Icon of program: Correlation Filters AFIS

Correlation Filters AFIS for Windows

Download now

Used Correlation Filters AFIS for Windows?

Editors’ Review

Download.com staff
This Matlab source code implements an automated fingerprint identification system (AFIS). It uses advanced correlation filters to test image authenticity by analyzing correlation peak outputs to distinguish between authentic users and impostors.

  • Pros

    • Provides Matlab source code for fingerprint identification
    • Classifier features graceful degradation and shift invariance
    • Utilizes closed-form solutions for computation
    • Achieves a low one-to-many identification error rate (
    • Authenticates images using image intensity domain analysis

  • Cons

    • Requires Matlab environment for execution
    • Validation performed on a small fingerprint database
    • Reported Equal Error Rate for verification is 5.6641%
    • Tested with data from a single sensor type
    • Lacks a graphical user interface for interaction
Icon of program: Correlation Filters AFIS

Correlation Filters AFIS for Windows

Download now

Used Correlation Filters AFIS for Windows?

Explore More

Full Specifications

GENERAL
Release
Latest update
Version
1.0
OPERATING SYSTEMS
Platform
Windows
Operating System
  • Windows NT
  • Windows 10
  • Windows Server
  • Windows Vista
  • Windows 7
  • Windows 8
  • Windows ME
  • Windows 98
  • Windows 2000
  • Windows XP
  • Windows 2003
Additional Requirements
Matlab
POPULARITY
Total Downloads
148
Downloads Last Week
14
Report Software

Program available in other languages

Last Updated

Developer’s Description

By Luigi Rosa
Test the authenticity of a target image using correlation filters AFIS.
The theory of advanced correlation filters has evolved from the literature of optical pattern recognition in the last two decades; they have proved effective classifiers in a number of applications, among them biometric recognition and automatic target recognition. Correlation filter designs use the image intensity domain of training examples to compute a class template that produces characteristic correlation outputs to distinguish between authentic users and impostors. When applying the filter for testing the authenticity of a new target image, the output plane is expected to have a shape containing a correlation peak if the image is authentic, but no such peak if the image belongs to another class. Properties of correlation filter classifiers include graceful degradation, shift invariance and closed-form solutions.

The code has been tested using fingerprint images taken with an UPEK swipe fingerprint reader with capacitive sensor and USB 2.0 connection. Database is 16 fingers wide and 8 impressions per finger deep (128 fingerprints in all). We have obtained the following results:One-to-many fingerprint identification: using 2 images for each finger randomly selected for training and the remaining 6 images for testing (totally 32 images for training and 96 images for testing), without any overlapping, we have obtained an error rate smaller than 0.6% (top one error rate).One-to-one fingerprint verification: we have obtained an EER equal to 5.6641%.Index Terms: Matlab, source, code, correlation, filters, AFIS, automated, fingerprint, identification, system.

Download.com
Your review for Correlation Filters AFIS