A simple toolchain that performs anti-spoofing on the LivDet2013 database

To edit a toolchain, please use a modern browser (Mozilla Firefox 3.0+, Google Chrome 1+, Apple Safari 3+, Opera 9.5+, Microsoft Internet Explorer 9+)

This toolchain will first train an LDA projection using all the training data available. Because this is a binary classification problem, 1 LDA component will be left-over after this step.

Once the LDA vector has been estimated, each sample on the training set is projected through this vector in order to compress the input data into a single score, which is then used for classification.

Updated Name Databases/Protocols Analyzers
anjos/anjos/livdet-lda/1/livdet-2013-biometrika-test livdet2013/1@Biometrika anjos/livdet_analysis/1
Terms of Service | Contact Information | BEAT platform version 2.2.1b0 | © Idiap Research Institute - 2013-2024