Cleaning up after a face tracker: False positive removal

Makarand Tapaswi; Cemal Çaʇi Çörez; Martin Bäuml; Hazim Kemal Ekenel; Rainer Stiefelhagen

doi:10.1109/ICIP.2014.7025050

Cleaning up after a face tracker: False positive removal

Makarand Tapaswi, Cemal Çaʇi Çörez, Martin Bäuml, Hazim Kemal Ekenel, Rainer Stiefelhagen

Department of Computer Engineering

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

4 Citations (Scopus)

Abstract

Automatic person identification in TV series has gained popularity over the years. While most of the works rely on using face-based recognition, errors during tracking such as false positive face tracks are typically ignored. We propose a variety of methods to remove false positive face tracks and categorize the methods into confidence- and context-based. We evaluate our methods on a large TV series data set and show that up to 75% of the false positive face tracks are removed at the cost of 3.6% true positive tracks. We further show that the proposed method is general and applicable to other detectors or trackers.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	253-257
Number of pages	5
ISBN (Electronic)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025050
Publication status	Published - 28 Jan 2014

Publication series

Name	2014 IEEE International Conference on Image Processing, ICIP 2014

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

TV series
face tracking
false positive removal
video processing

Access to Document

10.1109/ICIP.2014.7025050

Cite this

Tapaswi, M., Çörez, C. Ç., Bäuml, M., Ekenel, H. K., & Stiefelhagen, R. (2014). Cleaning up after a face tracker: False positive removal. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 253-257). Article 7025050 (2014 IEEE International Conference on Image Processing, ICIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025050

@inproceedings{7238fe9aa50b4980a926fd31de2bd011,

title = "Cleaning up after a face tracker: False positive removal",

abstract = "Automatic person identification in TV series has gained popularity over the years. While most of the works rely on using face-based recognition, errors during tracking such as false positive face tracks are typically ignored. We propose a variety of methods to remove false positive face tracks and categorize the methods into confidence- and context-based. We evaluate our methods on a large TV series data set and show that up to 75% of the false positive face tracks are removed at the cost of 3.6% true positive tracks. We further show that the proposed method is general and applicable to other detectors or trackers.",

keywords = "TV series, face tracking, false positive removal, video processing",

author = "Makarand Tapaswi and {\c C}{\"o}rez, {Cemal {\c C}aʇi} and Martin B{\"a}uml and Ekenel, {Hazim Kemal} and Rainer Stiefelhagen",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025050",

language = "English",

series = "2014 IEEE International Conference on Image Processing, ICIP 2014",

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

pages = "253--257",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

address = "United States",

}

Tapaswi, M, Çörez, CÇ, Bäuml, M, Ekenel, HK & Stiefelhagen, R 2014, Cleaning up after a face tracker: False positive removal. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025050, 2014 IEEE International Conference on Image Processing, ICIP 2014, Institute of Electrical and Electronics Engineers Inc., pp. 253-257. https://doi.org/10.1109/ICIP.2014.7025050

Cleaning up after a face tracker: False positive removal. / Tapaswi, Makarand; Çörez, Cemal Çaʇi; Bäuml, Martin et al.
2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 253-257 7025050 (2014 IEEE International Conference on Image Processing, ICIP 2014).

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

TY - GEN

T1 - Cleaning up after a face tracker

T2 - False positive removal

AU - Tapaswi, Makarand

AU - Çörez, Cemal Çaʇi

AU - Bäuml, Martin

AU - Ekenel, Hazim Kemal

AU - Stiefelhagen, Rainer

PY - 2014/1/28

Y1 - 2014/1/28

N2 - Automatic person identification in TV series has gained popularity over the years. While most of the works rely on using face-based recognition, errors during tracking such as false positive face tracks are typically ignored. We propose a variety of methods to remove false positive face tracks and categorize the methods into confidence- and context-based. We evaluate our methods on a large TV series data set and show that up to 75% of the false positive face tracks are removed at the cost of 3.6% true positive tracks. We further show that the proposed method is general and applicable to other detectors or trackers.

AB - Automatic person identification in TV series has gained popularity over the years. While most of the works rely on using face-based recognition, errors during tracking such as false positive face tracks are typically ignored. We propose a variety of methods to remove false positive face tracks and categorize the methods into confidence- and context-based. We evaluate our methods on a large TV series data set and show that up to 75% of the false positive face tracks are removed at the cost of 3.6% true positive tracks. We further show that the proposed method is general and applicable to other detectors or trackers.

KW - TV series

KW - face tracking

KW - false positive removal

KW - video processing

UR - http://www.scopus.com/inward/record.url?scp=84949927178&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025050

DO - 10.1109/ICIP.2014.7025050

M3 - Conference contribution

AN - SCOPUS:84949927178

T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014

SP - 253

EP - 257

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Tapaswi M, Çörez CÇ, Bäuml M, Ekenel HK, Stiefelhagen R. Cleaning up after a face tracker: False positive removal. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 253-257. 7025050. (2014 IEEE International Conference on Image Processing, ICIP 2014). doi: 10.1109/ICIP.2014.7025050

Cleaning up after a face tracker: False positive removal

Abstract

Publication series

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this