Human detection using non-negative matrix factorization

Jing Xiu Zeng, Chih Yang Lin, Wei Yang Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Currently, most of the human detection methods are based on low-level features. In this paper, we proposed a middle-level feature generation method based on non-negative matrix factorization (NMF) for human detection. We also proposed an improvement scheme to guarantee that a better middle-level feature can be achieved. The proposed scheme can be applied to a complex background and the experimental results are better than those when only the low-level feature is involved.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages370-371
Number of pages2
ISBN (Electronic)9781479987443
DOIs
StatePublished - 20 Aug 2015
Event2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015 - Taipei, Taiwan
Duration: 6 Jun 20158 Jun 2015

Publication series

Name2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015

Conference

Conference2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
Country/TerritoryTaiwan
CityTaipei
Period6/06/158/06/15

Keywords

  • Biomedical imaging
  • Computer vision
  • Conferences
  • Feature extraction
  • Pattern recognition
  • Testing
  • Training

Fingerprint

Dive into the research topics of 'Human detection using non-negative matrix factorization'. Together they form a unique fingerprint.

Cite this