Pose and illumination invariant 2D to 3D facial recognition system

Ukil Yang, Hyoungchul Shin, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper proposes a pose and illumination invariant face recognition method based on a 2D to 3D facial recognition system which uses two dimensional (2D) image as an input and three dimensional (3D) data as a database. To improve the performance of a facial recognition system, we reorganize the framework of a conventional recognition system into more suitable framework for a 2D to 3D facial recognition system. 2D to 3D pose and illumination estimation algorithm is proposed based on a learning algorithm using multilayer perceptron (MLP). The proposed method estimates both pose and illumination factors of an input image in real-time, and compensates for a database in order to overcome the problems of pose and illumination without any occlusion occurred by insufficient information. To evaluate the performance, we performed both the accuracy tests of pose and illumination estimation and the recognition tests of 2D to 3D facial recognition system with a face database containing both two and three dimensional data.

Original languageEnglish
Title of host publication2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008
Pages2121-2126
Number of pages6
DOIs
Publication statusPublished - 2008 Sep 23
Event2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008 - Singapore, Singapore
Duration: 2008 Jun 32008 Jun 5

Publication series

Name2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008

Other

Other2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008
CountrySingapore
CitySingapore
Period08/6/308/6/5

Fingerprint

Lighting
Multilayer neural networks
Face recognition
Learning algorithms

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Yang, U., Shin, H., & Sohn, K. (2008). Pose and illumination invariant 2D to 3D facial recognition system. In 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008 (pp. 2121-2126). [4582894] (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008). https://doi.org/10.1109/ICIEA.2008.4582894
Yang, Ukil ; Shin, Hyoungchul ; Sohn, Kwanghoon. / Pose and illumination invariant 2D to 3D facial recognition system. 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008. 2008. pp. 2121-2126 (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008).
@inproceedings{955d11668af24f87a87d01579e51ef58,
title = "Pose and illumination invariant 2D to 3D facial recognition system",
abstract = "This paper proposes a pose and illumination invariant face recognition method based on a 2D to 3D facial recognition system which uses two dimensional (2D) image as an input and three dimensional (3D) data as a database. To improve the performance of a facial recognition system, we reorganize the framework of a conventional recognition system into more suitable framework for a 2D to 3D facial recognition system. 2D to 3D pose and illumination estimation algorithm is proposed based on a learning algorithm using multilayer perceptron (MLP). The proposed method estimates both pose and illumination factors of an input image in real-time, and compensates for a database in order to overcome the problems of pose and illumination without any occlusion occurred by insufficient information. To evaluate the performance, we performed both the accuracy tests of pose and illumination estimation and the recognition tests of 2D to 3D facial recognition system with a face database containing both two and three dimensional data.",
author = "Ukil Yang and Hyoungchul Shin and Kwanghoon Sohn",
year = "2008",
month = "9",
day = "23",
doi = "10.1109/ICIEA.2008.4582894",
language = "English",
isbn = "9781424417186",
series = "2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008",
pages = "2121--2126",
booktitle = "2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008",

}

Yang, U, Shin, H & Sohn, K 2008, Pose and illumination invariant 2D to 3D facial recognition system. in 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008., 4582894, 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008, pp. 2121-2126, 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008, Singapore, Singapore, 08/6/3. https://doi.org/10.1109/ICIEA.2008.4582894

Pose and illumination invariant 2D to 3D facial recognition system. / Yang, Ukil; Shin, Hyoungchul; Sohn, Kwanghoon.

2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008. 2008. p. 2121-2126 4582894 (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Pose and illumination invariant 2D to 3D facial recognition system

AU - Yang, Ukil

AU - Shin, Hyoungchul

AU - Sohn, Kwanghoon

PY - 2008/9/23

Y1 - 2008/9/23

N2 - This paper proposes a pose and illumination invariant face recognition method based on a 2D to 3D facial recognition system which uses two dimensional (2D) image as an input and three dimensional (3D) data as a database. To improve the performance of a facial recognition system, we reorganize the framework of a conventional recognition system into more suitable framework for a 2D to 3D facial recognition system. 2D to 3D pose and illumination estimation algorithm is proposed based on a learning algorithm using multilayer perceptron (MLP). The proposed method estimates both pose and illumination factors of an input image in real-time, and compensates for a database in order to overcome the problems of pose and illumination without any occlusion occurred by insufficient information. To evaluate the performance, we performed both the accuracy tests of pose and illumination estimation and the recognition tests of 2D to 3D facial recognition system with a face database containing both two and three dimensional data.

AB - This paper proposes a pose and illumination invariant face recognition method based on a 2D to 3D facial recognition system which uses two dimensional (2D) image as an input and three dimensional (3D) data as a database. To improve the performance of a facial recognition system, we reorganize the framework of a conventional recognition system into more suitable framework for a 2D to 3D facial recognition system. 2D to 3D pose and illumination estimation algorithm is proposed based on a learning algorithm using multilayer perceptron (MLP). The proposed method estimates both pose and illumination factors of an input image in real-time, and compensates for a database in order to overcome the problems of pose and illumination without any occlusion occurred by insufficient information. To evaluate the performance, we performed both the accuracy tests of pose and illumination estimation and the recognition tests of 2D to 3D facial recognition system with a face database containing both two and three dimensional data.

UR - http://www.scopus.com/inward/record.url?scp=51949100775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51949100775&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2008.4582894

DO - 10.1109/ICIEA.2008.4582894

M3 - Conference contribution

SN - 9781424417186

T3 - 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008

SP - 2121

EP - 2126

BT - 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008

ER -

Yang U, Shin H, Sohn K. Pose and illumination invariant 2D to 3D facial recognition system. In 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008. 2008. p. 2121-2126. 4582894. (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008). https://doi.org/10.1109/ICIEA.2008.4582894