| | |
Summary: Robust Real-Time Face Alignment Based on ASM with Boosting Regression
for Displacement Prediction
Yanchao SU1
, Haizhou AI1
, Shihong LAO2
1
Computer Science and Technology Department, Tsinghua University, China
2
Sensing and Control Technology Laboratory, Omron Corporation, Japan
ahz@mail.tsinghua.edu.cn
Abstract
Face alignment is a critical problem in many face
related applications such as facial expression analysis,
face recognition, etc. This paper presents a novel real
time face alignment algorithm based on Active Shape
Model (ASM). In our algorithm, local textures of each
label point is used to predict the displacement of each
label point by applying boost non-linear regressions
on the local search stage of the ASM framework. Ex-
periments on different datasets show that our algo-
|
