Content-based indexing and teaching focus mining for lecture videos

Yu Tzu Lin, Bai Jang Yen, Greg C. Lee, Chia Hu Chang, Yu Chih Lin

Research output: Contribution to journalArticle

Abstract

Purpose – The purpose of this paper is to propose an indexing and teaching focus mining system for lecture videos recorded in an unconstrained environment. Design/methodology/approach – By applying the proposed algorithms in this paper, the slide structure can be reconstructed by extracting slide images from the video. Instead of applying traditional shot-change detection methods for general videos, a new edge-based shot-change detection algorithm is designed specifically for lecture videos. Besides, light influence and occlusions in the lecture video can be removed to obtain more accurate results. Moreover, the teaching focus can be extracted according to instructors' behavior based on the analyses of visual and audio information extracted from the lecture video. Findings – Experiment results show the feasibility of the proposed method, that is, the slide shots can be correctly detected even if the illumination conditions are variant or the slides are obstructed by the instructor or students, and the teaching focus can be extracted to provide learners with an efficient way to study. Research limitations/implications – This paper provides only technical experiments, but lacks complete educational study. In the future, more subjective tests will be designed to examine the educational effects on students. Practical implications – This paper proposes a practical indexing and teaching focus mining system for lecture videos which can help students learn. Originality/value – The proposed algorithms for indexing and teaching focus mining are derived and applied in lecture videos in this paper.

Original languageEnglish
Pages (from-to)131-153
Number of pages23
JournalInteractive Technology and Smart Education
Volume7
Issue number3
DOIs
Publication statusPublished - 2010 Sep 7

Fingerprint

indexing
Teaching
video
Students
instructor
Lighting
Experiments
student
experiment
lack
methodology
Values

Keywords

  • Digital storage
  • E-learning
  • Lectures
  • Semantics
  • Teaching
  • Video

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Education

Cite this

Content-based indexing and teaching focus mining for lecture videos. / Lin, Yu Tzu; Yen, Bai Jang; Lee, Greg C.; Chang, Chia Hu; Lin, Yu Chih.

In: Interactive Technology and Smart Education, Vol. 7, No. 3, 07.09.2010, p. 131-153.

Research output: Contribution to journalArticle

Lin, Yu Tzu ; Yen, Bai Jang ; Lee, Greg C. ; Chang, Chia Hu ; Lin, Yu Chih. / Content-based indexing and teaching focus mining for lecture videos. In: Interactive Technology and Smart Education. 2010 ; Vol. 7, No. 3. pp. 131-153.
@article{94beaf774cba4ecaa7bdaaf4242dea99,
title = "Content-based indexing and teaching focus mining for lecture videos",
abstract = "Purpose – The purpose of this paper is to propose an indexing and teaching focus mining system for lecture videos recorded in an unconstrained environment. Design/methodology/approach – By applying the proposed algorithms in this paper, the slide structure can be reconstructed by extracting slide images from the video. Instead of applying traditional shot-change detection methods for general videos, a new edge-based shot-change detection algorithm is designed specifically for lecture videos. Besides, light influence and occlusions in the lecture video can be removed to obtain more accurate results. Moreover, the teaching focus can be extracted according to instructors' behavior based on the analyses of visual and audio information extracted from the lecture video. Findings – Experiment results show the feasibility of the proposed method, that is, the slide shots can be correctly detected even if the illumination conditions are variant or the slides are obstructed by the instructor or students, and the teaching focus can be extracted to provide learners with an efficient way to study. Research limitations/implications – This paper provides only technical experiments, but lacks complete educational study. In the future, more subjective tests will be designed to examine the educational effects on students. Practical implications – This paper proposes a practical indexing and teaching focus mining system for lecture videos which can help students learn. Originality/value – The proposed algorithms for indexing and teaching focus mining are derived and applied in lecture videos in this paper.",
keywords = "Digital storage, E-learning, Lectures, Semantics, Teaching, Video",
author = "Lin, {Yu Tzu} and Yen, {Bai Jang} and Lee, {Greg C.} and Chang, {Chia Hu} and Lin, {Yu Chih}",
year = "2010",
month = "9",
day = "7",
doi = "10.1108/17415651011071613",
language = "English",
volume = "7",
pages = "131--153",
journal = "Interactive Technology and Smart Education",
issn = "1741-5659",
publisher = "Emerald Group Publishing Ltd.",
number = "3",

}

TY - JOUR

T1 - Content-based indexing and teaching focus mining for lecture videos

AU - Lin, Yu Tzu

AU - Yen, Bai Jang

AU - Lee, Greg C.

AU - Chang, Chia Hu

AU - Lin, Yu Chih

PY - 2010/9/7

Y1 - 2010/9/7

N2 - Purpose – The purpose of this paper is to propose an indexing and teaching focus mining system for lecture videos recorded in an unconstrained environment. Design/methodology/approach – By applying the proposed algorithms in this paper, the slide structure can be reconstructed by extracting slide images from the video. Instead of applying traditional shot-change detection methods for general videos, a new edge-based shot-change detection algorithm is designed specifically for lecture videos. Besides, light influence and occlusions in the lecture video can be removed to obtain more accurate results. Moreover, the teaching focus can be extracted according to instructors' behavior based on the analyses of visual and audio information extracted from the lecture video. Findings – Experiment results show the feasibility of the proposed method, that is, the slide shots can be correctly detected even if the illumination conditions are variant or the slides are obstructed by the instructor or students, and the teaching focus can be extracted to provide learners with an efficient way to study. Research limitations/implications – This paper provides only technical experiments, but lacks complete educational study. In the future, more subjective tests will be designed to examine the educational effects on students. Practical implications – This paper proposes a practical indexing and teaching focus mining system for lecture videos which can help students learn. Originality/value – The proposed algorithms for indexing and teaching focus mining are derived and applied in lecture videos in this paper.

AB - Purpose – The purpose of this paper is to propose an indexing and teaching focus mining system for lecture videos recorded in an unconstrained environment. Design/methodology/approach – By applying the proposed algorithms in this paper, the slide structure can be reconstructed by extracting slide images from the video. Instead of applying traditional shot-change detection methods for general videos, a new edge-based shot-change detection algorithm is designed specifically for lecture videos. Besides, light influence and occlusions in the lecture video can be removed to obtain more accurate results. Moreover, the teaching focus can be extracted according to instructors' behavior based on the analyses of visual and audio information extracted from the lecture video. Findings – Experiment results show the feasibility of the proposed method, that is, the slide shots can be correctly detected even if the illumination conditions are variant or the slides are obstructed by the instructor or students, and the teaching focus can be extracted to provide learners with an efficient way to study. Research limitations/implications – This paper provides only technical experiments, but lacks complete educational study. In the future, more subjective tests will be designed to examine the educational effects on students. Practical implications – This paper proposes a practical indexing and teaching focus mining system for lecture videos which can help students learn. Originality/value – The proposed algorithms for indexing and teaching focus mining are derived and applied in lecture videos in this paper.

KW - Digital storage

KW - E-learning

KW - Lectures

KW - Semantics

KW - Teaching

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=84993094745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84993094745&partnerID=8YFLogxK

U2 - 10.1108/17415651011071613

DO - 10.1108/17415651011071613

M3 - Article

AN - SCOPUS:84993094745

VL - 7

SP - 131

EP - 153

JO - Interactive Technology and Smart Education

JF - Interactive Technology and Smart Education

SN - 1741-5659

IS - 3

ER -