TALKING HANDS · Sign language recognition from real-time video
6РП — Действия „Мария Кюри“
- Период
- 2004-08-01 → 2006-07-31
- Финансиране от ЕС
- 148 207 €
- Участници
- 1
- Схема
- IIF
Линиите свързват координатора с партньорите.
Накратко на български
Система за разпознаване на жестомик чрез видеокамера превежда жестовете на човека в английски текст в реално време. Това помага за по-лесното общуване между глухите хора и тези, които чуват.
Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.
Резултати накратко
Final Activity Report Summary - TALKING HANDS (Sign Language Recognition from Real-time video)
The aim of this project was to produce a computer-based sign language translation system, which can translate sign language to text. The human user performs gestures from sign language in front of a single video camera attached to a personal computer and the computer displays an English translation. Our most important achievement was to produce a live demo system, which can run on a laptop and has been shown to work in real-time in a number of different locations. We introduced methods to detect human skin colour and to describe hand motion and shape. We hope that our system will eventually allow deaf and hearing people to communicate more easily.
Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз
Цел на проекта
Our aim is to produce a computer-based Sign language translation system which can translate Irish SignLanguage (ISL) to English. The system will be implemented on a standard personal computer connected to acolour video camera. Hand, face and body gestures will be recognised using image processing techniques basedon Principal Component Analysis and multi-resolution hierarchical search. The system will have a vocabulary ofover 1000 gestures and incorporate ISL grammar and syntax. The system will be trained an d tested by native ISLsigners.We are proposing to recruit a highly talented Chinese researcher who has shown great promise in the field ofpattern recognition in video images. His new knowledge and perspective will enrich European research in thisarea. The project addresses the 1ST strategic theme of Multi-modal Interfaces. It also addresses the objective ofelnclusion by making computers more accessible to a disadvantaged group in society, viz. the Deaf.
Оригинален текст от CORDIS (на английски).
Участници
- DUBLIN CITY UNIVERSITY · DUBLINКоординаторИрландия
Връзки
Данни: CORDIS, © Европейски съюз