Detail

Ubiquitous Web Access for Visually Impaired People (Acesso Ubíquo à WEB para cegos)

Visually impaired people are info-excluded due to the
overwhelming task they face to read information on the web. Indeed,
unlike fully capacitated people, blind people can not read information
by just scanning it quickly i.e. they can not read in the “diagonal”. As
a consequence, they have to come through all sentences of web pages to
understand if a document is interesting or not. This is obviously an
overwhelming task which clearly excludes visually impaired people to
quick access to information. Although a lot has been done for blind
people to access information with braille screens, braille keyboards,
braille PDAs andText-to-Speech interfaces, very little has been made to
reduce the amount of information they have to deal with. Today, this is
one of the most important challenge of our society to deal with the
info-inclusion of visually impaired people. Indeed, do you really need
to read a 20 pages document to know if it is interesting for you? Of
course not. But blind people need to do this. So, we clearly need to
solve this problem which deeply limits web information access. Another
important factor is that most blind people do not have access to
expensive adapted devices (mentioned above). This fact can be seen as a
society-exclusion problem. Indeed, only a small proportion of visually
impaired people have access to information. For that purpose, we aim at
proposing new human-computer interfaces that run on classical devices
such as classical PCs, Pocket PCs or PDAs. As a consequence, blind
people may have access to affordable technology. In particular, we aim
at developing a wide range of technological solutions so that visually
impaired people can take advantage of the new ubiquitous technologies
that are fast growing in our every day lives. This project aims at
tackling this challenging task by introducing on-line services to
existing search engines. Indeed, the most efficient way to access to
information is search engines. As a consequence, our focus will be to
provide solutions via a meta search engine which will include the
following tasks: (1) Automatic Clustering of Web Page Results, (2)
Accurate Synthetic Automatic Description of Documents, (3) Automatic
Summarization of Web Pages, (4) Automatic Description of Images based on
Text and Image features, (5) Speech-to-Speech Interfaces.

One of the particularity of these processes is that they are
computationally heavy which contrasts with the dynamicity of the web
which demands quick answers from the systems. As a consequence,
efficient algorithmic solutions will have to be designed to answer in
real-time to information access. This can be seen as tackling the
following tasks: (6) Implementation of Efficient Text Algorithms, (7)
Design of Distributed and Parallel Architectures.

Duration: 2008-2010

Leader: Gaël Harry Dias

External Participants: Pavel Brazdil (Univeristy of Porto, Portugal),
José Gabriel Pereira Lopes (New University of Lisbon, Portugal), Hugo
Liu (MIT, USA), Rada Mihalcea (North Texas University, USA).

Funding Agency: Fundação para a Ciência e a Tecnologia (Portugal)

Reference: PTDC/PLP/72142/2006

Visually impaired people are info-excluded due to the overwhelming task they face to read information on the web. Indeed, unlike fully capacitated people, blind people can not read information by just scanning it quickly i.e. they can not read in the “diagonal”. As a consequence, they have to
come through all sentences of web pages to understand if a document is interesting or not. This is obviously an overwhelming task which clearly excludes visually impaired people to quick access to information.

Although a lot has been done for blind people to access information with braille screens, braille keyboards, braille PDAs andText-to-Speech interfaces, very little has been made to reduce the amount of information they have to deal with. Today, this is one of the most important
challenge of our society to deal with the info-inclusion of visually impaired people. Indeed, do you really need to read a 20 pages document to know if it is interesting for you? Of course not. But blind people need to do this. So, we clearly need to solve this problem which deeply limits web
information access.

Another important factor is that most blind people do not have access to expensive adapted devices (mentioned above). This fact can be seen as a society-exclusion problem. Indeed, only a small proportion of visually impaired people have access to information. For that purpose, we aim at proposing new human-computer interfaces that run on classical devices such as classical PCs, Pocket PCs or PDAs. As a consequence, blind people may have access to affordable technology. In particular, we aim at developing a wide range of technological solutions so that visually impaired
people can take advantage of the new ubiquitous technologies that are fast growing in our every day lives.

This project aims at tackling this challenging task by introducing on-line services to existing search engines. Indeed, the most efficient way to access to information is search engines. As a consequence, our focus will be to provide solutions via a meta search engine which will include the following tasks:

(1) Automatic Clustering of Web Page results,
(2) Accurate Synthetic Automatic Description of Documents,
(3) Automatic Summarization of Web Pages,
(4) Automatic Description of Images based on Text and Image features,
(5) Speech-to-Speech Interfaces.

One of the particularity of these processes is that they are computationally heavy which contrasts with the dynamicity of the web which demands quick answers from the systems. As a consequence, efficient algorithmic solutions will have to be designed to answer in real-time to information access. This can be seen as tackling the following tasks:

(6) Implementation of Efficient Text Algorithms,
(7) Design of Distributed and Parallel Architectures.

We want to stress that this project aims at providing the blind community with a prototype that may lead to a final patented product. As a
consequence, the overall architecture will be developed and evaluated in association with the ACAPO (Associação dos Cegos e Amblíopes de Portugal (http://www.acapo.pt) association for visually impaired people.