Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots

Wei Ta Chu; Han Yuan Chang

doi:10.1109/ICS.2016.0086

Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots

Wei Ta Chu, Han Yuan Chang

Department of Computer Science and Information Engineering

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

1 Citation (Scopus)

Abstract

Advertisement plays an important role in the human society. Advertisement studies are related to many important issues in economics, social science, and marketing. In this paper, we propose a system to detect, segment, and classify advertisements from newspaper images and website snapshots, in order to facilitate advertisement studies. First, we detect advertisement candidates based on a connected components method. We then design rule-based filters and learning-based filters to remove non-advertisement candidates. From the remained advertisement candidates, we extract visual features and construct classifiers to classify them into predefined advertisement categories. Based on the advertisement categories published over years, we uncover several interesting statistics derived from newspaper front pages and website snapshots.

Original language	English
Title of host publication	Proceedings - 2016 International Computer Symposium, ICS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	396-401
Number of pages	6
ISBN (Electronic)	9781509034383
DOIs	https://doi.org/10.1109/ICS.2016.0086
Publication status	Published - 2017 Feb 16
Event	2016 International Computer Symposium, ICS 2016 - Chiayi, Taiwan Duration: 2016 Dec 15 → 2016 Dec 17

Publication series

Name	Proceedings - 2016 International Computer Symposium, ICS 2016

Other

Other	2016 International Computer Symposium, ICS 2016
Country	Taiwan
City	Chiayi
Period	16-12-15 → 16-12-17

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Hardware and Architecture
Computer Networks and Communications
Computer Science Applications

Access to Document

10.1109/ICS.2016.0086

Fingerprint Dive into the research topics of 'Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots'. Together they form a unique fingerprint.

Cite this

Chu, W. T., & Chang, H. Y. (2017). Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots. In Proceedings - 2016 International Computer Symposium, ICS 2016 (pp. 396-401). [7858508] (Proceedings - 2016 International Computer Symposium, ICS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICS.2016.0086

@inproceedings{e9e7a81da33d4a66887602f8a84c0321,

title = "Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots",

abstract = "Advertisement plays an important role in the human society. Advertisement studies are related to many important issues in economics, social science, and marketing. In this paper, we propose a system to detect, segment, and classify advertisements from newspaper images and website snapshots, in order to facilitate advertisement studies. First, we detect advertisement candidates based on a connected components method. We then design rule-based filters and learning-based filters to remove non-advertisement candidates. From the remained advertisement candidates, we extract visual features and construct classifiers to classify them into predefined advertisement categories. Based on the advertisement categories published over years, we uncover several interesting statistics derived from newspaper front pages and website snapshots.",

author = "Chu, {Wei Ta} and Chang, {Han Yuan}",

year = "2017",

month = feb,

day = "16",

doi = "10.1109/ICS.2016.0086",

language = "English",

series = "Proceedings - 2016 International Computer Symposium, ICS 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "396--401",

booktitle = "Proceedings - 2016 International Computer Symposium, ICS 2016",

address = "United States",

note = "2016 International Computer Symposium, ICS 2016 ; Conference date: 15-12-2016 Through 17-12-2016",

}

Chu, WT & Chang, HY 2017, Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots. in Proceedings - 2016 International Computer Symposium, ICS 2016., 7858508, Proceedings - 2016 International Computer Symposium, ICS 2016, Institute of Electrical and Electronics Engineers Inc., pp. 396-401, 2016 International Computer Symposium, ICS 2016, Chiayi, Taiwan, 16-12-15. https://doi.org/10.1109/ICS.2016.0086

Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots. / Chu, Wei Ta; Chang, Han Yuan.

Proceedings - 2016 International Computer Symposium, ICS 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 396-401 7858508 (Proceedings - 2016 International Computer Symposium, ICS 2016).

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

TY - GEN

T1 - Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots

AU - Chu, Wei Ta

AU - Chang, Han Yuan

PY - 2017/2/16

Y1 - 2017/2/16

N2 - Advertisement plays an important role in the human society. Advertisement studies are related to many important issues in economics, social science, and marketing. In this paper, we propose a system to detect, segment, and classify advertisements from newspaper images and website snapshots, in order to facilitate advertisement studies. First, we detect advertisement candidates based on a connected components method. We then design rule-based filters and learning-based filters to remove non-advertisement candidates. From the remained advertisement candidates, we extract visual features and construct classifiers to classify them into predefined advertisement categories. Based on the advertisement categories published over years, we uncover several interesting statistics derived from newspaper front pages and website snapshots.

AB - Advertisement plays an important role in the human society. Advertisement studies are related to many important issues in economics, social science, and marketing. In this paper, we propose a system to detect, segment, and classify advertisements from newspaper images and website snapshots, in order to facilitate advertisement studies. First, we detect advertisement candidates based on a connected components method. We then design rule-based filters and learning-based filters to remove non-advertisement candidates. From the remained advertisement candidates, we extract visual features and construct classifiers to classify them into predefined advertisement categories. Based on the advertisement categories published over years, we uncover several interesting statistics derived from newspaper front pages and website snapshots.

UR - http://www.scopus.com/inward/record.url?scp=85015322796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015322796&partnerID=8YFLogxK

U2 - 10.1109/ICS.2016.0086

DO - 10.1109/ICS.2016.0086

M3 - Conference contribution

AN - SCOPUS:85015322796

T3 - Proceedings - 2016 International Computer Symposium, ICS 2016

SP - 396

EP - 401

BT - Proceedings - 2016 International Computer Symposium, ICS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Computer Symposium, ICS 2016

Y2 - 15 December 2016 through 17 December 2016

ER -

Chu WT, Chang HY. Advertisement Detection, Segmentation, and Classification for Newspaper Images and Website Snapshots. In Proceedings - 2016 International Computer Symposium, ICS 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 396-401. 7858508. (Proceedings - 2016 International Computer Symposium, ICS 2016). https://doi.org/10.1109/ICS.2016.0086