TY - GEN
T1 - Application of constrained local neural fields in face recognition
AU - Sun, Jinna
AU - Yuan, Mingting
AU - Ding, Junhang
AU - Xu, Huasheng
AU - Sui, Qingmei
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/29
Y1 - 2017/12/29
N2 - The facial feature points localization is the core of face recognition, and its accuracy directly affects the accuracy of face recognition system. The accuracy of facial feature points is affected by light, noise, background, and face gestures. Considering the theoretical value and practical significance of facial feature points localization, this thesis goes into the most advanced algorithm of facial feature points localization-Constrained Local Neural Fields. Taking into account the reliability of each patch model (feature point detector), CLNF combines the Local Neural Field patch model. The analysis contrasts the advantages of Constrained Local Models.
AB - The facial feature points localization is the core of face recognition, and its accuracy directly affects the accuracy of face recognition system. The accuracy of facial feature points is affected by light, noise, background, and face gestures. Considering the theoretical value and practical significance of facial feature points localization, this thesis goes into the most advanced algorithm of facial feature points localization-Constrained Local Neural Fields. Taking into account the reliability of each patch model (feature point detector), CLNF combines the Local Neural Field patch model. The analysis contrasts the advantages of Constrained Local Models.
KW - Constrained Local Neural Fields
KW - Facial feature points localization
KW - Patch model
UR - https://www.scopus.com/pages/publications/85050344474
U2 - 10.1109/CAC.2017.8244216
DO - 10.1109/CAC.2017.8244216
M3 - 会议稿件
AN - SCOPUS:85050344474
T3 - Proceedings - 2017 Chinese Automation Congress, CAC 2017
SP - 7920
EP - 7924
BT - Proceedings - 2017 Chinese Automation Congress, CAC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 Chinese Automation Congress, CAC 2017
Y2 - 20 October 2017 through 22 October 2017
ER -