An Enhanced Deep Feature Representation for Person Re-identification

Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features. We propose a novel feat...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2016-04
Main Authors: Wu, Shangxuan, Ying-Cong, Chen, Li, Xiang, An-Cong, Wu, Jin-Jie, You, Wei-Shi, Zheng
Format: Article
Language:English
Subjects:
Artificial neural networks
Back propagation
Critical components
Feature extraction
Histograms
Neural networks
Representations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features. We propose a novel feature extraction model called Feature Fusion Net (FFN) for pedestrian image representation. In FFN, back propagation makes CNN features constrained by the handcrafted features. Utilizing color histogram features (RGB, HSV, YCbCr, Lab and YIQ) and texture features (multi-scale and multi-orientation Gabor features), we get a new deep feature representation that is more discriminative and compact. Experiments on three challenging datasets (VIPeR, CUHK01, PRID450s) validates the effectiveness of our proposal.
ISSN:2331-8422
DOI:10.48550/arxiv.1604.07807