2011 | OriginalPaper | Buchkapitel
A Novel Objects Recognition Technique
verfasst von : XiaoXue Li
Erschienen in: Advances in Computer Science, Intelligent System and Environment
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
In this paper, we assume that the objects can be classified according to the pattern in the contour, i.e. features such as dimension, position and orientation are only confounding factors which should not be used in the recognition process. Based on these assumptions, a novel patter Recognition technique was proposed to recognize two dimensional objects with closed contours via the use of Fast Fourier Transform and a constrained k-means clustering technique.