Image processing

TL;DR

This paper introduces Gabor Surface Feature (GSF), a novel face recognition method that fully describes Gabor magnitude pictures as smooth surfaces by analyzing derivatives and constructing joint histograms, demonstrating improved performance on standard datasets.

Contribution

The paper proposes a new face recognition approach that models Gabor magnitude images as surfaces using derivatives, enhancing feature representation over existing methods.

Findings

GSF outperforms previous methods on FERET, ORL, and FRGC databases.

Incorporating derivatives improves face recognition accuracy.

Joint histograms effectively capture surface shape information.

Abstract

Gabor filters can extract multi-orientation and multiscale features from face images. Researchers have designed different ways to use the magnitude of the filtered results for face recognition: Gabor Fisher classifier exploited only the magnitude information of Gabor magnitude pictures (GMPs); Local Gabor Binary Pattern uses only the gradient information. In this paper, we regard GMPs as smooth surfaces. By completely describing the shape of GMPs, we get a face representation method called Gabor Surface Feature (GSF). First, we compute the magnitude, 1st and 2nd derivatives of GMPs, then binarize them and transform them into decimal values. Finally we construct joint histograms and use subspace methods for classification. Experiments on FERET, ORL and FRGC 1.0.4 database show the effectiveness of GSF.