Scene Cut Detection Using the Colored Pattern Appearance Model

Kin Wai Sze; Kin Man Lam; Guoping Qiu

Scene Cut Detection Using the Colored Pattern Appearance Model

Kin Wai Sze, Kin Man Lam, Guoping Qiu

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

21 Citations (Scopus)

Abstract

In this paper, we propose to use the Colored Pattern Appearance Model (CPAM) as a content representation for video scene break detection. This model represents a scene by means of global statistics of the local visual appearance, and was originally motivated by studies in human color vision. The performance of this method is compared to several histogram-based approaches. An adaptive thresholding technique, namely entropic thresholding, is applied to determine the respective optimal threshold values for each of the approaches. In the experiments, the two video sequences in the MPEG-7 content set are used to evaluate the performances of the CPAM and the histogram-based methods. Experimental results show that our proposed model outperforms other histogram-based approaches in scene break detection.

Original language	English
Title of host publication	IEEE International Conference on Image Processing
Pages	1017-1020
Number of pages	4
Publication status	Published - 17 Dec 2003
Event	Proceedings: 2003 International Conference on Image Processing, ICIP-2003 - Barcelona, Spain Duration: 14 Sept 2003 → 17 Sept 2003

Conference

Conference	Proceedings: 2003 International Conference on Image Processing, ICIP-2003
Country/Territory	Spain
City	Barcelona
Period	14/09/03 → 17/09/03

ASJC Scopus subject areas

Hardware and Architecture
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Cite this

@inproceedings{9d8afdcd087a4ca28c529f0edcd46dc9,

title = "Scene Cut Detection Using the Colored Pattern Appearance Model",

abstract = "In this paper, we propose to use the Colored Pattern Appearance Model (CPAM) as a content representation for video scene break detection. This model represents a scene by means of global statistics of the local visual appearance, and was originally motivated by studies in human color vision. The performance of this method is compared to several histogram-based approaches. An adaptive thresholding technique, namely entropic thresholding, is applied to determine the respective optimal threshold values for each of the approaches. In the experiments, the two video sequences in the MPEG-7 content set are used to evaluate the performances of the CPAM and the histogram-based methods. Experimental results show that our proposed model outperforms other histogram-based approaches in scene break detection.",

author = "Sze, {Kin Wai} and Lam, {Kin Man} and Guoping Qiu",

year = "2003",

month = dec,

day = "17",

language = "English",

pages = "1017--1020",

booktitle = "IEEE International Conference on Image Processing",

note = "Proceedings: 2003 International Conference on Image Processing, ICIP-2003 ; Conference date: 14-09-2003 Through 17-09-2003",

}

TY - GEN

T1 - Scene Cut Detection Using the Colored Pattern Appearance Model

AU - Sze, Kin Wai

AU - Lam, Kin Man

AU - Qiu, Guoping

PY - 2003/12/17

Y1 - 2003/12/17

N2 - In this paper, we propose to use the Colored Pattern Appearance Model (CPAM) as a content representation for video scene break detection. This model represents a scene by means of global statistics of the local visual appearance, and was originally motivated by studies in human color vision. The performance of this method is compared to several histogram-based approaches. An adaptive thresholding technique, namely entropic thresholding, is applied to determine the respective optimal threshold values for each of the approaches. In the experiments, the two video sequences in the MPEG-7 content set are used to evaluate the performances of the CPAM and the histogram-based methods. Experimental results show that our proposed model outperforms other histogram-based approaches in scene break detection.

AB - In this paper, we propose to use the Colored Pattern Appearance Model (CPAM) as a content representation for video scene break detection. This model represents a scene by means of global statistics of the local visual appearance, and was originally motivated by studies in human color vision. The performance of this method is compared to several histogram-based approaches. An adaptive thresholding technique, namely entropic thresholding, is applied to determine the respective optimal threshold values for each of the approaches. In the experiments, the two video sequences in the MPEG-7 content set are used to evaluate the performances of the CPAM and the histogram-based methods. Experimental results show that our proposed model outperforms other histogram-based approaches in scene break detection.

UR - http://www.scopus.com/inward/record.url?scp=0345565805&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 1017

EP - 1020

BT - IEEE International Conference on Image Processing

T2 - Proceedings: 2003 International Conference on Image Processing, ICIP-2003

Y2 - 14 September 2003 through 17 September 2003

ER -

Scene Cut Detection Using the Colored Pattern Appearance Model

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this