Enhanced facial texture illumination normalization for face recognition

Yong Luo; Ye-Peng Guan

doi:10.1364/AO.54.006887

Applied Optics
Vol. 54,
Issue 22,
pp. 6887-6894
(2015)
•https://doi.org/10.1364/AO.54.006887

Enhanced facial texture illumination normalization for face recognition

Yong Luo and Ye-Peng Guan

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Yong Luo and Ye-Peng Guan, "Enhanced facial texture illumination normalization for face recognition," Appl. Opt. 54, 6887-6894 (2015)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Related Topics
Table of Contents Category
- Machine Vision
Optics & Photonics Topics
?

The topics in this list come from the Optics and Photonics Topics applied to this article.

About this Article
History
- Original Manuscript: March 12, 2015
- Revised Manuscript: May 31, 2015
- Manuscript Accepted: June 23, 2015
- Published: July 30, 2015
Virtual Issues
Virtual Journal for Biomedical Optics Vol. 10, Iss. 8

Abstract

An uncontrolled lighting condition is one of the most critical challenges for practical face recognition applications. An enhanced facial texture illumination normalization method is put forward to resolve this challenge. An adaptive relighting algorithm is developed to improve the brightness uniformity of face images. Facial texture is extracted by using an illumination estimation difference algorithm. An anisotropic histogram-stretching algorithm is proposed to minimize the intraclass distance of facial skin and maximize the dynamic range of facial texture distribution. Compared with the existing methods, the proposed method can more effectively eliminate the redundant information of facial skin and illumination. Extensive experiments show that the proposed method has superior performance in normalizing illumination variation and enhancing facial texture features for illumination-insensitive face recognition.

Full Article | PDF Article

More Like This

Thermal-to-visible face recognition using partial least squares

Shuowen Hu, Jonghyun Choi, Alex L. Chan, and William Robson Schwartz
J. Opt. Soc. Am. A 32(3) 431-442 (2015)

A de-illumination scheme for face recognition based on fast decomposition and detail feature fusion

Yi Zhou, Sheng-Tong Zhou, Zuo-Yang Zhong, and Hong-Guang Li
Opt. Express 21(9) 11294-11308 (2013)

Illumination invariant recognition and 3D reconstruction of faces using desktop optics

Ajmal Mian
Opt. Express 19(8) 7491-7506 (2011)

Previous Article Next Article

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (9)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (4)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (10)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

	PCA	LDA	KFA	GLDA	eLBPH	MMSEC
Original	$8.99 \pm 3.93$	$26.42 \pm 11.04$	$21.51 \pm 8.55$	$38.76 \pm 16.84$	$47.39 \pm 9.69$	$27.21 \pm 10.89$
HWIN	$67.65 \pm 7.62$	$82.79 \pm 11.78$	$78.65 \pm 10.36$	$89.81 \pm 14.42$	$71.11 \pm 7.88$	$86.71 \pm 6.70$
GRF	$66.86 \pm 14.34$	$81.38 \pm 12.36$	$79.96 \pm 9.88$	$89.16 \pm 10.55$	$76.05 \pm 8.43$	$77.61 \pm 12.68$
RET	$88.89 \pm 4.93$	$93.08 \pm 2.56$	$92.57 \pm 2.58$	$93.69 \pm 8.47$	$79.96 \pm 6.33$	$93.05 \pm 3.44$
SQI	$68.54 \pm 14.01$	$88.94 \pm 7.07$	$84.71 \pm 10.03$	$89.34 \pm 10.86$	$79.87 \pm 12.67$	$91.15 \pm 4.34$
TT	$73.47 \pm 6.30$	$91.42 \pm 2.89$	$84.93 \pm 4.17$	$91.77 \pm 10.14$	$81.86 \pm 4.80$	$90.67 \pm 3.84$
wGWF	$73.57 \pm 13.09$	$91.63 \pm 5.22$	$83.42 \pm 10.56$	$92.47 \pm 10.06$	$82.37 \pm 5.21$	$88.52 \pm 6.93$
Proposed	$92.65 \pm 2.68$	$95.87 \pm 1.23$	$94.33 \pm 1.52$	$96.65 \pm 5.88$	$82.61 \pm 6.02$	$96.50 \pm 1.24$

	PCA	LDA	KFA	GLDA	eLBPH	MMSEC
Original	$22.79 \pm 3.43$	$68.42 \pm 7.46$	$57.59 \pm 8.34$	$85.44 \pm 8.94$	$94.11 \pm 7.24$	$71.25 \pm 11.73$
HWIN	$90.43 \pm 3.48$	$99.59 \pm 0.58$	$97.73 \pm 2.10$	$99.69 \pm 0.32$	$96.84 \pm 1.16$	$99.71 \pm 0.40$
GRF	$95.23 \pm 6.36$	$99.49 \pm 0.41$	$96.11 \pm 1.86$	$99.56 \pm 0.40$	$93.18 \pm 6.56$	$99.91 \pm 0.15$
RET	$99.55 \pm 0.69$	$99.98 \pm 0.05$	$99.91 \pm 0.15$	$99.99 \pm 0.08$	$92.42 \pm 9.21$	$99.92 \pm 0.11$
SQI	$99.99 \pm 0.02$	$100 \pm 0$	$100 \pm 0$	$100 \pm 0$	$95.10 \pm 6.11$	$100 \pm 0$
TT	$90.00 \pm 11.63$	$99.85 \pm 0.24$	$95.42 \pm 6.42$	$99.86 \pm 0.22$	$94.60 \pm 6.90$	$99.75 \pm 0.39$
wGWF	$96.14 \pm 2.89$	$99.99 \pm 0.02$	$99.53 \pm 0.58$	$99.99 \pm 0.02$	$98.00 \pm 2.95$	$99.96 \pm 0.08$
Proposed	$100 \pm 0$	$100 \pm 0$	$100 \pm 0$	$100 \pm 0$	$98.40 \pm 2.39$	$100 \pm 0$

	PCA	LDA	KFA	GLDA	eLBPH	MMSEC
Original	$5.71 \pm 0.26$	$30.48 \pm 4.36$	$14.71 \pm 1.69$	$43.12 \pm 4.04$	$24.24 \pm 4.21$	$26.94 \pm 4.03$
HWIN	$17.36 \pm 0.39$	$33.02 \pm 2.54$	$25.08 \pm 1.79$	$57.04 \pm 4.81$	$28.76 \pm 3.64$	$35.86 \pm 2.99$
GRF	$21.03 \pm 4.47$	$35.88 \pm 8.25$	$26.73 \pm 6.63$	$45.58 \pm 8.22$	$29.61 \pm 5.62$	$36.28 \pm 7.61$
RET	$19.55 \pm 1.38$	$34.87 \pm 3.03$	$27.72 \pm 3.45$	$60.73 \pm 4.47$	$36.14 \pm 5.07$	$34.91 \pm 3.90$
SQI	$19.53 \pm 2.90$	$39.13 \pm 4.33$	$31.21 \pm 5.09$	$55.00 \pm 4.77$	$34.86 \pm 2.71$	$41.28 \pm 3.58$
TT	$18.39 \pm 1.69$	$33.87 \pm 3.13$	$25.03 \pm 2.85$	$60.76 \pm 3.20$	$42.30 \pm 3.60$	$33.26 \pm 3.48$
wGWF	$17.29 \pm 1.61$	$36.69 \pm 3.95$	$25.96 \pm 3.72$	$58.12 \pm 4.54$	$42.83 \pm 3.43$	$35.79 \pm 3.72$
Proposed	$25.11 \pm 2.02$	$42.84 \pm 3.17$	$33.97 \pm 3.95$	$63.87 \pm 4.93$	$42.89 \pm 3.56$	$43.70 \pm 2.88$

	PCA	LDA	KFA	GLDA	eLBPH	MMSEC
Original	$8.99 \pm 3.93$	$26.42 \pm 11.04$	$21.51 \pm 8.55$	$38.76 \pm 16.84$	$47.39 \pm 9.69$	$27.21 \pm 10.89$
HWIN	$67.65 \pm 7.62$	$82.79 \pm 11.78$	$78.65 \pm 10.36$	$89.81 \pm 14.42$	$71.11 \pm 7.88$	$86.71 \pm 6.70$
GRF	$66.86 \pm 14.34$	$81.38 \pm 12.36$	$79.96 \pm 9.88$	$89.16 \pm 10.55$	$76.05 \pm 8.43$	$77.61 \pm 12.68$
RET	$88.89 \pm 4.93$	$93.08 \pm 2.56$	$92.57 \pm 2.58$	$93.69 \pm 8.47$	$79.96 \pm 6.33$	$93.05 \pm 3.44$
SQI	$68.54 \pm 14.01$	$88.94 \pm 7.07$	$84.71 \pm 10.03$	$89.34 \pm 10.86$	$79.87 \pm 12.67$	$91.15 \pm 4.34$
TT	$73.47 \pm 6.30$	$91.42 \pm 2.89$	$84.93 \pm 4.17$	$91.77 \pm 10.14$	$81.86 \pm 4.80$	$90.67 \pm 3.84$
wGWF	$73.57 \pm 13.09$	$91.63 \pm 5.22$	$83.42 \pm 10.56$	$92.47 \pm 10.06$	$82.37 \pm 5.21$	$88.52 \pm 6.93$
Proposed	$92.65 \pm 2.68$	$95.87 \pm 1.23$	$94.33 \pm 1.52$	$96.65 \pm 5.88$	$82.61 \pm 6.02$	$96.50 \pm 1.24$

	PCA	LDA	KFA	GLDA	eLBPH	MMSEC
Original	$22.79 \pm 3.43$	$68.42 \pm 7.46$	$57.59 \pm 8.34$	$85.44 \pm 8.94$	$94.11 \pm 7.24$	$71.25 \pm 11.73$
HWIN	$90.43 \pm 3.48$	$99.59 \pm 0.58$	$97.73 \pm 2.10$	$99.69 \pm 0.32$	$96.84 \pm 1.16$	$99.71 \pm 0.40$
GRF	$95.23 \pm 6.36$	$99.49 \pm 0.41$	$96.11 \pm 1.86$	$99.56 \pm 0.40$	$93.18 \pm 6.56$	$99.91 \pm 0.15$
RET	$99.55 \pm 0.69$	$99.98 \pm 0.05$	$99.91 \pm 0.15$	$99.99 \pm 0.08$	$92.42 \pm 9.21$	$99.92 \pm 0.11$
SQI	$99.99 \pm 0.02$	$100 \pm 0$	$100 \pm 0$	$100 \pm 0$	$95.10 \pm 6.11$	$100 \pm 0$
TT	$90.00 \pm 11.63$	$99.85 \pm 0.24$	$95.42 \pm 6.42$	$99.86 \pm 0.22$	$94.60 \pm 6.90$	$99.75 \pm 0.39$
wGWF	$96.14 \pm 2.89$	$99.99 \pm 0.02$	$99.53 \pm 0.58$	$99.99 \pm 0.02$	$98.00 \pm 2.95$	$99.96 \pm 0.08$
Proposed	$100 \pm 0$	$100 \pm 0$	$100 \pm 0$	$100 \pm 0$	$98.40 \pm 2.39$	$100 \pm 0$

Abstract

Cited By

Figures (9)

Tables (4)

Equations (10)

Applied Optics