showed the effects of face detection errors and shape estimation errors. The encouraging results demonstrate that the proposed methods can improve the performance of face recognition systems. Especially the proposed method can enhance the resolution of single-frame, low-resolution facial images.

AB - This paper proposes a face hallucination method for the reconstruction of high-resolution facial images from single-frame, low-resolution facial images. The proposed method has been derived from example-based hallucination methods and morphable face models. First, we propose a recursive error back-projection method to compensate for residual errors, and a region-based reconstruction method to preserve characteristics of local facial regions. Then, we define an extended morphable face model, in which an extended face is composed of the interpolated high-resolution face from a given low-resolution face, and its original high-resolution equivalent. Then, the extended face is separated into an extended shape and an extended texture. We performed various hallucination experiments using the MPI, XM2VTS, and KF databases, compared the reconstruction errors, structural similarity index, and recognition rates, and showed the effects of face detection errors and shape estimation errors. The encouraging results demonstrate that the proposed methods can improve the performance of face recognition systems. Especially the proposed method can enhance the resolution of single-frame, low-resolution facial images.

KW - Error back-projection

KW - Example-based reconstruction

KW - Extended morphable face model

KW - Face hallucination

KW - Face recognition

KW - Region-based reconstruction

UR - http://www.scopus.com/inward/record.url?scp=52549116762&partnerID=8YFLogxK

U2 - 10.1109/TIP.2008.2001394

DO - 10.1109/TIP.2008.2001394

M3 - Article

C2 - 18784029

AN - SCOPUS:52549116762

SN - 1057-7149

VL - 17

SP - 1806

EP - 1816

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

IS - 10

ER -

An example-based face hallucination method for single-frame, low-resolution facial images

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this