Reconstruction of high-resolution facial images for visual surveillance

Jeong Seon Park, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

In this chapter we provide a summary of our previous works concerning the reconstruction of high-resolution facial images for visual surveillance. Specifically we present our methods of reconstructing high-resolution facial image from a low-resolution facial image based on example-based learning and iterative error back-projection. In our method, a face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. Moreover iterative error back-projection is applied to improve the result of high-resolution reconstruction. The encouraging results of our methods show that our high-resolution reconstruction methods can be used to improve the performance of the face recognition by enhancing the resolution of low-resolution facial images captured in visual surveillance systems.

Original languageEnglish
Title of host publicationHandbook of Pattern Recognition and Computer Vision, 3rd Edition
PublisherWorld Scientific Publishing Co.
Pages445-460
Number of pages16
ISBN (Electronic)9789812775320
ISBN (Print)9812561056, 9789812561053
DOIs
Publication statusPublished - 2005 Jan 1

Fingerprint

Textures
Face recognition
Pixels

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Park, J. S., & Lee, S. W. (2005). Reconstruction of high-resolution facial images for visual surveillance. In Handbook of Pattern Recognition and Computer Vision, 3rd Edition (pp. 445-460). World Scientific Publishing Co.. https://doi.org/10.1142/9789812775320_0024

Reconstruction of high-resolution facial images for visual surveillance. / Park, Jeong Seon; Lee, Seong Whan.

Handbook of Pattern Recognition and Computer Vision, 3rd Edition. World Scientific Publishing Co., 2005. p. 445-460.

Research output: Chapter in Book/Report/Conference proceedingChapter

Park, JS & Lee, SW 2005, Reconstruction of high-resolution facial images for visual surveillance. in Handbook of Pattern Recognition and Computer Vision, 3rd Edition. World Scientific Publishing Co., pp. 445-460. https://doi.org/10.1142/9789812775320_0024
Park JS, Lee SW. Reconstruction of high-resolution facial images for visual surveillance. In Handbook of Pattern Recognition and Computer Vision, 3rd Edition. World Scientific Publishing Co. 2005. p. 445-460 https://doi.org/10.1142/9789812775320_0024
Park, Jeong Seon ; Lee, Seong Whan. / Reconstruction of high-resolution facial images for visual surveillance. Handbook of Pattern Recognition and Computer Vision, 3rd Edition. World Scientific Publishing Co., 2005. pp. 445-460
@inbook{a7976c3a5d6c4bc4aed4ad80637a41e0,
title = "Reconstruction of high-resolution facial images for visual surveillance",
abstract = "In this chapter we provide a summary of our previous works concerning the reconstruction of high-resolution facial images for visual surveillance. Specifically we present our methods of reconstructing high-resolution facial image from a low-resolution facial image based on example-based learning and iterative error back-projection. In our method, a face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. Moreover iterative error back-projection is applied to improve the result of high-resolution reconstruction. The encouraging results of our methods show that our high-resolution reconstruction methods can be used to improve the performance of the face recognition by enhancing the resolution of low-resolution facial images captured in visual surveillance systems.",
author = "Park, {Jeong Seon} and Lee, {Seong Whan}",
year = "2005",
month = "1",
day = "1",
doi = "10.1142/9789812775320_0024",
language = "English",
isbn = "9812561056",
pages = "445--460",
booktitle = "Handbook of Pattern Recognition and Computer Vision, 3rd Edition",
publisher = "World Scientific Publishing Co.",

}

TY - CHAP

T1 - Reconstruction of high-resolution facial images for visual surveillance

AU - Park, Jeong Seon

AU - Lee, Seong Whan

PY - 2005/1/1

Y1 - 2005/1/1

N2 - In this chapter we provide a summary of our previous works concerning the reconstruction of high-resolution facial images for visual surveillance. Specifically we present our methods of reconstructing high-resolution facial image from a low-resolution facial image based on example-based learning and iterative error back-projection. In our method, a face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. Moreover iterative error back-projection is applied to improve the result of high-resolution reconstruction. The encouraging results of our methods show that our high-resolution reconstruction methods can be used to improve the performance of the face recognition by enhancing the resolution of low-resolution facial images captured in visual surveillance systems.

AB - In this chapter we provide a summary of our previous works concerning the reconstruction of high-resolution facial images for visual surveillance. Specifically we present our methods of reconstructing high-resolution facial image from a low-resolution facial image based on example-based learning and iterative error back-projection. In our method, a face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. Moreover iterative error back-projection is applied to improve the result of high-resolution reconstruction. The encouraging results of our methods show that our high-resolution reconstruction methods can be used to improve the performance of the face recognition by enhancing the resolution of low-resolution facial images captured in visual surveillance systems.

UR - http://www.scopus.com/inward/record.url?scp=84968862669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84968862669&partnerID=8YFLogxK

U2 - 10.1142/9789812775320_0024

DO - 10.1142/9789812775320_0024

M3 - Chapter

AN - SCOPUS:84968862669

SN - 9812561056

SN - 9789812561053

SP - 445

EP - 460

BT - Handbook of Pattern Recognition and Computer Vision, 3rd Edition

PB - World Scientific Publishing Co.

ER -