A robust and lightweight feature system for video fingerprinting

Tzu Jui Liu; Hye Jung Han; Xin Xin; Zhu Li; Aggelos K Katsaggelos

A robust and lightweight feature system for video fingerprinting

Tzu Jui Liu^*, Hye Jung Han, Xin Xin, Zhu Li, Aggelos K Katsaggelos

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

In this paper, a new content-based feature identification method for video sequences is presented. It is robust to a number of image transformations and relatively lightweight compare to most state of the art methods. A scale and rotation invariant descriptor for a set of interest points in detected key frames is proposed based on modified minimal spanning tree algorithm. In addition, a predicative coding scheme is used to achieve minimal size of the descriptor for transmission. Furthermore, the pairwise distance between the frequency responses of the curvature vector from the descriptors is calculated and compared to efficiently match query with a large database. Experimental results demonstrate the effectiveness of our approach.

Original language	English (US)
Title of host publication	Proceedings of the 20th European Signal Processing Conference, EUSIPCO 2012
Pages	160-164
Number of pages	5
State	Published - Nov 27 2012
Event	20th European Signal Processing Conference, EUSIPCO 2012 - Bucharest Duration: Aug 27 2012 → Aug 31 2012

Other

Other	20th European Signal Processing Conference, EUSIPCO 2012
City	Bucharest
Period	8/27/12 → 8/31/12

Keywords

content-based fingerprinting
multimedia fingerprinting
Robust video hashing
video copy detection

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering

Cite this

@inproceedings{b3330392cd5249d2a8db131d28a18a8d,

title = "A robust and lightweight feature system for video fingerprinting",

abstract = "In this paper, a new content-based feature identification method for video sequences is presented. It is robust to a number of image transformations and relatively lightweight compare to most state of the art methods. A scale and rotation invariant descriptor for a set of interest points in detected key frames is proposed based on modified minimal spanning tree algorithm. In addition, a predicative coding scheme is used to achieve minimal size of the descriptor for transmission. Furthermore, the pairwise distance between the frequency responses of the curvature vector from the descriptors is calculated and compared to efficiently match query with a large database. Experimental results demonstrate the effectiveness of our approach.",

keywords = "content-based fingerprinting, multimedia fingerprinting, Robust video hashing, video copy detection",

author = "Liu, {Tzu Jui} and Han, {Hye Jung} and Xin Xin and Zhu Li and Katsaggelos, {Aggelos K}",

year = "2012",

month = nov,

day = "27",

language = "English (US)",

isbn = "9781467310680",

pages = "160--164",

booktitle = "Proceedings of the 20th European Signal Processing Conference, EUSIPCO 2012",

note = "20th European Signal Processing Conference, EUSIPCO 2012 ; Conference date: 27-08-2012 Through 31-08-2012",

}

TY - GEN

T1 - A robust and lightweight feature system for video fingerprinting

AU - Liu, Tzu Jui

AU - Han, Hye Jung

AU - Xin, Xin

AU - Li, Zhu

AU - Katsaggelos, Aggelos K

PY - 2012/11/27

Y1 - 2012/11/27

N2 - In this paper, a new content-based feature identification method for video sequences is presented. It is robust to a number of image transformations and relatively lightweight compare to most state of the art methods. A scale and rotation invariant descriptor for a set of interest points in detected key frames is proposed based on modified minimal spanning tree algorithm. In addition, a predicative coding scheme is used to achieve minimal size of the descriptor for transmission. Furthermore, the pairwise distance between the frequency responses of the curvature vector from the descriptors is calculated and compared to efficiently match query with a large database. Experimental results demonstrate the effectiveness of our approach.

AB - In this paper, a new content-based feature identification method for video sequences is presented. It is robust to a number of image transformations and relatively lightweight compare to most state of the art methods. A scale and rotation invariant descriptor for a set of interest points in detected key frames is proposed based on modified minimal spanning tree algorithm. In addition, a predicative coding scheme is used to achieve minimal size of the descriptor for transmission. Furthermore, the pairwise distance between the frequency responses of the curvature vector from the descriptors is calculated and compared to efficiently match query with a large database. Experimental results demonstrate the effectiveness of our approach.

KW - content-based fingerprinting

KW - multimedia fingerprinting

KW - Robust video hashing

KW - video copy detection

UR - http://www.scopus.com/inward/record.url?scp=84869748131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869748131&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84869748131

SN - 9781467310680

SP - 160

EP - 164

BT - Proceedings of the 20th European Signal Processing Conference, EUSIPCO 2012

T2 - 20th European Signal Processing Conference, EUSIPCO 2012

Y2 - 27 August 2012 through 31 August 2012

ER -

A robust and lightweight feature system for video fingerprinting

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this