Automatic Face Recognition from Video

TL;DR

This paper introduces advanced face recognition techniques from videos under challenging conditions, significantly improving accuracy over existing methods by leveraging face appearance manifolds and novel clustering algorithms.

Contribution

It presents the Generic Shape-Illumination Manifold recognition algorithm and the Anisotropic Manifold Space clustering method, advancing face recognition in unconstrained, real-world video scenarios.

Findings

The Generic Shape-Illumination Manifold outperforms state-of-the-art methods.

The algorithms work effectively with low-quality, variable-condition video data.

Preliminary results show promising performance in real-world applications.

Abstract

The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide variability, and video input is of low quality. At the centre of focus are face appearance manifolds: this thesis presents a significant advance of their understanding and application in the sphere of face recognition. The two main contributions are the Generic Shape-Illumination Manifold recognition algorithm and the Anisotropic Manifold Space clustering. The Generic Shape-Illumination Manifold is evaluated on a large data corpus acquired in real-world conditions and its performance is shown to greatly exceed that of state-of-the-art methods in the literature and the best performing commercial software. Empirical evaluation of the Anisotropic Manifold Space clustering on a popular situation comedy is also described with excellent preliminary results.