An efficient image automatic tagging method based on a subject area

Seongho Lim, Taebeom Lim, Hyeran Byun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Through the development of social media, we need technology to search for images created at a rapid rate. Generally searching for images can be done by users inserting tag information into the images. This study suggests a system that is to insert tag information automatically by using trained data when new images enter. A suggested system, region of interest is selected in the images and it is divided into many blocks. Histogram is made by computing Local Binary Pattern for each blocks. computed histograms are connected with each other, which is used as feature vectors, and it is trained at random forests. Each feature vectors having strong on rotation, are created by computed each histogram don by Discrete Fourier Transforms. In the same way, feature vectors are created when new images enter; then, by using Random Forest, images can be expected which categories they are involved in. Tags for certain categories are collected from tag pool and tags are automatically inserted by calculation of weighting. Performance is evaluated after a comparative experimental study between a proposed system and an existing tagging system.

Original languageEnglish
Title of host publicationIEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program
DOIs
Publication statusPublished - 2012 Oct 22
Event2012 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Seoul, Korea, Republic of
Duration: 2012 Jun 272012 Jun 29

Other

Other2012 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012
CountryKorea, Republic of
CitySeoul
Period12/6/2712/6/29

Fingerprint

Discrete Fourier transforms
weighting
social media
performance

All Science Journal Classification (ASJC) codes

  • Communication
  • Media Technology
  • Electrical and Electronic Engineering
  • Human-Computer Interaction
  • Computer Science Applications
  • Computer Networks and Communications
  • Computer Graphics and Computer-Aided Design

Cite this

Lim, S., Lim, T., & Byun, H. (2012). An efficient image automatic tagging method based on a subject area. In IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program [6264320] https://doi.org/10.1109/BMSB.2012.6264320
Lim, Seongho ; Lim, Taebeom ; Byun, Hyeran. / An efficient image automatic tagging method based on a subject area. IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program. 2012.
@inproceedings{264cbc7352654e2aba47365bec6b9b37,
title = "An efficient image automatic tagging method based on a subject area",
abstract = "Through the development of social media, we need technology to search for images created at a rapid rate. Generally searching for images can be done by users inserting tag information into the images. This study suggests a system that is to insert tag information automatically by using trained data when new images enter. A suggested system, region of interest is selected in the images and it is divided into many blocks. Histogram is made by computing Local Binary Pattern for each blocks. computed histograms are connected with each other, which is used as feature vectors, and it is trained at random forests. Each feature vectors having strong on rotation, are created by computed each histogram don by Discrete Fourier Transforms. In the same way, feature vectors are created when new images enter; then, by using Random Forest, images can be expected which categories they are involved in. Tags for certain categories are collected from tag pool and tags are automatically inserted by calculation of weighting. Performance is evaluated after a comparative experimental study between a proposed system and an existing tagging system.",
author = "Seongho Lim and Taebeom Lim and Hyeran Byun",
year = "2012",
month = "10",
day = "22",
doi = "10.1109/BMSB.2012.6264320",
language = "English",
isbn = "9781467302937",
booktitle = "IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program",

}

Lim, S, Lim, T & Byun, H 2012, An efficient image automatic tagging method based on a subject area. in IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program., 6264320, 2012 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012, Seoul, Korea, Republic of, 12/6/27. https://doi.org/10.1109/BMSB.2012.6264320

An efficient image automatic tagging method based on a subject area. / Lim, Seongho; Lim, Taebeom; Byun, Hyeran.

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program. 2012. 6264320.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An efficient image automatic tagging method based on a subject area

AU - Lim, Seongho

AU - Lim, Taebeom

AU - Byun, Hyeran

PY - 2012/10/22

Y1 - 2012/10/22

N2 - Through the development of social media, we need technology to search for images created at a rapid rate. Generally searching for images can be done by users inserting tag information into the images. This study suggests a system that is to insert tag information automatically by using trained data when new images enter. A suggested system, region of interest is selected in the images and it is divided into many blocks. Histogram is made by computing Local Binary Pattern for each blocks. computed histograms are connected with each other, which is used as feature vectors, and it is trained at random forests. Each feature vectors having strong on rotation, are created by computed each histogram don by Discrete Fourier Transforms. In the same way, feature vectors are created when new images enter; then, by using Random Forest, images can be expected which categories they are involved in. Tags for certain categories are collected from tag pool and tags are automatically inserted by calculation of weighting. Performance is evaluated after a comparative experimental study between a proposed system and an existing tagging system.

AB - Through the development of social media, we need technology to search for images created at a rapid rate. Generally searching for images can be done by users inserting tag information into the images. This study suggests a system that is to insert tag information automatically by using trained data when new images enter. A suggested system, region of interest is selected in the images and it is divided into many blocks. Histogram is made by computing Local Binary Pattern for each blocks. computed histograms are connected with each other, which is used as feature vectors, and it is trained at random forests. Each feature vectors having strong on rotation, are created by computed each histogram don by Discrete Fourier Transforms. In the same way, feature vectors are created when new images enter; then, by using Random Forest, images can be expected which categories they are involved in. Tags for certain categories are collected from tag pool and tags are automatically inserted by calculation of weighting. Performance is evaluated after a comparative experimental study between a proposed system and an existing tagging system.

UR - http://www.scopus.com/inward/record.url?scp=84867525297&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867525297&partnerID=8YFLogxK

U2 - 10.1109/BMSB.2012.6264320

DO - 10.1109/BMSB.2012.6264320

M3 - Conference contribution

AN - SCOPUS:84867525297

SN - 9781467302937

BT - IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program

ER -

Lim S, Lim T, Byun H. An efficient image automatic tagging method based on a subject area. In IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2012 - Final Program. 2012. 6264320 https://doi.org/10.1109/BMSB.2012.6264320