Multi-feature query language for image classification

Raoul Pascal Pein, Joan Lu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Despite the major effort put into the creation of Content-Based Image Retrieval (CBIR) systems during the last decade, the solutions available are still not satisfying for generic purposes. The most severe issue seems to be the so-called "semantic gap". It is feasible to define and use domain specific feature vectors on a low level and use this information for a similarity based retrieval. Yet, mapping these to higher level semantics remains difficult. This research investigates a domain-independent way of automatized image categorization. A CBIR query language is constructed to build query-like descriptors for each category to be learned. The proposed learning algorithm is based on decision-trees. The resulting descriptors are aimed to be understandable and modifiable by expert users. A case-study is presented to support these claims.

LanguageEnglish
Pages2549-2557
Number of pages9
JournalProcedia Computer Science
Volume1
Issue number1
DOIs
Publication statusPublished - 1 May 2010

Fingerprint

Query languages
Image classification
Image retrieval
Semantics
Information use
Decision trees
Learning algorithms

Cite this

Pein, Raoul Pascal ; Lu, Joan. / Multi-feature query language for image classification. In: Procedia Computer Science. 2010 ; Vol. 1, No. 1. pp. 2549-2557.
@article{1266a9aeaa3e4affbbc5f521fd35a279,
title = "Multi-feature query language for image classification",
abstract = "Despite the major effort put into the creation of Content-Based Image Retrieval (CBIR) systems during the last decade, the solutions available are still not satisfying for generic purposes. The most severe issue seems to be the so-called {"}semantic gap{"}. It is feasible to define and use domain specific feature vectors on a low level and use this information for a similarity based retrieval. Yet, mapping these to higher level semantics remains difficult. This research investigates a domain-independent way of automatized image categorization. A CBIR query language is constructed to build query-like descriptors for each category to be learned. The proposed learning algorithm is based on decision-trees. The resulting descriptors are aimed to be understandable and modifiable by expert users. A case-study is presented to support these claims.",
keywords = "Categorization, Content-based image retrieval, Decision tree, Query language",
author = "Pein, {Raoul Pascal} and Joan Lu",
year = "2010",
month = "5",
day = "1",
doi = "10.1016/j.procs.2010.04.287",
language = "English",
volume = "1",
pages = "2549--2557",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",
number = "1",

}

Multi-feature query language for image classification. / Pein, Raoul Pascal; Lu, Joan.

In: Procedia Computer Science, Vol. 1, No. 1, 01.05.2010, p. 2549-2557.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multi-feature query language for image classification

AU - Pein, Raoul Pascal

AU - Lu, Joan

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Despite the major effort put into the creation of Content-Based Image Retrieval (CBIR) systems during the last decade, the solutions available are still not satisfying for generic purposes. The most severe issue seems to be the so-called "semantic gap". It is feasible to define and use domain specific feature vectors on a low level and use this information for a similarity based retrieval. Yet, mapping these to higher level semantics remains difficult. This research investigates a domain-independent way of automatized image categorization. A CBIR query language is constructed to build query-like descriptors for each category to be learned. The proposed learning algorithm is based on decision-trees. The resulting descriptors are aimed to be understandable and modifiable by expert users. A case-study is presented to support these claims.

AB - Despite the major effort put into the creation of Content-Based Image Retrieval (CBIR) systems during the last decade, the solutions available are still not satisfying for generic purposes. The most severe issue seems to be the so-called "semantic gap". It is feasible to define and use domain specific feature vectors on a low level and use this information for a similarity based retrieval. Yet, mapping these to higher level semantics remains difficult. This research investigates a domain-independent way of automatized image categorization. A CBIR query language is constructed to build query-like descriptors for each category to be learned. The proposed learning algorithm is based on decision-trees. The resulting descriptors are aimed to be understandable and modifiable by expert users. A case-study is presented to support these claims.

KW - Categorization

KW - Content-based image retrieval

KW - Decision tree

KW - Query language

UR - http://www.scopus.com/inward/record.url?scp=78650272971&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2010.04.287

DO - 10.1016/j.procs.2010.04.287

M3 - Article

VL - 1

SP - 2549

EP - 2557

JO - Procedia Computer Science

T2 - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

IS - 1

ER -