Local Gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition

TLDR

Face recognition has traditionally relied on subspace discriminant analysis or statistical learning, which often suffer from limited generalizability. This work introduces the local Gabor binary pattern histogram sequence (LGBPHS), a non‑statistical representation that eliminates the need for a training phase and thereby addresses generalizability issues. LGBPHS models a face as a concatenated histogram sequence of local Gabor magnitude binary pattern maps, and recognition is performed by histogram intersection with weighted histograms and nearest‑neighbor classification. Experiments on the AR and FERET databases demonstrate that LGBPHS is effective for partially occluded faces and achieves the best performance reported on FERET.

Abstract

For years, researchers in face recognition area have been representing and recognizing faces based on subspace discriminant analysis or statistical learning. Nevertheless, these approaches are always suffering from the generalizability problem. This paper proposes a novel non-statistics based face representation approach, local Gabor binary pattern histogram sequence (LGBPHS), in which training procedure is unnecessary to construct the face model, so that the generalizability problem is naturally avoided. In this approach, a face image is modeled as a "histogram sequence" by concatenating the histograms of all the local regions of all the local Gabor magnitude binary pattern maps. For recognition, histogram intersection is used to measure the similarity of different LGBPHSs and the nearest neighborhood is exploited for final classification. Additionally, we have further proposed to assign different weights for each histogram piece when measuring two LGBPHSes. Our experimental results on AR and FERET face database show the validity of the proposed approach especially for partially occluded face images, and more impressively, we have achieved the best result on FERET face database.