Robust Eye Centers Localization with Zero--Crossing Encoded Image Projections

TL;DR

This paper introduces a novel eye center localization method using zero-crossing encoded image projections combined with an MLP classifier, achieving fast and reliable results in unconstrained environments.

Contribution

It presents a new encoding of normalized image projections based on zero-crossings and a trained MLP for improved eye center detection.

Findings

Effective on multiple face databases including LFW and Yale B.

Fast and reliable localization in unconstrained environments.

Outperforms existing methods in accuracy and speed.

Abstract

This paper proposes a new framework for the eye centers localization by the joint use of encoding of normalized image projections and a Multi Layer Perceptron (MLP) classifier. The encoding is novel and it consists in identifying the zero-crossings and extracting the relevant parameters from the resulting modes. The compressed normalized projections produce feature descriptors that are inputs to a properly-trained MLP, for discriminating among various categories of image regions. The proposed framework forms a fast and reliable system for the eye centers localization, especially in the context of face expression analysis in unconstrained environments. We successfully test the proposed method on a wide variety of databases including BioID, Cohn-Kanade, Extended Yale B and Labelled Faces in the Wild (LFW) databases.