南京理工大学学报（自然科学版）2018，Vol.42Issue(3)：278-285,8.DOI:10.14177/j.cnki.32-1397n.2018.42.03.004
基于动态多视角模型集成策略的人脸特征点定位算法
Facial features localization algorithm based on integration strategy of dynamic multi-view models
摘要
Abstract
A new facial features localization algorithm is presented to improve the accuracy of various facial pose features localization in an unconstrained environment. Different face samples are classified by using pose classification algorithms during the training and testing process of multi-view models based on cascade regression. Facial key points are forecasted by using an integration strategy for various multi-view models. Experimental results show that,compared with the explicit shape regression(ESR),etc,this algorithm is more robust to changes in facial expression in an unconstrained environment.关键词
多视角模型/人脸特征点定位/级联回归模型/姿态分类算法Key words
multi-view models/facial features localization/cascade regression model/pose classifica-tion algorithm分类
信息技术与安全科学引用本文复制引用
王世昊,宋晓宁..基于动态多视角模型集成策略的人脸特征点定位算法[J].南京理工大学学报（自然科学版）,2018,42(3):278-285,8.基金项目
国家重点研发计划(2017YFC1601800) （2017YFC1601800）
中国博士后科学基金(2018T110441) （2018T110441）
江苏省自然科学基金(BK20161135) （BK20161135）
江苏省"六大人才高峰"高层次人才项目(XYDXX-012) （XYDXX-012）
