期刊文献+

基于环形核的旋转不变性特征提取方法

Feature extraction method based on CKF for face recognition
下载PDF
导出
摘要 针对人脸在XOZ平面内旋转,即在图像所在平面内人脸产生的旋转,因特征值变化大导致人脸识别率降低的问题,提出了一种新颖的基于环形核的旋转不变性特征(Circular Kernel Feature,CKF)提取方法。所提算法有两个创新点,第一点是给出了环形核的建立方式,定位人脸上明显的特征部分。第二点是提供了特征的旋转不变计算方式。首先建立环形核,定位人脸上明显特征的坐标区域;然后,用旋转不变的计算方式获取定位区域的特征值。在Georgia Tech人脸数据库上的实验证明:人脸旋转前后CKF的值相较Gabor,LBP等特征值的变化小了98%。 A novel mechanism named CKF( Circular Kernel Feature ) for solving the problem that face recognition rate reduced by rotation is proposed in this paper. Firstly, characteristics of rotation in-variants are defined. Then, to establish the annular nuclear, striking features are located. Secondly, eigenvalues by rotation invariant method are calculated. Experimental results show that, compared with traditional Gabor and LBP, the Euclidean distance of CKF achieved 98 percent reduction using Georgia Tech database.
出处 《电视技术》 北大核心 2016年第3期1-4,共4页 Video Engineering
基金 国家科技支撑计划课题项目(2014BAK11B02) 广西科学研究与技术开发计划项目(桂科攻14122007-5) 广西自然科学基金项目(2013GXNSFAA019326)
关键词 CKF 旋转不变 环形核 CKF rotation invariant circular nucleus
  • 相关文献

参考文献8

  • 1GUO B F,LAM K M, LINK H, et al. Human face recogni- tion based on spatially weighted Hausdorff distance [ J ]. Pat- tern recognition letters,2003,24 ( 3 ) :499-507. 被引量:1
  • 2祝磊,朱善安.人脸识别的一种新的特征提取方法[J].光电工程,2007,34(6):122-125. 被引量:7
  • 3HAMSICIONUR C. Rotation invariant kernels and their ap- plication to shape analysis [ J ]. IEEE transactions on pattern analysis and machine intelligence,2009,31 ( 11 ) : 1985-1999. 被引量:1
  • 4LI D, KONG F. Facial feature point extraction using a new improve active shape model [ J ]. International congress on image & signal processing,2010(2) :944-948. 被引量:1
  • 5MILBORROW S, MORKEL J, NICOLLS F. The MUCT landmarked face database [ EB/OL]. [ 2015-08-24 ]. ht- tps ://www. researchgate, net/publication/264885609_The_ MUCT_Landmarked_Face_Database. 被引量:1
  • 6MILBORROW S, NICOLLS F. Active shape models with SIFT descriptors and MARS[ EB/OL]. [ 2015-08-24 ]. ht- tp://xueshu, baidu, corn/s? wd = paperuri% 3A% 285a8b47ec4e9b9f94367fOObfa93f45cO% 29&fiher = sc_ long_sign&tn = SE_xueshusource_2kduw22v&sc_vurl = ht- tp% 3A% 2F% 2Fdx. doi. org% 2F10. 5220% 2 F0004680003800387 &ie = utf-8. 被引量:1
  • 7王庆军,张汝波.基于Log-Gabor和正交等度规映射的人脸识别[J].计算机科学,2011,38(2):274-276. 被引量:8
  • 8王映辉著..人脸识别 原理、方法与技术[M].北京:科学出版社,2010:320.

二级参考文献28

  • 1聂祥飞,郭军.利用Gabor小波变换解决人脸识别中的小样本问题[J].光学精密工程,2007,15(6):973-977. 被引量:20
  • 2Turk M,Pentland A.Eigenfaces for recognition[J].Journal of cognitive Neuroscience,1991,3(1):72-86. 被引量:1
  • 3Belhumeur P N,Hespanha J P,Kriegman D J.Eigenfaces vs.fisherfaces:Recognition using class specific linear projection[J].IEEE Trans.on Pattern Analysis and machine Intelligence,1997,19(7):711-720. 被引量:1
  • 4Tenenbaum J B,de Silva V,Langford J C.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290(5500):2319-2323. 被引量:1
  • 5Roweis S T,Saul L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323-2326. 被引量:1
  • 6Belkin M.Laplacian eigenmaps for dimensionality reduction and data representation[J].Neural Computation,2003,15(6):1373-1396. 被引量:1
  • 7Cai Deng,He Xiao-fei,Han Jia-wei.Isometric projection[C] ∥Proceedings of AAAI'2007.Vancouver,British Columbia,2007:528-533. 被引量:1
  • 8He Xiao-fei,Cai Deng,Yan Shui-cheng,et al.Neighborhood preserving embedding[C] ∥Tenth IEEE International Conference on Computer Vision.Beijing,China,2005:1208-1213. 被引量:1
  • 9He Xiao-fei,Yan Shui-cheng.Face recognition using laplacian-faces[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,2005,27(3):328-340. 被引量:1
  • 10Zheng Z L,Yang F,Tan W A,et a1.Gabor feature-based face recognition using supervised locality preserving projection[J].Signal Processing,2007,87(10):2473-2483. 被引量:1

共引文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部