Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Cho-Ying, Ding, Jian-Jiun
Format: Preprint
Veröffentlicht: 2019
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909321131982848
author Wu, Cho-Ying
Ding, Jian-Jiun
author_facet Wu, Cho-Ying
Ding, Jian-Jiun
contents In this paper, a very effective method to solve the contiguous face occlusion recognition problem is proposed. It utilizes the robust image gradient direction features together with a variety of mapping functions and adopts a hierarchical sparse and low-rank regression model. This model unites the sparse representation in dictionary learning and the low-rank representation on the error term that is usually messy in the gradient domain. We call it the "weak low-rankness" optimization problem, which can be efficiently solved by the framework of Alternating Direction Method of Multipliers (ADMM). The optimum of the error term has a similar weak low-rank structure as the reference error map and the recognition performance can be enhanced by leaps and bounds using weak low-rankness optimization. Extensive experiments are conducted on real-world disguise / occlusion data and synthesized contiguous occlusion data. These experiments show that the proposed gradient direction-based hierarchical adaptive sparse and low-rank (GD-HASLR) algorithm has the best performance compared to state-of-the-art methods, including popular convolutional neural network-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_1906_02429
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction
Wu, Cho-Ying
Ding, Jian-Jiun
Image and Video Processing
Computer Vision and Pattern Recognition
Numerical Analysis
In this paper, a very effective method to solve the contiguous face occlusion recognition problem is proposed. It utilizes the robust image gradient direction features together with a variety of mapping functions and adopts a hierarchical sparse and low-rank regression model. This model unites the sparse representation in dictionary learning and the low-rank representation on the error term that is usually messy in the gradient domain. We call it the "weak low-rankness" optimization problem, which can be efficiently solved by the framework of Alternating Direction Method of Multipliers (ADMM). The optimum of the error term has a similar weak low-rank structure as the reference error map and the recognition performance can be enhanced by leaps and bounds using weak low-rankness optimization. Extensive experiments are conducted on real-world disguise / occlusion data and synthesized contiguous occlusion data. These experiments show that the proposed gradient direction-based hierarchical adaptive sparse and low-rank (GD-HASLR) algorithm has the best performance compared to state-of-the-art methods, including popular convolutional neural network-based methods.
title Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction
topic Image and Video Processing
Computer Vision and Pattern Recognition
Numerical Analysis
url https://arxiv.org/abs/1906.02429