George T. Ioannidis

TeDUB: A System for Presenting and Exploring Technical Drawings for Blind People

Blind people can access and use textual information effectively in a variety of ways - through Braille, audiotape or computer-based systems. Access and use of graphic information is much more problematic, with tactile versions both time-consuming and difficult to make and textual descriptions failing to provide independent access to the material. The TeDUB Project is developing a system which will automatically generate descriptions of certain classes of graphics (electronic circuit diagrams, UML diagrams and architectural plans) and allow blind people to explore them independently. This system has great potential in work, education and leisure domains to open up independent access to graphic materials for blind people.

Automatic content-based analysis of georeferenced image data: Detection of Beggiatoa mats in seafloor video mosaics from the HÅkon Mosby Mud Volcano

The combination of new underwater technology as remotely operating vehicles (ROVs), high-resolution video imagery, and software to compute georeferenced mosaics of the seafloor provides new opportunities for marine geological or biological studies and applications in offshore industry. Even during single surveys by ROVs or towed systems large amounts of images are compiled. While these underwater techniques are now well-engineered, there is still a lack of methods for the automatic analysis of the acquired image data. During ROV dives more than 4200 georeferenced video mosaics were compiled for the HAkon Mosby Mud Volcano (HMMV). Mud volcanoes as HMMV are considered as significant source locations for methane characterised by unique chemoautotrophic communities as Beggiatoa mats. For the detection and quantification of the spatial distribution of Beggiatoa mats an automated image analysis technique was developed, which applies watershed transformation and relaxation-based labelling of pre-segmented regions. Comparison of the data derived by visual inspection of 2840 video images with the automated image analysis revealed similarities with a precision better than 90%. We consider this as a step towards a time-efficient and accurate analysis of seafloor images for computation of geochemical budgets and identification of habitats at the seafloor.

Automated interpretation and accessible presentation of technical diagrams for blind people

The EU-supported TeDUB (Technical Drawings Understanding for the Blind) project is developing a software system that aims to make technical diagrams accessible to blind and visually impaired people. It consists of two separate modules: one that analyses drawings either semi-automatically or automatically, and one that presents the results of this analysis to blind people and allows them to interact with it. The system is capable of analysing and presenting diagrams from a number of formally defined domains. A diagram enters the system as one of two types: first, diagrams contained in bitmap images, which do not explicitly contain the semantic structure of their content and thus have to be interpreted by the system, and second, diagrams obtained in a semantically enriched format that already yields this structure. The TeDUB system provides blind users with an interface to navigate and annotate these diagrams using a number of input and output devices. Extensive user evaluations have been carried out and an overall positive response from the participants has shown the effectiveness of the approach.

Accessing Libraries of Media Art through Metadata

Being faced with digital libraries containing images and video content, means are required that characterize the content for efficient access. In addition, the confluence of media content which is distributed over a number of content providers requires a common and standardized way for searching the content. The usual solution consists in the employment of metadata which describes media content. Among others, issues that arise concern the kind of metadata to be used, how it is to be represented, and how it is to be integrated into the architecture of a portal for accessing the distributed digital archives. The methods presented in this paper have been implemented in the context of the project Gateway to Archives of Media Art (GAMA for short). The objective of this project is to establish a portal for online access to some of the most important digital archives and libraries on media art in Europe.

The bigger picture: Automated production tools-for Tactile Graphics

The Graphics to Tactile project (G2T) aimed to provide a semi-automatic image processing tool to enhance the creation of tactile graphics. In attempting to convert graphical and visual information into accessible formats, it is important that the information used for input is sufficiently well defined. Print diagrams and graphics contain information (such as perspective, overlapping lines, and colour) that cannot be represented in a Braille reader. People who are blind therefore cannot access complex formatted text, pictures, graphics or maps. The G2T system makes use of advanced image processing technologies partially to automate the tactile graphic production process and can be used in conjunction with existing drawing tools.

MAXICULTURE: Assessing the Impact of EU Projects in the Digital Cultural Heritage Domain

This paper describes the MAXICULTURE methodology for the socio-economic impact assessment of the DigiCult domain and projects funded by the European Commission, including the development process and the implementation trajectory for the MAXICULTURE lifecycle. With the term DigiCult domain we refer to a specific research field of the European Commission in which projects investigate how ICT instruments and future development can be applied to the Cultural Heritage sector for improving access to digital cultural resources and the related user experience, in order to also increase the innovation, the growth of the domain and the interlink with Culture and Creativity industries. The MAXICULTURE methodology is presented here in its second revision while the final version will be made available at the end of the MAXICULTURE project after being tested with DigiCult projects. This document incorporates the feedback received from projects.

Automatic, context-of-capture-based categorization, structure detection and segmentation of news telecasts

The objective of the work reported here is to provide an automatic, context-of-capture categorization, structure detection and segmentation of news broadcasts employing a multimodal semantic based approach. We assume that news broadcasts can be described with context-free grammars that specify their structural characteristics. We propose a system consisting of two main types of interoperating units: The recognizer unit consisting of several modules and a parser unit. The recognizer modules (audio, video and semantic recognizer) analyze the telecast and each one identifies hypothesized instances of features in the audiovisual input. A probabilistic parser analyzes the identifications provided by the recognizers. The grammar represents the possible structures a news telecast may have, so the parser can identify the exact structure of the analyzed telecast.

Semantic Video Segmentation Using Probabilistic Relaxation

In this paper we propose a method for temporal segmentation of strongly structured videos on a semantic level. The proposed method is based on a naive Bayes classifier on low level visual features, followed by a two-stage probabilistic relaxation process. The first stage relaxation is on successive video frames that have been classified with the naive Bayes classifier into structural tokens and aims to improve the initial classification result. The second relaxation process is applied on successive video segments and uses knowledge from temporal relations of structural tokens that are characteristic for each broadcasting format and results so to the video segmentation on a semantic level. The experiments carried out, show that the proposed method can be successfully applied to magazine broadcastings.

Document processing for accessibility: standards and initiatives

This paper presents the Document Processing for Accessibility Workshop that is held at CEN/ISSS and summarizes its findings so far. It focuses on standards and initiatives that have been elaborated and concern document management and accessibility issues especially for the publishing industry. The paper provides also an outline of the work to be done and invites interested parties to take an active role in shaping the workshop.

Building accessible content processing frameworks

One of the more profound challenges facing those working in the field of accessibility lies in attracting general interest for accessible solutions. Many of these solutions are perceived as being of only limited application, and this is indeed often a valid viewpoint. It is becoming clear that many accessibility initiatives lack a wider context and as a result many very good initiatives remain unadopted due to their lack of integration with wider developments. There is a continuing need to incorporate accessibility within innovative information technology solutions. This convergence also resonates within market environments. There already are initiatives within the technology arena that incorporate some of these notions into their core. Despite this, there remains a need for a more unified approach in this area that allows the identification of similarities in needs, requirements and solutions conceived by the individual participants in product development, production and consumption.