2011 | OriginalPaper | Buchkapitel
RENS – Enabling A Robot to Identify A Person
verfasst von : Xin Yan, Sabina Jeschke, Hinrich Schütze, Amit Dubey, Marc Wilke
Erschienen in: Automation, Communication and Cybernetics in Science and Engineering 2009/2010
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
We delineate a web personal information mining system that enables robots or devices (like mobile phones) possessing a visual perception system to discover a person’s identity and his personal information (such as phone number, email, etc.) based on visual perception through NLP methods. At the core of the system lies a rule based personal information extraction algorithm that does not require any supervision or manual annotation, and can be easily applied to other domains such as travel or books. This first implementation was used as a proof of concept and experimental results showed that our annotation-free method is promising and compares favorably to supervised approaches.