Manifold learning based on multi-feature for road-sign recognition

Qieshi Zhang, Seiichiro Kamata

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

1 Citation (Scopus)

Abstract

In this paper, a multi-feature selection and application based manifold learning metric method is proposed for Road-Sign Recognition (RSR). Firstly, the manifold metric between manifold from subspace is discussed in detail. After that, the multi-feature analyzing, selection, classification and application are introduced for rough recognition and create the manifold. Then the proposed method is used to evaluate the distance between the manifolds. Finally, the RSR results suggest that the proposed method is robust than other methods.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1143-1146
Number of pages4
Publication statusPublished - 2011
Event50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 - Tokyo
Duration: 2011 Sep 132011 Sep 18

Other

Other50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011
CityTokyo
Period11/9/1311/9/18

    Fingerprint

Keywords

  • Feature Analyzing
  • Feature Selection
  • Manifold Learning
  • Road-Sign Recognition (RSR)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Zhang, Q., & Kamata, S. (2011). Manifold learning based on multi-feature for road-sign recognition. In Proceedings of the SICE Annual Conference (pp. 1143-1146). [6060505]