2009 | OriginalPaper | Buchkapitel
A Reliable Skin Detection Using Dempster-Shafer Theory of Evidence
verfasst von : Mohammad Shoyaib, Mohammad Abdullah-Al-Wadud, Oksam Chae
Erschienen in: Computational Science and Its Applications – ICCSA 2009
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
Efficient skin detection can be considered as a primary work for so many vital applications in the image processing arena. For the last few years researchers have been trying in several ways to solve this problem. But most of the methods suffer from accuracy and reliability when applied to a variety of images. This happens due to some significant factors such as error in skin model, use of predefined threshold. We combine these issues by proposing an improved approach for skin detection that uses Dempster Shafer Theory of evidence to build a skin prediction model with better reliability. The proposed approach gives higher accuracy for a variety of skin images than existing methods in considerable computation time (similar to Bayesian classifier) and suitable for real-time applications.