Image recommendation system based on social, semantic and visual characteristics

Journal Title: Romanian Journal of Human - Computer Interaction - Year 2011, Vol 4, Issue 1

Abstract

The article presents recommendation systems in terms of the most important aspects and types of algorithms used in different approaches and implementations, as well as issues which arise and need to be overcome. The application presented in this article was developed based on a combination of multiple ways to recommend images. The proposed model brings quality results using the following aspects of recommendation: social - by applying the concept of collaborative filtering, visual - by calculating the similarities between the visual features extracted from images, semantic - using metrics based on WordNet similarity between terms, and also by integrating a SVM classifier for recognition of scene types based on visual aspects. We present in detail the scientific methods and the architectural design used in our proposed system.

Authors and Affiliations

Maria Roditis, Andreea Tabacariu, Ştefan Trăuşan-Matu

Keywords

Related Articles

An Analysis Of The Quality And Accessibility Of Suicide Information Available To The Romanian-Speaking User

As the potential impact of Internet use on suicidal behaviour is currently under questioned, experts have yet not conclusively ruled on the extent of this problem. At the moment, no one really knows what kind of informat...

The Evaluation Of Two Augmented Reality Applications For School Environment – Focus Group With Teachers

In this paper are presented the evaluation results with teachers of added value by economic and psychological adequate utilization of a learning-teaching platform based on augmented reality technology. Two didactical ap...

Emotional State Evaluation Based On The Human Body Position, Through Computer-Vision Methods

The recognition of the users’ emotional states is a subject of interest concerning the human-computer interaction, as it conforms to the concept of natural interaction. The elimination of every constraint regarding the h...

Development of Multimedia Components for Educational Mobile Systems

This paper proposes a solution based on templates for generating multimedia components for distributed training systems, which can be used in applications that run on both PCs and mobile devices. The purpose of this solu...

Visual representations of educational processes

As an editorial to this special issue, we pinpoint some ways on how visual representations of educational processes can help analyzing these processes, and in turn lead to designing of new tools informed by interdiscipli...

Download PDF file
  • EP ID EP28847
  • DOI -
  • Views 332
  • Downloads 10

How To Cite

Maria Roditis, Andreea Tabacariu, Ştefan Trăuşan-Matu (2011). Image recommendation system based on social, semantic and visual characteristics. Romanian Journal of Human - Computer Interaction, 4(1), -. https://europub.co.uk/articles/-A-28847