TY - JOUR
T1 - Dynamic image-to-class warping for occluded face recognition
AU - Wei, Xingjie
AU - Li, Chang-Tsun
AU - Lei, Zhen
AU - Yi, Dong
AU - Li, Stan Z.
N1 - Includes bibliographical references.
PY - 2014/12/1
Y1 - 2014/12/1
N2 - Face recognition (FR) systems in real-world applications need to deal with a wide range of interferences, such as occlusions and disguises in face images. Compared with other forms of interferences such as nonuniform illumination and pose changes, face with occlusions has not attracted enough attention yet. A novel approach, coined dynamic image-to-class warping (DICW), is proposed in this work to deal with this challenge in FR. The face consists of the forehead, eyes, nose, mouth, and chin in a natural order and this order does not change despite occlusions. Thus, a face image is partitioned into patches, which are then concatenated in the raster scan order to form an ordered sequence. Considering this order information, DICW computes the image-to-class distance between a query face and those of an enrolled subject by finding the optimal alignment between the query sequence and all sequences of that subject along both the time dimension and within-class dimension. Unlike most existing methods, our method is able to deal with occlusions which exist in both gallery and probe images. Extensive experiments on public face databases with various types of occlusions have confirmed the effectiveness of the proposed method.
AB - Face recognition (FR) systems in real-world applications need to deal with a wide range of interferences, such as occlusions and disguises in face images. Compared with other forms of interferences such as nonuniform illumination and pose changes, face with occlusions has not attracted enough attention yet. A novel approach, coined dynamic image-to-class warping (DICW), is proposed in this work to deal with this challenge in FR. The face consists of the forehead, eyes, nose, mouth, and chin in a natural order and this order does not change despite occlusions. Thus, a face image is partitioned into patches, which are then concatenated in the raster scan order to form an ordered sequence. Considering this order information, DICW computes the image-to-class distance between a query face and those of an enrolled subject by finding the optimal alignment between the query sequence and all sequences of that subject along both the time dimension and within-class dimension. Unlike most existing methods, our method is able to deal with occlusions which exist in both gallery and probe images. Extensive experiments on public face databases with various types of occlusions have confirmed the effectiveness of the proposed method.
KW - Biometrics
KW - Dynamic time warping
KW - Face recognition
KW - Image-to-class distance
KW - Occlusion
UR - http://www.scopus.com/inward/record.url?scp=84911215301&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84911215301&partnerID=8YFLogxK
U2 - 10.1109/TIFS.2014.2359632
DO - 10.1109/TIFS.2014.2359632
M3 - Article
AN - SCOPUS:84911215301
SN - 1556-6013
VL - 9
SP - 2035
EP - 2050
JO - IEEE Transactions on Information Forensics and Security
JF - IEEE Transactions on Information Forensics and Security
IS - 12
M1 - 6906281
ER -