A service-oriented framework for personalized recommender systems using a colour-impression-based image retrieval and ranking method

Ana Šaša, Yasushi Kiyoki, Shuichi Kurabayashi, Xing Chen, Marjan Krisper

Research output: Contribution to journalArticle

Abstract

This paper points out that achievements in the field of multimedia analysis and retrieval represent an important opportunity for improvement of recommender system mechanisms. Online shopping systems use various recommender systems; however a study of different approaches has shown that they do not exploit the potential of information carried by multimedia product data for product recommendations. We demonstrate how this can be accomplished by a personalized recommender system framework that is based on a method of analysis of colour features of entity images. Colour-features are based on image colour histograms, psychological properties of colours and a learning mechanism. We have developed a service-oriented framework for a personalized recommender system that is based on incorporation of this method into a highly interactive business process model. The framework is designed in a generic way and can be applied to an arbitrary domain. It is based on service-oriented architecture in order to promote its flexibility and reuse, which is important when applying it to existing recommender system environments. An experimental study was performed for the domain of travel agency. The framework provides several important advantages, such as automatic creation of entity image meta-data which is based on colour-based image analysis and extraction of their semantic properties, user-interaction based learning, dynamic selection and presentation ordering of entity images, and feedback for creation of base image entity sets.

Original languageEnglish
Pages (from-to)59-76
Number of pages18
JournalFrontiers in Artificial Intelligence and Applications
Volume237
DOIs
Publication statusPublished - 2012

Fingerprint

Recommender systems
Image retrieval
Color
Service oriented architecture (SOA)
Metadata
Image analysis
Semantics
Feedback
Industry

Keywords

  • business process
  • colour-impression
  • image analysis
  • Product recommendation
  • service-oriented architecture

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

A service-oriented framework for personalized recommender systems using a colour-impression-based image retrieval and ranking method. / Šaša, Ana; Kiyoki, Yasushi; Kurabayashi, Shuichi; Chen, Xing; Krisper, Marjan.

In: Frontiers in Artificial Intelligence and Applications, Vol. 237, 2012, p. 59-76.

Research output: Contribution to journalArticle

@article{8978cab15fb2442d9bac17b364720c3b,
title = "A service-oriented framework for personalized recommender systems using a colour-impression-based image retrieval and ranking method",
abstract = "This paper points out that achievements in the field of multimedia analysis and retrieval represent an important opportunity for improvement of recommender system mechanisms. Online shopping systems use various recommender systems; however a study of different approaches has shown that they do not exploit the potential of information carried by multimedia product data for product recommendations. We demonstrate how this can be accomplished by a personalized recommender system framework that is based on a method of analysis of colour features of entity images. Colour-features are based on image colour histograms, psychological properties of colours and a learning mechanism. We have developed a service-oriented framework for a personalized recommender system that is based on incorporation of this method into a highly interactive business process model. The framework is designed in a generic way and can be applied to an arbitrary domain. It is based on service-oriented architecture in order to promote its flexibility and reuse, which is important when applying it to existing recommender system environments. An experimental study was performed for the domain of travel agency. The framework provides several important advantages, such as automatic creation of entity image meta-data which is based on colour-based image analysis and extraction of their semantic properties, user-interaction based learning, dynamic selection and presentation ordering of entity images, and feedback for creation of base image entity sets.",
keywords = "business process, colour-impression, image analysis, Product recommendation, service-oriented architecture",
author = "Ana Šaša and Yasushi Kiyoki and Shuichi Kurabayashi and Xing Chen and Marjan Krisper",
year = "2012",
doi = "10.3233/978-1-60750-992-9-59",
language = "English",
volume = "237",
pages = "59--76",
journal = "Frontiers in Artificial Intelligence and Applications",
issn = "0922-6389",
publisher = "IOS Press",

}

TY - JOUR

T1 - A service-oriented framework for personalized recommender systems using a colour-impression-based image retrieval and ranking method

AU - Šaša, Ana

AU - Kiyoki, Yasushi

AU - Kurabayashi, Shuichi

AU - Chen, Xing

AU - Krisper, Marjan

PY - 2012

Y1 - 2012

N2 - This paper points out that achievements in the field of multimedia analysis and retrieval represent an important opportunity for improvement of recommender system mechanisms. Online shopping systems use various recommender systems; however a study of different approaches has shown that they do not exploit the potential of information carried by multimedia product data for product recommendations. We demonstrate how this can be accomplished by a personalized recommender system framework that is based on a method of analysis of colour features of entity images. Colour-features are based on image colour histograms, psychological properties of colours and a learning mechanism. We have developed a service-oriented framework for a personalized recommender system that is based on incorporation of this method into a highly interactive business process model. The framework is designed in a generic way and can be applied to an arbitrary domain. It is based on service-oriented architecture in order to promote its flexibility and reuse, which is important when applying it to existing recommender system environments. An experimental study was performed for the domain of travel agency. The framework provides several important advantages, such as automatic creation of entity image meta-data which is based on colour-based image analysis and extraction of their semantic properties, user-interaction based learning, dynamic selection and presentation ordering of entity images, and feedback for creation of base image entity sets.

AB - This paper points out that achievements in the field of multimedia analysis and retrieval represent an important opportunity for improvement of recommender system mechanisms. Online shopping systems use various recommender systems; however a study of different approaches has shown that they do not exploit the potential of information carried by multimedia product data for product recommendations. We demonstrate how this can be accomplished by a personalized recommender system framework that is based on a method of analysis of colour features of entity images. Colour-features are based on image colour histograms, psychological properties of colours and a learning mechanism. We have developed a service-oriented framework for a personalized recommender system that is based on incorporation of this method into a highly interactive business process model. The framework is designed in a generic way and can be applied to an arbitrary domain. It is based on service-oriented architecture in order to promote its flexibility and reuse, which is important when applying it to existing recommender system environments. An experimental study was performed for the domain of travel agency. The framework provides several important advantages, such as automatic creation of entity image meta-data which is based on colour-based image analysis and extraction of their semantic properties, user-interaction based learning, dynamic selection and presentation ordering of entity images, and feedback for creation of base image entity sets.

KW - business process

KW - colour-impression

KW - image analysis

KW - Product recommendation

KW - service-oriented architecture

UR - http://www.scopus.com/inward/record.url?scp=84865757796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865757796&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-992-9-59

DO - 10.3233/978-1-60750-992-9-59

M3 - Article

AN - SCOPUS:84865757796

VL - 237

SP - 59

EP - 76

JO - Frontiers in Artificial Intelligence and Applications

JF - Frontiers in Artificial Intelligence and Applications

SN - 0922-6389

ER -