Palm vein biometrics based on infrared imaging and complex matched filtering

  • Authors:
  • Modris Greitans;Mihails Pudzs;Rihards Fuksis

  • Affiliations:
  • Institute of Electronics and Computer Science, Riga, Latvia;Institute of Electronics and Computer Science, Riga, Latvia;Institute of Electronics and Computer Science, Riga, Latvia

  • Venue:
  • Proceedings of the 12th ACM workshop on Multimedia and security
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, the use of the palm vein pattern for biometrics is discussed. To obtain pictures of blood vessels, two methods of infrared imaging -- reflection and transmission are investigated. Basic image processing methods for extraction of vein structure are discussed. Complex matched filtering result provides matching intensity vectors that are used to segment the vessels. The similarity index of vector sets of two images is introduced to recognize vein pattern of the individual person. Experimental results of person identification are obtained using palm infrared image database from 50 people. The achieved Equal error rate of proposed method for the used database is 0.17%.