1 / 14

Hierarchical Ensemble of Global and Local Classifiers for Face Recognition

Hierarchical Ensemble of Global and Local Classifiers for Face Recognition. Yu Su, Shiguang Shan , Member, IEEE , Xilin Chen , Member, IEEE , and Wen Gao , Fellow, IEEE. I. INTRODUCTION.

prem
Download Presentation

Hierarchical Ensemble of Global and Local Classifiers for Face Recognition

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Hierarchical Ensemble of Global and Local Classifiers for Face Recognition Yu Su, Shiguang Shan, Member, IEEE, Xilin Chen, Member, IEEE, and Wen Gao, Fellow, IEEE

  2. I.INTRODUCTION • This paper proposes a novel face recognition method which exploits both global and local discriminative features. • Global features are extracted by 2-D discrete Fourier transform. • Local feature are extracted by Gabor wavelet transform. • The combination of global and local features plays a key role. • Ensemble is also a key contributor to improve generalizability

  3. I.INTRODUCTION • Different Roles of Global and Local Features

  4. II. EXTRACTION 2-D Discrete Fourier Transformation ( DFT ) Extraction of Global Fourier Features A 2-D image of size M byN pixels, 0 ≦u≦M - 1 and 0 ≦v≦N - 1 are frequency variables. R( u, v) and I( u, v ) is real and imaginary components. 2009/12/16 4

  5. II. EXTRACTION • Global feature extraction by 2-D DFT Some examples of inverse transform by using only the low frequency bands (about 30% of all the energy). The real and imaginary components named global Fourier feature vector (GFFV). 2009/12/16 5

  6. II. EXTRACTION Extraction of Local Gabor Features • Gabor Wavelet Transform ( GWT) Gabor wavelet consists of a planar sinusoid multiplied by a 2-D Gaussian. 2009/12/16 6

  7. II. EXTRACTION Gabor features are grouped into a number of feature vectors named local Gabor feature vector (LGFV) 2009/12/16 7

  8. II. EXTRACTION Patch Selection via Greedy Search • in this paper, we propose a patch selection methodto automatically determine the positions and sizes of the localpatches

  9. Two layers of ensemble: III.COMBINING Construction of Hierarchical Ensemble Classifier Li : Local Gabor feature vector (LGFV) CLi :Local Component Classifier (LCC) CL : Local Ensemble Classifier (LEC) CG: Global Classifier (GC) CH : Hierarchical Ensemble Classifier (HEC) 2009/12/16 9

  10. III.COMBINING Weight Learning for Component Classifiers • Firstly, the face images can be divided into two classes named intrapersonal pairs and interpersonal pairs. • Secondly, for each image pair, a similarity vectorcan be obtained. • Last step, two classes of the N–dimensionalsamples are fed into FLD to get an optimal linearprojection from N-D to 1-D. 2009/12/16 10

  11. IV. RESULT Different Roles of Global and Local Features • Gabor feature are more sensitive to the detailed local variations.

  12. IV. RESULT • The performance improvement becomes trivial when the number of LCCs exceeds 30. • The performance of LEC is much better than that of the individual LCC (especially on Experiment 4).

  13. IV. RESULT Hierarchical Ensemble Classifier

  14. Thanks

More Related