Efficient large-scale video retrieval via discriminative signatures

Pengyi Hao, Seiichiro Kamata

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The topic of retrieving videos containing a desired person from a dataset just using the content of faces without any help of textual information has many interesting applications like video surveillance, social network, video mining, etc. However, traditional face matching against a huge number of detected faces leads to an unacceptable response time and may also reduce the accuracy due to the large variations in facial expressions, poses, lighting, etc. Therefore, in this paper we propose a novel method to generate discriminative "signatures" for efficiently retrieving the videos containing the same person with a query. In this research, the signature is defined as a compact, discriminative and reduced dimensionality representation, which is generated from a set of high-dimensional feature vectors of an individual. The desired videos are retrieved based on the similarities between the signature of the query and those of individuals in the database. In particular, we make the following contributions. Firstly, we give an algorithm of two directional linear discriminant analysis with maximum correntropy criterion (2DLDA-MCC) as an extension to our recently proposed maximum correntropy criterion based linear discriminant analysis (LDA-MCC). Both algorithms are robust to outliers and noise. Secondly, we present an approach for transferring a set of exemplars to a fixed-length signature using LDA-MCC and 2DLDA-MCC, resulting in two kinds of signatures that are called 1D signature and 2D signature. Finally, a novel video retrieval scheme is given based on the signatures, which has low storage requirement and can achieve a fast search. Evaluations on a large dataset of videos show reliable measurement of similarities by using the proposed signatures to represent the identities generated from videos. Experimental results also demonstrate that the proposed video retrieval scheme has the potential to substantially reduce the response time and slightly increase the mean average precision of retrieval.

Original languageEnglish
Pages (from-to)1800-1810
Number of pages11
JournalIEICE Transactions on Information and Systems
VolumeE96-D
Issue number8
DOIs
Publication statusPublished - 2013

Fingerprint

Discriminant analysis
Lighting

Keywords

  • Individual retrieval
  • Linear discriminant analysis
  • Signature
  • Video dataset

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Efficient large-scale video retrieval via discriminative signatures. / Hao, Pengyi; Kamata, Seiichiro.

In: IEICE Transactions on Information and Systems, Vol. E96-D, No. 8, 2013, p. 1800-1810.

Research output: Contribution to journalArticle

@article{330551bb9ed94a54b41de00b5396cd32,
title = "Efficient large-scale video retrieval via discriminative signatures",
abstract = "The topic of retrieving videos containing a desired person from a dataset just using the content of faces without any help of textual information has many interesting applications like video surveillance, social network, video mining, etc. However, traditional face matching against a huge number of detected faces leads to an unacceptable response time and may also reduce the accuracy due to the large variations in facial expressions, poses, lighting, etc. Therefore, in this paper we propose a novel method to generate discriminative {"}signatures{"} for efficiently retrieving the videos containing the same person with a query. In this research, the signature is defined as a compact, discriminative and reduced dimensionality representation, which is generated from a set of high-dimensional feature vectors of an individual. The desired videos are retrieved based on the similarities between the signature of the query and those of individuals in the database. In particular, we make the following contributions. Firstly, we give an algorithm of two directional linear discriminant analysis with maximum correntropy criterion (2DLDA-MCC) as an extension to our recently proposed maximum correntropy criterion based linear discriminant analysis (LDA-MCC). Both algorithms are robust to outliers and noise. Secondly, we present an approach for transferring a set of exemplars to a fixed-length signature using LDA-MCC and 2DLDA-MCC, resulting in two kinds of signatures that are called 1D signature and 2D signature. Finally, a novel video retrieval scheme is given based on the signatures, which has low storage requirement and can achieve a fast search. Evaluations on a large dataset of videos show reliable measurement of similarities by using the proposed signatures to represent the identities generated from videos. Experimental results also demonstrate that the proposed video retrieval scheme has the potential to substantially reduce the response time and slightly increase the mean average precision of retrieval.",
keywords = "Individual retrieval, Linear discriminant analysis, Signature, Video dataset",
author = "Pengyi Hao and Seiichiro Kamata",
year = "2013",
doi = "10.1587/transinf.E96.D.1800",
language = "English",
volume = "E96-D",
pages = "1800--1810",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "8",

}

TY - JOUR

T1 - Efficient large-scale video retrieval via discriminative signatures

AU - Hao, Pengyi

AU - Kamata, Seiichiro

PY - 2013

Y1 - 2013

N2 - The topic of retrieving videos containing a desired person from a dataset just using the content of faces without any help of textual information has many interesting applications like video surveillance, social network, video mining, etc. However, traditional face matching against a huge number of detected faces leads to an unacceptable response time and may also reduce the accuracy due to the large variations in facial expressions, poses, lighting, etc. Therefore, in this paper we propose a novel method to generate discriminative "signatures" for efficiently retrieving the videos containing the same person with a query. In this research, the signature is defined as a compact, discriminative and reduced dimensionality representation, which is generated from a set of high-dimensional feature vectors of an individual. The desired videos are retrieved based on the similarities between the signature of the query and those of individuals in the database. In particular, we make the following contributions. Firstly, we give an algorithm of two directional linear discriminant analysis with maximum correntropy criterion (2DLDA-MCC) as an extension to our recently proposed maximum correntropy criterion based linear discriminant analysis (LDA-MCC). Both algorithms are robust to outliers and noise. Secondly, we present an approach for transferring a set of exemplars to a fixed-length signature using LDA-MCC and 2DLDA-MCC, resulting in two kinds of signatures that are called 1D signature and 2D signature. Finally, a novel video retrieval scheme is given based on the signatures, which has low storage requirement and can achieve a fast search. Evaluations on a large dataset of videos show reliable measurement of similarities by using the proposed signatures to represent the identities generated from videos. Experimental results also demonstrate that the proposed video retrieval scheme has the potential to substantially reduce the response time and slightly increase the mean average precision of retrieval.

AB - The topic of retrieving videos containing a desired person from a dataset just using the content of faces without any help of textual information has many interesting applications like video surveillance, social network, video mining, etc. However, traditional face matching against a huge number of detected faces leads to an unacceptable response time and may also reduce the accuracy due to the large variations in facial expressions, poses, lighting, etc. Therefore, in this paper we propose a novel method to generate discriminative "signatures" for efficiently retrieving the videos containing the same person with a query. In this research, the signature is defined as a compact, discriminative and reduced dimensionality representation, which is generated from a set of high-dimensional feature vectors of an individual. The desired videos are retrieved based on the similarities between the signature of the query and those of individuals in the database. In particular, we make the following contributions. Firstly, we give an algorithm of two directional linear discriminant analysis with maximum correntropy criterion (2DLDA-MCC) as an extension to our recently proposed maximum correntropy criterion based linear discriminant analysis (LDA-MCC). Both algorithms are robust to outliers and noise. Secondly, we present an approach for transferring a set of exemplars to a fixed-length signature using LDA-MCC and 2DLDA-MCC, resulting in two kinds of signatures that are called 1D signature and 2D signature. Finally, a novel video retrieval scheme is given based on the signatures, which has low storage requirement and can achieve a fast search. Evaluations on a large dataset of videos show reliable measurement of similarities by using the proposed signatures to represent the identities generated from videos. Experimental results also demonstrate that the proposed video retrieval scheme has the potential to substantially reduce the response time and slightly increase the mean average precision of retrieval.

KW - Individual retrieval

KW - Linear discriminant analysis

KW - Signature

KW - Video dataset

UR - http://www.scopus.com/inward/record.url?scp=84882571634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882571634&partnerID=8YFLogxK

U2 - 10.1587/transinf.E96.D.1800

DO - 10.1587/transinf.E96.D.1800

M3 - Article

AN - SCOPUS:84882571634

VL - E96-D

SP - 1800

EP - 1810

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 8

ER -