Improved Face Recognition on Video Surveillance Images using Pose Correction

被引：0

作者：

Jamil, Nur A'in ^{[1
]}

Sheikh, U. U. ^{[1
]}

Mokji, Musa Mohd. ^{[1
]}

Omar, Zaid ^{[1
]}

Ab Rahman, Ab Al Hadi ^{[1
]}

机构：

[1] Univ Teknol Malaysia, Fac Elect Engn, Johor Baharu, Malaysia

来源：

TENCON 2017 - 2017 IEEE REGION 10 CONFERENCE | 2017年

关键词：

biometrics; video surveillance; face recognition; pose correction; ZERNIKE MOMENTS;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Face recognition in video surveillance is challenging as there is no control on the quality of the face image captured especially under uncooperative situations with head pose variation, occlusion, and low-quality image. These issues create large discrepancy between probe and gallery images which affects the performance of recognition. To overcome these issues, pose correction is proposed to narrow the difference between probe and gallery images and image enhancer to highlight face image details. Face representation is improved by creating an average face image to reduce the effect of non-facial details captured such as background, occlusion and noise. The proposed methods are tested on ChokePoint dataset and resulted in improved face recognition.

引用

页码：1391 / 1395

页数：5

共 13 条

[1]

An L, 2012, INT C PATT RECOG, P2885

[2] Constrained Local Neural Fields for robust facial landmark detection in the wild [J].

Baltrusaitis, Tadas ;

Robinson, Peter ;

Morency, Louis-Philippe .

2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2013, :354-361

[3] Watch-List Screening Using Ensembles Based on Multiple Face Representations [J].

Bashbaghi, Saman ;

Granger, Eric ;

Sabourin, Robert ;

Bilodeau, Guillaume-Alexandre .

2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, :4489-4494

[4] Adaptive appearance model tracking for still-to-video face recognition [J].

Dewan, M. Ali Akber ;

Granger, E. ;

Marcialis, G. -L. ;

Sabourin, R. ;

Roli, F. .

PATTERN RECOGNITION, 2016, 49 :129-151

[5] Multi-task Pose-Invariant Face Recognition [J].

Ding, Changxing ;

Xu, Chang ;

Tao, Dacheng .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (03) :980-993

[6] Near infrared face recognition using Zernike moments and Hermite kernels [J].

Farokhi, Sajad ;

Sheikh, Usman Ullah ;

Flusser, Jan ;

Yang, Bo .

INFORMATION SCIENCES, 2015, 316 :234-245

[7] Near infrared face recognition by combining Zernike moments and undecimated discrete wavelet transform [J].

Farokhi, Sajad ;

Shamsuddin, Siti Mariyam ;

Sheikh, U. U. ;

Flusser, Jan ;

Khansari, Mohammad ;

Jafari-Khouzani, Kourosh .

DIGITAL SIGNAL PROCESSING, 2014, 31 :13-27

[8] 3-D Generic Elastic Models for Fast and Texture Preserving 2-D Novel Pose Synthesis [J].

Heo, Jingu ;

Savvides, Marios .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2012, 7 (02) :563-576

[9] Unrestricted pose-invariant face recognition by sparse dictionary matrix [J].

Moeini, Ali ;

Moeini, Hossein ;

Faez, Karim .

IMAGE AND VISION COMPUTING, 2015, 36 :9-22

[10] Poisson image editing [J].

Pérez, P ;

Gangnet, M ;

Blake, A .

ACM TRANSACTIONS ON GRAPHICS, 2003, 22 (03) :313-318

← 1 2 →