Local feature hierarchy for face recognition across pose and illumination

07/12/2016
by   Xiaoyue Jiang, et al.
0

Even though face recognition in frontal view and normal lighting condition works very well, the performance degenerates sharply in extreme conditions. Recently there are many work dealing with pose and illumination problems, respectively. However both the lighting and pose variation will always be encountered at the same time. Accordingly we propose an end-to-end face recognition method to deal with pose and illumination simultaneously based on convolutional networks where the discriminative nonlinear features that are invariant to pose and illumination are extracted. Normally the global structure for images taken in different views is quite diverse. Therefore we propose to use the 1*1 convolutional kernel to extract the local features. Furthermore the parallel multi-stream multi-layer 1*1 convolution network is developed to extract multi-hierarchy features. In the experiments we obtained the average face recognition rate of 96.9 state-of-the-art of face recognition across poses and illumination by 7.5 Especially for profile-wise positions, the average recognition rate of our proposed network is 97.8 rate by 19

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

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
08/01/2018

Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate

In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block...
research
02/22/2022

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

We present a new method for face recognition from digital images acquire...
research
08/01/2013

Compositional Dictionaries for Domain Adaptive Face Recognition

We present a dictionary learning approach to compensate for the transfor...
research
12/05/2013

An adaptive block based integrated LDP,GLCM,and Morphological features for Face Recognition

This paper proposes a technique for automatic face recognition using int...
research
11/16/2013

Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?

The standard approach to unconstrained face recognition in natural photo...
research
03/27/2023

FaceLit: Neural 3D Relightable Faces

We propose a generative framework, FaceLit, capable of generating a 3D f...

Please sign up or login with your details

Forgot password? Click here to reset