Ioannis Andreou

A platform for virtual museums with personalized content

Presentation of content is an important aspect of today’s virtual reality applications, especially in domains such as virtual museums. The large amount and variety of exhibits in such applications raise a need for adaptation and personalization of the environment. This paper presents a content personalization platform for Virtual Museums, which is based on a semantic description of content and on information implicitly collected about the users through their interactions with the museum. The proposed platform uses stereotypes to initialize user models, adapts user profiles dynamically and clusters users into similar interest groups. A science fiction museum has been set up as a case study for this platform and an evaluation has been carried out.

Interactive Search Results

In this paper, we address the issue of interactive search results manipulation, as provided by typical Web-based information retrieval modules like search engines and directories. Many digital library systems could benefit a lot from the proposed approach, since it is heavily based on metadata, which constitute the building block of such systems. We also propose a way of ranking search results according to their overall importance, which is defined as a weighted combination of the relevancy and popularity of a resource that is being referenced in a search results list. In order to evaluate this model, we have developed an interactive search results manipulation application, which is executed at the clients workspace through a Web browser without any further interaction with the server that provided the initial search results list. The prototype implementation is based on the XML standard and has been evaluated through an adequate evaluation process from which useful conclusions have been obtained.

Personalization of content in virtual exhibitions

Presentation of content is an important aspect of todays virtual reality applications, especially in domains such as virtual exhibitions. The large amount and variety of exhibits in such applications raise a need for adaptation and personalization of the environment. This paper presents a content personalization framework for Virtual Exhibitions, which is based on a semantic description of content and on information implicitly collected about the users through their interaction. The proposed framework uses stereotypes to initialize user models, adapts user profiles dynamically and clusters users into interest groups. A 3D virtual museum has been implemented as a case study, and an evaluation has been conducted.

Shape-based retrieval of 3D models in scene synthesis

This article describes SR-3DEditor, a complete system for creating, editing and displaying 3D scene that incorporates original technologies for fast 3D scene synthesis. The system allows the user to draw outlines of 3D shapes on the computer screen using the mouse cursor. At any time during this process, the user can query a 3D model database for models with similar outlines and then select the ones s/he thinks are more relevant. The system can then automatically calculate the parameters that position the selected model in the scene, so that its outline fits the shape sketched by the user. Evaluation results demonstrate that the users are satisfied by the usability and efficiency that is added by the automatic selection facility. SR-3DEditor is freely available for download and experimentation.

Sketch creation utilizing shape matching techniques

This paper describes a sketch creation method that can act as a front-end to a visual image retrieval system by allowing the user to draw the types of images s/he is interested in. In addition, the method supports sketch generation processes, in general, by allowing the designer to automatically replace sketch components in the current sketch with similar components from a shape database. The method consists of a shape matching step in which the contents of the user sketch are compared with the contents of a shape database and of a placement step in which similar shapes from the database are properly aligned and replace automatically the contents of the user sketch. Shape matching uses a mixture of local and global shape features such as the turning function difference and the degree of openness of a curve.

Semantifying queries over large-scale Web search engines

In many situations, searching the web is synonymous to information seeking. Currently, web search engines are the most popular vehicle via which people get access to the web. Their popularity is partially due to the intrinsic way that people interact with them, i.e., by typing some keywords to the corresponding input box. Despite their popularity, search engines often fail to satisfy certain information needs, especially when the latter are haze and poorly articulated. In this paper, we focus on the occasions when large-scale web search engines find it difficult to cope with specific information-seeking behaviors and we accordingly introduce a query construction service that is targeted towards the solution of this problem. The proposed service leverages information coming from various DBpedia datasets and provides an intuitive GUI via which searchers determine the semantic orientation of their queries before these are addressed to the underlying search engine. The evaluation of the query construction service justifies the motive of this paper and indicates that it can considerably improve the searchers’ querying ability when search engines fail to provide adequate help.

Utilizing shape retrieval in sketch synthesis

This article describes SR-Sketch, a sketch creation tool that can act both as a front-end visual query module to visual information retrieval systems and as an aid tool for fast image composition. The system allows the user to draw shapes on the computer screen using the mouse cursor. At any time during this process the user can query a shape database for similar shapes and then select the ones s/he thinks are more relevant. The system can then automatically align and replace user-drawn objects with the chosen database shapes in the user sketch. For any match between a sketch shape and a database shape, the application can provide a visual explanation of how and why two shapes are considered similar. Evaluation results show that the system achieves favorable results with respect to noise tolerance, speed and reliability. SR-Sketch is freely available for download and experimentation.

A Query Construction Service for Large-Scale Web Search Engines

Despite their wide usage, large-scale search engines are not always effective in tracing the best possible information for the user needs. There are times when web searchers spend too much time searching over a large-scale search engine. When (if) they eventually succeed in getting back the anticipated results, they often realize that their successful queries are significantly different from their initial one. In this paper, we introduce a query construction service for assisting web information seekers specify precise and un-ambiguous queries over large-scale search engines. The proposed service leverages the collective knowledge encapsulated mainly in the Wikipedia corpus and provides an intuitive GUI via which web users can determine the se-mantic orientation of their searches before these are executed by the desired engine.