TY - JOUR
T1 - Three-Phase Face Recognition Algorithm via Locally Frontal Face Synthesis and Two-Phase Face Recognition
AU - Zhao, Qing Jie
AU - Qi, Hui
AU - Zhang, Yu
AU - Wang, Hao
N1 - Publisher Copyright:
© 2017, Editorial Department of Transaction of Beijing Institute of Technology. All right reserved.
PY - 2017/6/1
Y1 - 2017/6/1
N2 - Two-phase test sample representation algorithm (TPTSR), which is robust to interference such as occlusion and noise, performs well in face recognition without pose variation. However, its recognition rate will decline when the face pose varies dramatically. To solve this problem, a three-phase test sample representation algorithm was proposed. The first was frontal face synthesizing was a frontal face with small horizontal deflection angle was synthesized using view-library and proposed frontal face synthesizing algorithm. Thus, a frontal face was synthesized as the new test sample. The second was training sample selecting phase, M training samples that make the most contribution were selected to represent the new test sample. The third was decision and recognition phase, a face was recognized using the M training samples. Experiments on some publicly available face recognition benchmarks demonstrate that the proposed 3PTSR algorithm outperforms the state-of-the-art methods in challenging conditions, especially for the face with various poses.
AB - Two-phase test sample representation algorithm (TPTSR), which is robust to interference such as occlusion and noise, performs well in face recognition without pose variation. However, its recognition rate will decline when the face pose varies dramatically. To solve this problem, a three-phase test sample representation algorithm was proposed. The first was frontal face synthesizing was a frontal face with small horizontal deflection angle was synthesized using view-library and proposed frontal face synthesizing algorithm. Thus, a frontal face was synthesized as the new test sample. The second was training sample selecting phase, M training samples that make the most contribution were selected to represent the new test sample. The third was decision and recognition phase, a face was recognized using the M training samples. Experiments on some publicly available face recognition benchmarks demonstrate that the proposed 3PTSR algorithm outperforms the state-of-the-art methods in challenging conditions, especially for the face with various poses.
KW - Face recognition
KW - Frontal face synthesis
KW - Sparse representation
UR - http://www.scopus.com/inward/record.url?scp=85028883130&partnerID=8YFLogxK
U2 - 10.15918/j.tbit1001-0645.2017.06.016
DO - 10.15918/j.tbit1001-0645.2017.06.016
M3 - Article
AN - SCOPUS:85028883130
SN - 1001-0645
VL - 37
SP - 637
EP - 643
JO - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
JF - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
IS - 6
ER -