Skip to main content

Package for BioSIG-2017 paper on Extended-Range imaging for 3D-Mask PAD.

Project description

This package is part of the Bob toolkit. Scripts in this package can be used to reproduce face-PAD results the following paper:

@inproceedings{bhattacharjeeBiosig2017,
author = {Sushil Bhattacharjee and S{\'{e}}bastien Marcel},
title = {What you can't see can help you -- extended range imaging for 3d-mask presentation attack detection},
year = {2017},
month = sep,
booktitle = {Proceedings of the 16th International Conference of the Biometrics Special Interest Group (BIOSIG)},
address = {Darmstadt, Germany},
}
                                                    §

If you use this package and/or its results, please cite the paper.

Installation

The installation instructions are based on conda and works on Linux systems only. Install conda before continuing.

Once you have installed conda, download the source code of this paper and unpack it. Then, you can create a conda environment with the following command:

$ cd bob.paper.biosig2017_3dmaskprestudy
$ conda env create -f environment.yml
$ source activate bob.paper.biosig2017_3dmaskprestudy  # activate the environment
$ buildout

This will install all the required software to reproduce this paper.

Downloading the dataset

This package works with the ERPA dataset published by IDIAP. Please download the dataset before proceeding.

Generating the plot

Figure 5 in the paper shows distributions of the mean pixel-values of the face-region in the thermal images captured using the Xenics Gobi camera. To reproduce this plot, use the following command:

$ ./bin/thermal_mean_hist.py -ip <input-ERPA-folder>/Xenics_Gobi/ -op <output-plot-folder>

where <input-ERPA-folder> should be the folder containing the ERPA dataset, and <output-plot-folder> should specify the folder where you want the plot to be created as a pdf file. This command will process images from the ‘Xenics_Gobi’ sub-folder in the specified input-folder (<input-ERPA-folder>), and create a file called thermal_profile_hist.pdf in the specified output folder.

Project details


Release history Release notifications

Download files

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

Filename, size & hash SHA256 hash help File type Python version Upload date
bob.paper.biosig2017_3dmaskprestudy-1.0.0.zip (37.3 kB) Copy SHA256 hash SHA256 Source None Oct 23, 2017

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page