Evaluation of Acceleration Algorithm for Biometric Identification

Serina Egawa, Ali Ismail Awad, Kensuke Baba

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

17 Citations (Scopus)

Abstract

This paper evaluates an existing acceleration algorithm for biometric identification. In identification based on biometric images, the number of image comparisons is an important factor to estimate the total processing time in addition to the processing time of a single image comparison. Maeda et al. proposed an identification algorithm which reduces the number of image comparisons. This paper evaluates the algorithm in terms of the time and the accuracy with the features extracted by SIFT from palmprint images. The evaluation in this paper proves that the algorithm is applicable to the SIFT-based palmprint features. However, the evaluation also proves that an overhead of the algorithm requires the processing time which depends on the database size. Therefore, for an identification system with a large database, the total processing time of an identification is not reduced by a straightforward application of the algorithm by Maeda et al.

Original languageEnglish
Title of host publicationNetworked Digital Technologies- 4th International Conference, NDT 2012, Proceedings
EditorsRachid Benlamri
Pages231-242
Number of pages12
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event4th International Conference on Networked Digital Technologies, NDT 2012 - Dubai, United Arab Emirates
Duration: Apr 24 2012Apr 26 2012

Publication series

NameCommunications in Computer and Information Science
Volume294 PART 2
ISSN (Print)1865-0929

Conference

Conference4th International Conference on Networked Digital Technologies, NDT 2012
CountryUnited Arab Emirates
CityDubai
Period4/24/124/26/12

Keywords

  • biometrics
  • palmprint
  • Personal identification
  • SIFT

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Evaluation of Acceleration Algorithm for Biometric Identification'. Together they form a unique fingerprint.

Cite this