Image description with 1D local patterns by multi-scans: An application to face recognition

Wei Zhou, Alireza Ahrary, Seiichiro Kamata

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

4 Citations (Scopus)

Abstract

In this work, a novel approach which called 1D local patterns by multi-scans(1DLPMS) for presenting the local features is proposed and its simplifications and extensions to facial image analysis are also considered. First, multi-scans are applied to capture different spatial information on the image with less computation than some traditional ways, such as Local Binary Patterns(LBP). Then, some 1D local patterns are given to encode the local features based on different coding rules. To make the proposed approach computationally simpler and easy to extend, grouped 1D local patterns by multiscans( G1DLPMS) is studied, which divides 1DLPMS into several groups and uses the co-occurrences of these groups. Performance assessment in face recognition under different challenges shows that the proposed approach is superior than traditional ones.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages4553-4556
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong
Duration: 2010 Sep 262010 Sep 29

Other

Other2010 17th IEEE International Conference on Image Processing, ICIP 2010
CityHong Kong
Period10/9/2610/9/29

    Fingerprint

Keywords

  • 1DLPMS
  • Face recognition
  • G1DLPMS
  • Local presentation
  • Multi-scans

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Zhou, W., Ahrary, A., & Kamata, S. (2010). Image description with 1D local patterns by multi-scans: An application to face recognition. In Proceedings - International Conference on Image Processing, ICIP (pp. 4553-4556). [5650586] https://doi.org/10.1109/ICIP.2010.5650586