An Enhanced Deep Feature Representation for Person Re-identification

TL;DR

This paper introduces Feature Fusion Net (FFN), a novel deep feature extraction model that combines handcrafted histogram features with CNN features to improve person re-identification accuracy.

Contribution

The paper proposes a new feature fusion approach that constrains CNN features with handcrafted histogram features, enhancing discriminative power in person re-identification.

Findings

Improved accuracy on VIPeR, CUHK01, PRID450s datasets.

Fusion of color and texture features enhances discriminability.

Demonstrates effectiveness of combining handcrafted and CNN features.

Abstract

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.