一种基于特征匹配的人脸配准判断方法
An assessment method for face alignment based on feature matching
查看参考文献18篇
文摘
|
现有的人脸识别应用系统大都忽略了人脸配准的检查,造成"误配准灾难",导致识别性能下降。因此,对规格化后的人脸图像进行判断筛选,以保证只有正确配准的人脸图像才能用于后续识别。选用一定数量正确配准的规格化人脸图像平均值作为标准人脸,用SIFT关键点定位方法得到标准人脸的多个关键点,采用分块的梯度方向直方图统计方法提取关键点的邻域图像特征;然后,将标准人脸的关键点位置作为待检测人脸的定位点,用同样的方法提取定位点的邻域图像特征;计算待检图像与标准人脸图像对应关键点的特征矢量相似度,设定合理阈值判断待检测图像是否配准。实验证明,该方法能有效去除误配准人脸图像,有利于提高人脸识别系统的可靠性。 |
其他语种文摘
|
The lacking of confirmation for face alignment leads to an incorrect feature match. The decline of recognition rate in current application of face recognition is called "mis-alignment crash". Therefore, it is necessary to test and filter the normalized face images to make sure only the aligned face images can go through the recognition procedure. In the method, a bunch of right-alignment normalized face images were used to form a mean face which was defined as the standard face. The key points location theory of SIFT was used to get the key points of standard face and the features of neighboring images were extracted on the basis of blocked statistical histogram in gradient orientation. The location of key points of a standard face was taken as the positioning point of a face to be detected. Using the same method to extract the features of neighboring images showed that the similarities of the test images to the standard face were calculated according to their corresponding feature descriptors of the key points. A reasonable threshold was chosen to estimate and classify the images according to their similarities to standard face. The experiment proved that this method is effective in eliminating mis-aligned face image effectively and is beneficial for increasing the reliability of a face recognition system. |
来源
|
智能系统学报
,2015,10(1):12-19 【核心库】
|
关键词
|
人脸识别
;
图像规格化
;
配准判断
;
图像特征
;
SIFT描述子
;
梯度方向直方图
;
关键点定位
;
图像匹配
|
地址
|
中国科学院半导体研究所, 北京, 100083
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1673-4785 |
学科
|
自动化技术、计算机技术 |
基金
|
国家自然科学基金资助项目
|
文献收藏号
|
CSCD:5357979
|
参考文献 共
18
共1页
|
1.
山世光. 人脸识别中的"误配准灾难"问题研究.
计算机学报,2005,28(5):782-791
|
被引
6
次
|
|
|
|
2.
唱轶钲. Gabor特征判别分析人脸识别方法的误配准鲁棒性分析.
计算机工程与运用,2005(5):56-59
|
被引
4
次
|
|
|
|
3.
Jung C. Eye detection under varying illumination using the retinex theory.
Elsevier Science,2013,113:130-137
|
被引
1
次
|
|
|
|
4.
Gu Jiayu. Feature local binary patterns with application to eye detection.
Neurocomputing,2013,113:138-152
|
被引
3
次
|
|
|
|
5.
Wang Shangfei. Eye localization from thermal infrared images.
Pattern Recognition,2013,46:2613-2621
|
被引
2
次
|
|
|
|
6.
翟倩茹.
不同姿态人脸配准方法研究,2012:1-12
|
被引
1
次
|
|
|
|
7.
Sethuram A. Extremely dense face registration: comparing automatic landmarking algorithms for general and ethno-gender models.
IEEE Fifth International Conference,2012:135-142
|
被引
1
次
|
|
|
|
8.
Lin H. Image registration based on Fourier-Mellin transform.
Geomatics and Information Science of Wuhan University,2012,37(6):649-652
|
被引
1
次
|
|
|
|
9.
刘小军. 基于SIFT的图像配准方法.
红外与激光工程,2008,37(1):156-160
|
被引
25
次
|
|
|
|
10.
Fumihiko S. Image matching based on relation between pixels located on the maximum and minimum gray-levels in local area.
IEEE Transactions on Electrical and Electronic Engineering,2007,12(2):169-178
|
被引
1
次
|
|
|
|
11.
Trajkocic M. Fast corner detection.
Image and Vision Computing,1998,16(2):75-87
|
被引
62
次
|
|
|
|
12.
苏延超. 基于非线性Boosting回归的多视角人脸配准.
自动化学报,2010,36(4):522-527
|
被引
3
次
|
|
|
|
13.
彭地.
图像配准技术与优化算法研究,2011:8-25
|
被引
1
次
|
|
|
|
14.
Lowe D. Distinctive image features from scale-invariant keypoints.
International Journal of Computer Vision,2004,60(2):91-110
|
被引
4626
次
|
|
|
|
15.
Lowe D. Object recognition from local scale invariant features.
International Conference on Computer Vision,1999:1150-1157
|
被引
8
次
|
|
|
|
16.
Lindeberg T. Scale-space theory: A basic tool for analysing structures at different scales.
Journal of Applied Statistics,1994,21(2):224-270
|
被引
127
次
|
|
|
|
17.
Li Weijun. A fast eye location algorithm based on geometric complexity.
Proceedings of the 5th World Congress on Intelligent Control and Automation,2004:4105-4107
|
被引
1
次
|
|
|
|
18.
Dalal N. Histograms of oriented gradients for human detection.
IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1,2005:886-893
|
被引
12
次
|
|
|
|
|