Feature learning via partial differential equation with applications to face recognition

Feature learning is a critical step in pattern recognition, such as image classification. However, most of the existing methods cannot extract features that are discriminative and at the same time invariant under some transforms. This limits the classification performance, especially in the case of...

Full description

Saved in:
Bibliographic Details
Main Authors: FANG, Cong, ZHAO, Zhenyu, ZHOU, Pan, LIN, Zhouchen
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2017
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9005
https://ink.library.smu.edu.sg/context/sis_research/article/10008/viewcontent/2017_PR_FE_PDE.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10008
record_format dspace
spelling sg-smu-ink.sis_research-100082024-07-25T08:16:06Z Feature learning via partial differential equation with applications to face recognition FANG, Cong ZHAO, Zhenyu ZHOU, Pan LIN, Zhouchen Feature learning is a critical step in pattern recognition, such as image classification. However, most of the existing methods cannot extract features that are discriminative and at the same time invariant under some transforms. This limits the classification performance, especially in the case of small training sets. To address this issue, in this paper we propose a novel Partial Differential Equation (PDE) based method for feature learning. The feature learned by our PDE is discriminative, also translationally and rotationally invariant, and robust to illumination variation. To our best knowledge, this is the first work that applies PDE to feature learning and image recognition tasks. Specifically, we model feature learning as an evolution process governed by a PDE, which is designed to be translationally and rotationally invariant and is learned via minimizing the training error, hence extracts discriminative information from data. After feature extraction, we apply a linear classifier for classification. We also propose an efficient algorithm that optimizes the whole framework. Our method is very effective when the training samples are few. The experimental results of face recognition on the four benchmark face datasets show that the proposed method outperforms the state-of-the-art feature learning methods in the case of low-resolution images and when the training samples are limited. 2017-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9005 info:doi/10.1016/J.PATCOG.2017.03.034 https://ink.library.smu.edu.sg/context/sis_research/article/10008/viewcontent/2017_PR_FE_PDE.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Feature learning Partial differential equation Fface recognition Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Feature learning
Partial differential equation
Fface recognition
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle Feature learning
Partial differential equation
Fface recognition
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
FANG, Cong
ZHAO, Zhenyu
ZHOU, Pan
LIN, Zhouchen
Feature learning via partial differential equation with applications to face recognition
description Feature learning is a critical step in pattern recognition, such as image classification. However, most of the existing methods cannot extract features that are discriminative and at the same time invariant under some transforms. This limits the classification performance, especially in the case of small training sets. To address this issue, in this paper we propose a novel Partial Differential Equation (PDE) based method for feature learning. The feature learned by our PDE is discriminative, also translationally and rotationally invariant, and robust to illumination variation. To our best knowledge, this is the first work that applies PDE to feature learning and image recognition tasks. Specifically, we model feature learning as an evolution process governed by a PDE, which is designed to be translationally and rotationally invariant and is learned via minimizing the training error, hence extracts discriminative information from data. After feature extraction, we apply a linear classifier for classification. We also propose an efficient algorithm that optimizes the whole framework. Our method is very effective when the training samples are few. The experimental results of face recognition on the four benchmark face datasets show that the proposed method outperforms the state-of-the-art feature learning methods in the case of low-resolution images and when the training samples are limited.
format text
author FANG, Cong
ZHAO, Zhenyu
ZHOU, Pan
LIN, Zhouchen
author_facet FANG, Cong
ZHAO, Zhenyu
ZHOU, Pan
LIN, Zhouchen
author_sort FANG, Cong
title Feature learning via partial differential equation with applications to face recognition
title_short Feature learning via partial differential equation with applications to face recognition
title_full Feature learning via partial differential equation with applications to face recognition
title_fullStr Feature learning via partial differential equation with applications to face recognition
title_full_unstemmed Feature learning via partial differential equation with applications to face recognition
title_sort feature learning via partial differential equation with applications to face recognition
publisher Institutional Knowledge at Singapore Management University
publishDate 2017
url https://ink.library.smu.edu.sg/sis_research/9005
https://ink.library.smu.edu.sg/context/sis_research/article/10008/viewcontent/2017_PR_FE_PDE.pdf
_version_ 1814047689882468352