Skip to main navigation Skip to search Skip to main content

A spectral feature based approach for face recognition with one training sample

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

In this paper, a novel spectral feature image-based 2DLDA (two-dimensional linear discriminant analysis) ensemble algorithm is proposed for face recognition with one sample image per person. In our algorithm, multi-resolution spectral feature images are constructed to represent the face images. The proposed method is inspired by our finding that, among these spectral feature images, features extracted from some orientations and scales using 2DLDA are not sensitive to variations of illumination and expression. In order to maintain the positive characteristics of these filters and to make correct category assignments, the strategy of classifier committee learning (CCL) is designed to combine the results obtained from different spectral feature images. Experimental results on the standard databases demonstrate the feasibility and efficiency of the proposed method. © 2012 IEEE.
Original languageEnglish
Title of host publication2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012
Pages218-222
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012 - Hong Kong, China
Duration: 12 Aug 201215 Aug 2012

Publication series

Name2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012

Conference

Conference2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012
PlaceChina
CityHong Kong
Period12/08/1215/08/12

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

  • classifier combination
  • Face recognition
  • Fourier transform
  • Gabor filter
  • linear discriminant analysis

Fingerprint

Dive into the research topics of 'A spectral feature based approach for face recognition with one training sample'. Together they form a unique fingerprint.

Cite this