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

DMCA

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

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Wenchao Zhang , Shiguang Shan , Wen Gao , Xilin Chen , Hongming Zhang

Venue:	in Proc. IEEE Int. Conf. Computer Vision
Citations:	150 - 11 self

BibTeX

@INPROCEEDINGS{Zhang_localgabor,
    author = {Wenchao Zhang and Shiguang Shan and Wen Gao and Xilin Chen and Hongming Zhang},
    title = {Local Gabor binary pattern histogram sequence (LGBPHS): A novel non-statistical model for face representation and recognition},
    booktitle = {in Proc. IEEE Int. Conf. Computer Vision},
    year = {},
    pages = {786--791}
}

OpenURL

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 LGBPHSes 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. 1.

Keyphrases

face representation novel non-statistical model feret face database generalizability problem face image training procedure final classification different weight occluded face image face recognition area different lgbphses face model novel non-statistics histogram intersection face representation approach statistical learning histogram piece experimental result local region subspace discriminant analysis histogram sequence

DMCA