Robust nose tip localization based on two-stage subclass discriminant analysis

Robust nose tip localization based on two-stage subclass discriminant analysis
复制标题

基于两阶段子类判别分析的鲁棒鼻尖定位

DOI:
10.1016/j.neucom.2013.02.055
复制
发表时间:
2014-08
期刊:
影响因子:
6
通讯作者:
Hongwei Ying
Hongwei Ying
中科院分区:
计算机科学2区
文献类型:
--
作者:
JIatao song;LIhua JIa;Wei Wang;Hongwei Ying

文献摘要

参考文献

相似文献

鼻子是人脸的显著特征之一,它的定位在人脸识别、人脸姿态识别、三维人脸重建等方面具有重要意义。在第一阶段,随机选取一些图像块作为负样本进行SDA分类器的训练,从整幅人脸图像中检测出鼻子。第二阶段利用一些鼻部上下文块作为负样本对SDA分类器的训练进行鼻尖位置精化。该方法从整个人脸图像中检测鼻子,不需要使用关于人脸部件布局的先验知识。在AR图像上的实验结果表明,该方法能够获得较高的鼻尖定位准确率,并且对光照和面部表情的变化具有较强的鲁棒性。
Nose is one of the salient features in a human face, and its localization is important for face recognition, face pose recognition, 3D face reconstruction, etc. In this paper, a novel nose tip localization method is proposed, which is based on two-stage subclass discriminant analysis (SDA). At the first stage, some randomly selected image patches are used as negative samples for the training of SDA classifier, and nose is detected from the whole face image. The second stage refines nose tip position by using some nose context patches as negative samples for the training of SDA classifier. The proposed method detects nose from the whole face image and no a priori knowledge about the layout of face components is used. Experimental results on AR images show that the proposed method can achieve high nose tip localization rates, and is robust to changes of illumination and facial expression.
DOI: 10.1109/cvpr.2005.582
发表时间: 2005-06
期刊: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops
影响因子: --
作者:
P. Sankaran;Satyanadh Gundimada;R. Tompkins;V. Asari
通讯作者: P. Sankaran;Satyanadh Gundimada;R. Tompkins;V. Asari
DOI: 10.1109/iai.2002.999905
发表时间: 2002-04
期刊: Proceedings Fifth IEEE Southwest Symposium on Image Analysis and Interpretation
影响因子: --
作者:
M. Gargesha;S. Panchanathan
通讯作者: M. Gargesha;S. Panchanathan
DOI: 10.1007/978-3-540-74171-8_126
发表时间: 2007-08
期刊: --
影响因子: --
作者:
X. Ren;Jiatao Song;H. Ying;Ya-ni Zhu;Xuena Qiu
通讯作者: X. Ren;Jiatao Song;H. Ying;Ya-ni Zhu;Xuena Qiu
DOI: 10.1109/cisp.2009.5305490
发表时间: 2009-10
期刊: 2009 2nd International Congress on Image and Signal Processing
影响因子: --
作者:
Lei Wei;Rui Mo;Wei Gao;Yi Zhu;Z. Peng;Yaohui Zhang
通讯作者: Lei Wei;Rui Mo;Wei Gao;Yi Zhu;Z. Peng;Yaohui Zhang
DOI: 10.1109/icip.2004.1421473
发表时间: 2004-10
期刊: 2004 International Conference on Image Processing, 2004. ICIP '04.
影响因子: --
作者:
Chenghua Xu;Yunhong Wang;T. Tan;Long Quan
通讯作者: Chenghua Xu;Yunhong Wang;T. Tan;Long Quan