Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition

02/22/2022
by   Yan Zhuang, et al.
7

We present a new method for face recognition from digital images acquired under varying illumination conditions. The method is based on mathematical modeling of local gradient distributions using the Radon Cumulative Distribution Transform (R-CDT). We demonstrate that lighting variations cause certain types of deformations of local image gradient distributions which, when expressed in R-CDT domain, can be modeled as a subspace. Face recognition is then performed using a nearest subspace in R-CDT domain of local gradient distributions. Experiment results demonstrate the proposed method outperforms other alternatives in several face recognition tasks with challenging illumination conditions. Python code implementing the proposed method is available, which is integrated as a part of the software package PyTransKit.

READ FULL TEXT

page 1

page 3

page 7

page 9

research
05/10/2019

Illumination Normalization via Merging Locally Enhanced Textures for Robust Face Recognition

In order to improve the accuracy of face recognition under varying illum...
research
12/11/2012

Robust Face Recognition using Local Illumination Normalization and Discriminant Feature Point Selection

Face recognition systems must be robust to the variation of various fact...
research
07/12/2016

Local feature hierarchy for face recognition across pose and illumination

Even though face recognition in frontal view and normal lighting conditi...
research
09/27/2005

Automatic Face Recognition System Based on Local Fourier-Bessel Features

We present an automatic face verification system inspired by known prope...
research
02/25/2017

An EM Based Probabilistic Two-Dimensional CCA with Application to Face Recognition

Recently, two-dimensional canonical correlation analysis (2DCCA) has bee...
research
06/01/2015

Robust Face Recognition with Structural Binary Gradient Patterns

This paper presents a computationally efficient yet powerful binary fram...
research
06/27/2012

Deep Lambertian Networks

Visual perception is a challenging problem in part due to illumination v...

Please sign up or login with your details

Forgot password? Click here to reset