TY - JOUR
T1 - Nighttime face recognition at large standoff
T2 - Cross-distance and cross-spectral matching
AU - Kang, Dongoh
AU - Han, Hu
AU - Jain, Anil K.
AU - Lee, Seong Whan
N1 - Funding Information:
The authors would like to thank the Pinellas County Sheriff׳s Office for providing the PCSO face database. We would also like to thank the Institute of Automation, Chinese Academy of Science (CASIA) for providing us the CASIA-FaceV5 database. This research was supported by the Implementation of Technologies for Identification, Behavior, and Location of Human based on Sensor Network Fusion Program through the Ministry of Trade, Industry and Energy (Grant number: 10041629 ) and the 2014 R&D Program for S/W Computing Industrial Core Technology through the MSIP(Ministry of Science, ICT and Future Planning)/KEIT(Korea Evaluation Institute of Industrial Technology) (Project No. 2014-044-023-001), Korea.
PY - 2014/12/1
Y1 - 2014/12/1
N2 - Face recognition in surveillance systems is important for security applications, especially in nighttime scenarios when the subject is far away from the camera. However, due to the face image quality degradation caused by large camera standoff and low illuminance, nighttime face recognition at large standoff is challenging. In this paper, we report a system that is capable of collecting face images at large standoff in both daytime and nighttime, and present an augmented heterogeneous face recognition (AHFR) approach for cross-distance (e.g., 150 m probe vs. 1 m gallery) and cross-spectral (near-infrared probe vs. visible light gallery) face matching. We recover high-quality face images from degraded probe images by proposing an image restoration method based on Locally Linear Embedding (LLE). The restored face images are matched to the gallery by using a heterogeneous face matcher. Experimental results show that the proposed AHFR approach significantly outperforms the state-of-the-art methods for cross-spectral and cross-distance face matching.
AB - Face recognition in surveillance systems is important for security applications, especially in nighttime scenarios when the subject is far away from the camera. However, due to the face image quality degradation caused by large camera standoff and low illuminance, nighttime face recognition at large standoff is challenging. In this paper, we report a system that is capable of collecting face images at large standoff in both daytime and nighttime, and present an augmented heterogeneous face recognition (AHFR) approach for cross-distance (e.g., 150 m probe vs. 1 m gallery) and cross-spectral (near-infrared probe vs. visible light gallery) face matching. We recover high-quality face images from degraded probe images by proposing an image restoration method based on Locally Linear Embedding (LLE). The restored face images are matched to the gallery by using a heterogeneous face matcher. Experimental results show that the proposed AHFR approach significantly outperforms the state-of-the-art methods for cross-spectral and cross-distance face matching.
KW - Cross-distance matching
KW - Cross-spectral matching
KW - Heterogeneous face matching
KW - Image restoration
KW - K-means clustering
KW - Locally Linear Embedding (LLE)
KW - Nighttime face recognition
UR - http://www.scopus.com/inward/record.url?scp=84907712027&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84907712027&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2014.06.004
DO - 10.1016/j.patcog.2014.06.004
M3 - Article
AN - SCOPUS:84907712027
VL - 47
SP - 3750
EP - 3766
JO - Pattern Recognition
JF - Pattern Recognition
SN - 0031-3203
IS - 12
ER -