Learning neighborhood discriminative manifolds for video-based face recognition

John See, Mohammad Faizal Ahmad Fauzi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In this paper, we propose a new supervised Neighborhood Discriminative Manifold Projection (NDMP) method for feature extraction in video-based face recognition. The abundance of data in videos often result in highly nonlinear appearance manifolds. In order to extract good discriminative features, an optimal low-dimensional projection is learned from selected face exemplars by solving a constrained least-squares objective function based on both local neighborhood geometry and global manifold structure. The discriminative ability is enhanced through the use of intra-class and inter-class neighborhood information. Experimental results on standard video databases and comparisons with state-of-art methods demonstrate the capability of NDMP in achieving high recognition accuracy.

Original languageEnglish
Title of host publicationImage Analysis and Processing. ICIAP 2011
EditorsG. Maino, G. L. Foresti
PublisherSpringer
Pages247-256
Number of pages10
ISBN (Electronic)9783642240850
ISBN (Print)9783642240843
DOIs
Publication statusPublished - 2011
Event16th International Conference on Image Analysis and Processing 2011 - Ravenna, Italy
Duration: 14 Sep 201116 Sep 2011

Publication series

NameLecture Notes in Computer Science
Volume6978
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference16th International Conference on Image Analysis and Processing 2011
Abbreviated titleICIAP 2011
CountryItaly
CityRavenna
Period14/09/1116/09/11

Keywords

  • feature extraction
  • Manifold learning
  • video-based face recognition

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Learning neighborhood discriminative manifolds for video-based face recognition'. Together they form a unique fingerprint.

Cite this