Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Fingerprint image enhancement using CNN filtering techniques.

Ertugrul Saatci1, Vedat Tavsanoglu

  • 1Faculty of Engineering, Science and The Built Environment, London South Bank University, Borough Road, SE1 0AA, London, UK. saatcie@lsbu.ac.uk.

International Journal of Neural Systems
|March 20, 2004
PubMed
Summary

This study enhances fingerprint images corrupted by noise using CNN Gabor-Type filters. This method improves ridge pattern accuracy for more effective fingerprint recognition.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Determination of Respiratory Parameters by Means of Hurst Exponents of the Respiratory Sounds and Stochastic Processing Methods.

IEEE transactions on bio-medical engineering·2021
Same author

Analysis of linear lung models based on state-space models.

Computer methods and programs in biomedicine·2019
Same author

Disturbance in long distance gamma coherence in bipolar disorder.

Progress in neuro-psychopharmacology & biological psychiatry·2010
Same author

Decrease of evoked delta, theta and alpha coherences in Alzheimer patients during a visual oddball paradigm.

Brain research·2008

Area of Science:

  • Biometrics
  • Image Processing
  • Computer Vision

Background:

  • Fingerprint images are often degraded by noise from acquisition devices and varying conditions.
  • Noise like cracks, scratches, and blurs leads to matching errors in fingerprint recognition systems.
  • Accurate ridge patterns are crucial for effective fingerprint identification.

Purpose of the Study:

  • To propose an effective fingerprint image enhancement method.
  • To address the challenges posed by noise in fingerprint recognition.
  • To improve the accuracy of fingerprint matching through enhanced ridge patterns.

Main Methods:

  • Analyzing fingerprint patterns segment by segment to determine ridge direction and frequency.
  • Utilizing Convolutional Neural Network (CNN) Gabor-Type filters for enhancement.

Related Experiment Videos

  • Selecting directional filters with appropriate parameters to match local ridge features.

    • Main Results:

    • The proposed CNN Gabor-Type filter approach effectively enhances corrupted fingerprint ridges.
    • Improved ridge clarity reduces matching errors in fingerprint recognition.
    • Accurate ridge enhancement leads to more reliable fingerprint identification.

    Conclusions:

    • CNN Gabor-Type filters offer a robust solution for fingerprint image enhancement.
    • This technique significantly improves the quality of fingerprint images for biometric applications.
    • The proposed method contributes to more accurate and reliable fingerprint recognition systems.