Fast fingerprint orientation field estimation incorporating general purpose GPU

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

5 Citations (Scopus)


Fingerprint is one of the broadly utilized biometric traits for personal identification in both civilian and forensic applications due to its high acceptability, strong security, and low cost. Fingerprint ridge orientation is one of the global fingerprint representations that keeps the holistic ridge structure in a small storage area. The importance of fingerprint ridge orientation comes from its usage in fingerprint singular point detection, coarse level classification, and fingerprint alignment. However, processing time is an important factor in any automatic fingerprint identification system, estimating that ridge orientation image may consume long processing time. This research presents an efficient ridge orientation estimation approach by incorporating a Graphics Processing Unit (GPU) capability to the traditional pixel gradient method. The simulation work shows a significant enhancement in ridge orientation estimation time by 6.41x using a general purpose GPU in comparison to the CPU execution.

Original languageEnglish
Title of host publicationSoft Computing Applications - Proceedings of the 6th International Workshop Soft Computing Applications, SOFA 2014
EditorsValentina Emilia Balas, Branko Kovačević, Lakhmi C. Jain
PublisherSpringer Verlag
Number of pages12
ISBN (Print)9783319184159
Publication statusPublished - 2016
Externally publishedYes
Event6th International Workshop Soft Computing Applications, SOFA 2014 - Timisoara, Romania
Duration: Jul 24 2014Jul 26 2014

Publication series

NameAdvances in Intelligent Systems and Computing
ISSN (Print)2194-5357


Conference6th International Workshop Soft Computing Applications, SOFA 2014


  • Fingerprints
  • GPU
  • Parallel processing
  • Ridge orientation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this