Face Recognition 1:N – Identify

Model by Trueface

Given one image, the model will identify the person in question from a database of known identities.
  • Description

    Product Description

    PERFORMANCE METRICS:

    98.4% on the Megaface Challenge.

    The fraction of correct predictions made by the classifier. This metric is calculated by dividing the number of correct predictions by the total number of predictions.

    Further information here.

    OVERVIEW:

    This model uses a Deep Neural Network (DNN), which was trained end-to-end on large scale face recognition datasets covering all ethnicities and genders.

    TRAINING:

    This model was trained end-to-end on large scale face recognition datasets covering all ethnicities and genders.

    VALIDATION:

    On an internal benchmark, the algorithm was able to search through a collection of 100 million identities in less than 1 second. Each face template created and corresponding metadata is only 1Kb in size. Therefore, a collection of 1 million identities only requires 1 GB of RAM.