TY - JOUR
T1 - Very low resolution face recognition problem
AU - Zou, Wilman W.W.
AU - Yuen, Pong C.
N1 - Funding Information:
Manuscript received October 30, 2010; revised March 28, 2011 and June 17, 2011; accepted July 10, 2011. Date of publication July 18, 2011; date of current version December 16, 2011. This work was supported in part by the Faculty Research Grant of Hong Kong Baptist University and in part by the National Natural Science Foundation of China–Guangdong Joint Fund under Grant U0835005. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. A. C. Kot.
PY - 2012/1
Y1 - 2012/1
N2 - This paper addresses the very low resolution (VLR) problem in face recognition in which the resolution of the face image to be recognized is lower than 16 × 16. With the increasing demand of surveillance camera-based applications, the VLR problem happens in many face application systems. Existing face recognition algorithms are not able to give satisfactory performance on the VLR face image. While face super-resolution (SR) methods can be employed to enhance the resolution of the images, the existing learning-based face SR methods do not perform well on such a VLR face image. To overcome this problem, this paper proposes a novel approach to learn the relationship between the high-resolution image space and the VLR image space for face SR. Based on this new approach, two constraints, namely, new data and discriminative constraints, are designed for good visuality and face recognition applications under the VLR problem, respectively. Experimental results show that the proposed SR algorithm based on relationship learning outperforms the existing algorithms in public face databases.
AB - This paper addresses the very low resolution (VLR) problem in face recognition in which the resolution of the face image to be recognized is lower than 16 × 16. With the increasing demand of surveillance camera-based applications, the VLR problem happens in many face application systems. Existing face recognition algorithms are not able to give satisfactory performance on the VLR face image. While face super-resolution (SR) methods can be employed to enhance the resolution of the images, the existing learning-based face SR methods do not perform well on such a VLR face image. To overcome this problem, this paper proposes a novel approach to learn the relationship between the high-resolution image space and the VLR image space for face SR. Based on this new approach, two constraints, namely, new data and discriminative constraints, are designed for good visuality and face recognition applications under the VLR problem, respectively. Experimental results show that the proposed SR algorithm based on relationship learning outperforms the existing algorithms in public face databases.
KW - Face recognition
KW - face super-resolution (SR)
KW - relationship learning
KW - very low resolution (VLR)
UR - http://www.scopus.com/inward/record.url?scp=84255177518&partnerID=8YFLogxK
U2 - 10.1109/TIP.2011.2162423
DO - 10.1109/TIP.2011.2162423
M3 - Journal article
C2 - 21775262
AN - SCOPUS:84255177518
SN - 1057-7149
VL - 21
SP - 327
EP - 340
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 1
M1 - 5957296
ER -