Skip to main content

Evaluation tools for verification systems under spoofing attacks: examples in face verification

Project description

This package provides methods for evaluation of biometric verification systems under spoofing attacks. The evaluation is based on the Expected Performance and Spoofability Curve (EPSC). Using this package, you can compute thresholds based on EPSC, compute various error rates and plot various curves related to EPSC.

Besides providing methods for plotting EPSC within your own scripts, this package brings several scripts that you can use to evaluate your own verification system from several perspectives. For example, you can:
  • evaluate the threshold of a classification system on the development set

  • apply the threshold on an evaluation or any other set to compute different error rates

  • plot score distributions

  • plot different performance curves (DET, EPC and EPSC)

Furthermore, you can generate hypothetical data and use them to exemplify the above mentioned functionalities.

Finally, several scripts enable you to evaluate 4 state-of-the-art face verification systems, before and after they are fused with an anti-spoofing system for better robustness to spoofing. The scripts enable you to plot the relevant curves of the systems together and compare them.

Please refer to the documentation for a full Reference Manual and User Guide.

Installation

There are 2 options you can follow to get this package installed and operational on your computer: you can use automatic installers like pip (or easy_install) or manually download, unpack and use zc.buildout to create a virtual work environment just for this package.

Using an automatic installer

Using pip is the easiest (shell commands are marked with a $ signal):

$ pip install antispoofing.utils

You can also do the same with easy_install:

$ easy_install antispoofing.utils

This will download and install this package plus any other required dependencies. It will also verify if the version of Bob you have installed is compatible.

This scheme works well with virtual environments by virtualenv or if you have root access to your machine. Otherwise, we recommend you use the next option.

Using zc.buildout

Download the latest version of this package from PyPI and unpack it in your working area. The installation of the toolkit itself uses buildout. You don’t need to understand its inner workings to use this package. Here is a recipe to get you started:

$ python bootstrap.py
$ ./bin/buildout

These 2 commands should download and install all non-installed dependencies and get you a fully operational test and development environment.

Problems

In case of problems, please contact ivana.chingovska@idiap.ch

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

antispoofing.evaluation-1.0.0.zip (39.5 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page