Face recognition with local gradient derivative patterns

Xianchun Zheng*, Sei Ichiro Kamata, Liang Yu

*Corresponding author for this work

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

1 Citation (Scopus)


In this work, we present a novel local pattern descriptor, Local Gradient Derivative Pattern (LGDP) to face recognition which considers more detailed information than the Local Binary Pattern (LBP). The face image is first divided into several small regions from which Local Gradient Derivative Pattern (LGDP) histograms are extracted and concatenated into a single, spatially enhanced feature vector to be used as a face descriptor. Three well-known and challenge-ORL, Yale and FERET face databases are used in the performances to evaluate the method. The experiments result clearly show that the proposed method give us a better performance than some other methods.

Original languageEnglish
Title of host publicationTENCON 2010 - 2010 IEEE Region 10 Conference
Number of pages4
Publication statusPublished - 2010 Dec 1
Event2010 IEEE Region 10 Conference, TENCON 2010 - Fukuoka, Japan
Duration: 2010 Nov 212010 Nov 24

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON


Other2010 IEEE Region 10 Conference, TENCON 2010


  • Face recognition
  • Histogram
  • Local Gradient Derivative Patterns (LGDP)

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Face recognition with local gradient derivative patterns'. Together they form a unique fingerprint.

Cite this