A Ranking Model for Face Alignment with Pseudo Census Transform

被引：0

作者：

Gao, Hua ^{[1
]}

Ekenel, Hazim Kemal ^{[1
]}

Stiefelhagen, Rainer ^{[1
]}

机构：

[1] Karlsruhe Inst Technol, Inst Anthropomat, D-76021 Karlsruhe, Germany

来源：

2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012) | 2012年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We extend the PCT (Pseudo Census Transform)based appearance model [3] to ranking-based appearance model for face alignment. The PCT-based weak ranking function is learned using RankSVM, and the ranking appearance model (RAM) is constructed in a boosting manner. Experiments show that the PCT-based RAM is more robust and generalize better than the PCT-based boosted appearance model (BAM). The PCT-RAM achieves about 23% improvement when tested on unseen data. We also investigate different sampling strategies for the learning to rank problem and find out that random permutation achieves similar results as using adjacent ordering pairs. The alignment results do not decrease significantly when only one ordinal pair is used for each direction.

引用

页码：1116 / 1119

页数：4

共 50 条

[1] Boosting Pseudo Census Transform Features for Face Alignment
Gao, Hua
Ekenel, Hazim Kemal
Fischer, Mika
Stiefelhagen, Rainer
[J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011, 2011,
[2] Face alignment via boosted ranking model
Wu, Hao
Liu, Xiaoming
Doretto, Gianfranco
[J]. 2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, : 3200 - +
[3] Face Alignment Using a Ranking Model based on Regression Trees
Gao, Hua
Ekenel, Hazim Kemal
Stiefelhagen, Rainer
[J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2012, 2012,
[4] Face detection with the modified census transform
Fröba, B
Ernst, A
[J]. SIXTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS, 2004, : 91 - 96
[5] Joint Face Detection and Alignment with a Deformable Hough Transform Model
McDonagh, John
Tzimiropoulos, Georgios
[J]. COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II, 2016, 9914 : 569 - 580
[6] Illumination normalization for face recognition using the census transform
Kim, Ji Hoon
Park, Jong Geun
Lee, Chulhee
[J]. COMPUTATIONAL IMAGING VI, 2008, 6814
[7] Robust face recognition using the modified census transform
Yun, Woo-han
Yoon, Ho-Sub
Kim, Do-Hyung
Chi, Su-young
[J]. 2007 INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES, VOLS 1-3, 2007, : 749 - 752
[8] Joint Face Alignment with a Generic Deformable Face Model
Zhao, Cong
Cham, Wai-Kuen
Wang, Xiaogang
[J]. 2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, : 561 - 568
[9] Illumination invariant face recognition for frontal faces using modified census transform
Bhavani, S.
Thawani, Amit
Sridhar, V
Ramakrishnan, K. R.
[J]. TENCON 2007 - 2007 IEEE REGION 10 CONFERENCE, VOLS 1-3, 2007, : 962 - +
[10] Appearance model based face-to-face transform
Nagai, T
Nguyen, T
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 749 - 752

← 1 2 3 4 5 →