A new approach for automatic object labeling

Joanna I. Olszewska

A new approach for automatic object labeling

Research output: Contribution to conference › Paper › peer-review

Abstract

In order to semantically label visual objects in a large amount of images, we propose a new approach which is fast and accurate. The developed automatic object labeling technique relies on the embedded double matching of local visual descriptors detected in the example and candidate images to semantically tag the candidate image with the label associated to the example image, leading thus to the automatic annotation of the candidate image. Our system has been successfully tested on different standard datasets and is compatible with online applications.

Original language	English
Number of pages	2
Publication status	Published - 13 Dec 2012
Externally published	Yes
Event	Vision and Language Net Workshop on Vision and Language 2012 - The Edge Conference Centre, University of Sheffield, Sheffield, United Kingdom Duration: 13 Dec 2012 → 14 Dec 2012 http://www.vlnet.org.uk/VL-Workshop-2012.html

Conference

Conference	Vision and Language Net Workshop on Vision and Language 2012
Abbreviated title	VL'12
Country/Territory	United Kingdom
City	Sheffield
Period	13/12/12 → 14/12/12
Internet address	http://www.vlnet.org.uk/VL-Workshop-2012.html

Access to Document

http://www.vlnet.org.uk/VLW12/VLW-2012-Accepted-Abstracts.html

Cite this

@conference{c68ab352bb1c4c858f253cb3ef3c768a,

title = "A new approach for automatic object labeling",

abstract = "In order to semantically label visual objects in a large amount of images, we propose a new approach which is fast and accurate. The developed automatic object labeling technique relies on the embedded double matching of local visual descriptors detected in the example and candidate images to semantically tag the candidate image with the label associated to the example image, leading thus to the automatic annotation of the candidate image. Our system has been successfully tested on different standard datasets and is compatible with online applications.",

author = "Olszewska, {Joanna I.}",

year = "2012",

month = dec,

day = "13",

language = "English",

note = "Vision and Language Net Workshop on Vision and Language 2012, VL'12 ; Conference date: 13-12-2012 Through 14-12-2012",

url = "http://www.vlnet.org.uk/VL-Workshop-2012.html",

}

TY - CONF

T1 - A new approach for automatic object labeling

AU - Olszewska, Joanna I.

PY - 2012/12/13

Y1 - 2012/12/13

N2 - In order to semantically label visual objects in a large amount of images, we propose a new approach which is fast and accurate. The developed automatic object labeling technique relies on the embedded double matching of local visual descriptors detected in the example and candidate images to semantically tag the candidate image with the label associated to the example image, leading thus to the automatic annotation of the candidate image. Our system has been successfully tested on different standard datasets and is compatible with online applications.

AB - In order to semantically label visual objects in a large amount of images, we propose a new approach which is fast and accurate. The developed automatic object labeling technique relies on the embedded double matching of local visual descriptors detected in the example and candidate images to semantically tag the candidate image with the label associated to the example image, leading thus to the automatic annotation of the candidate image. Our system has been successfully tested on different standard datasets and is compatible with online applications.

UR - http://www.vlnet.org.uk/VL-Workshop-2012.html

M3 - Paper

T2 - Vision and Language Net Workshop on Vision and Language 2012

Y2 - 13 December 2012 through 14 December 2012

ER -

A new approach for automatic object labeling

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this