Multifaceted conceptual image indexing on the world wide web

Wan Fariza Paizi@Fauzi, Mohammed Belkhatir

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper, we describe a user-centered design of an automated multifaceted concept based indexing framework which analyzes the semantics of the Web image contextual information and classifies it into five broad semantic concept facets: signal, object, abstract, scene, and relational; and identifies the semantic relationships between the concepts. An important aspect of our indexing model is that it relates to the users' levels of image descriptions. Also, a major contribution relies on the fact that the classification is performed automatically with the raw image contextual information extracted from any general webpage and is not solely based on image tags like state-of-the-art solutions. Human Language Technology techniques and an external knowledge base are used to analyze the information both syntactically and semantically. Experimental results on a human-annotated Web image collection and corresponding contextual information indicate that our method outperforms empirical frameworks employing tf-idf and location-based tf-idf weighting schemes as well as n-gram indexing in a recall/precision based evaluation framework.

Original languageEnglish
Pages (from-to)420-440
Number of pages21
JournalInformation Processing and Management
Volume49
Issue number2
DOIs
Publication statusPublished - 1 Jan 2013
Externally publishedYes

Fingerprint

indexing
World Wide Web
Semantics
Internet
semantics
empirical method
weighting
Indexing
language
evaluation

Keywords

  • Conceptual image indexing
  • Content analysis
  • Semantic facets
  • User-centered design
  • WWW contextual information

ASJC Scopus subject areas

  • Information Systems
  • Media Technology
  • Computer Science Applications
  • Management Science and Operations Research
  • Library and Information Sciences

Cite this

Multifaceted conceptual image indexing on the world wide web. / Paizi@Fauzi, Wan Fariza; Belkhatir, Mohammed.

In: Information Processing and Management, Vol. 49, No. 2, 01.01.2013, p. 420-440.

Research output: Contribution to journalArticle

@article{b86199d069aa4c3dafc4cf8fc130fe05,
title = "Multifaceted conceptual image indexing on the world wide web",
abstract = "In this paper, we describe a user-centered design of an automated multifaceted concept based indexing framework which analyzes the semantics of the Web image contextual information and classifies it into five broad semantic concept facets: signal, object, abstract, scene, and relational; and identifies the semantic relationships between the concepts. An important aspect of our indexing model is that it relates to the users' levels of image descriptions. Also, a major contribution relies on the fact that the classification is performed automatically with the raw image contextual information extracted from any general webpage and is not solely based on image tags like state-of-the-art solutions. Human Language Technology techniques and an external knowledge base are used to analyze the information both syntactically and semantically. Experimental results on a human-annotated Web image collection and corresponding contextual information indicate that our method outperforms empirical frameworks employing tf-idf and location-based tf-idf weighting schemes as well as n-gram indexing in a recall/precision based evaluation framework.",
keywords = "Conceptual image indexing, Content analysis, Semantic facets, User-centered design, WWW contextual information",
author = "Paizi@Fauzi, {Wan Fariza} and Mohammed Belkhatir",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.ipm.2012.08.001",
language = "English",
volume = "49",
pages = "420--440",
journal = "Information Processing and Management",
issn = "0306-4573",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Multifaceted conceptual image indexing on the world wide web

AU - Paizi@Fauzi, Wan Fariza

AU - Belkhatir, Mohammed

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper, we describe a user-centered design of an automated multifaceted concept based indexing framework which analyzes the semantics of the Web image contextual information and classifies it into five broad semantic concept facets: signal, object, abstract, scene, and relational; and identifies the semantic relationships between the concepts. An important aspect of our indexing model is that it relates to the users' levels of image descriptions. Also, a major contribution relies on the fact that the classification is performed automatically with the raw image contextual information extracted from any general webpage and is not solely based on image tags like state-of-the-art solutions. Human Language Technology techniques and an external knowledge base are used to analyze the information both syntactically and semantically. Experimental results on a human-annotated Web image collection and corresponding contextual information indicate that our method outperforms empirical frameworks employing tf-idf and location-based tf-idf weighting schemes as well as n-gram indexing in a recall/precision based evaluation framework.

AB - In this paper, we describe a user-centered design of an automated multifaceted concept based indexing framework which analyzes the semantics of the Web image contextual information and classifies it into five broad semantic concept facets: signal, object, abstract, scene, and relational; and identifies the semantic relationships between the concepts. An important aspect of our indexing model is that it relates to the users' levels of image descriptions. Also, a major contribution relies on the fact that the classification is performed automatically with the raw image contextual information extracted from any general webpage and is not solely based on image tags like state-of-the-art solutions. Human Language Technology techniques and an external knowledge base are used to analyze the information both syntactically and semantically. Experimental results on a human-annotated Web image collection and corresponding contextual information indicate that our method outperforms empirical frameworks employing tf-idf and location-based tf-idf weighting schemes as well as n-gram indexing in a recall/precision based evaluation framework.

KW - Conceptual image indexing

KW - Content analysis

KW - Semantic facets

KW - User-centered design

KW - WWW contextual information

UR - http://www.scopus.com/inward/record.url?scp=84886396168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886396168&partnerID=8YFLogxK

U2 - 10.1016/j.ipm.2012.08.001

DO - 10.1016/j.ipm.2012.08.001

M3 - Article

VL - 49

SP - 420

EP - 440

JO - Information Processing and Management

JF - Information Processing and Management

SN - 0306-4573

IS - 2

ER -