2-D shape recognition using recursive landmark determination and fuzzy ART network learning

    Authors

    A. Saengdeejing; Z. H. Qu; N. Chaeroenlap;Y. F. Jin

    Abbreviated Journal Title

    Neural Process. Lett.

    Keywords

    fuzzy ART network; recursive landmark determination; 2-D shape; recognition; CURVES; ALGORITHM; Computer Science, Artificial Intelligence; Neurosciences

    Abstract

    In this Letter, 2-D shape recognition is done using a combination of recursive search of landmarks, landmark-based invariant features, and a fuzzy ART neural-network classifier. To make this novel combination work well, an upper limit is imposed on the number of total landmarks allowed, and this maximum size is then translated into fixed dimensions of invariant features and into the neural processing of the features. It is shown that the recursive landmark search approximates very well any smooth 2-D shape contour, that the shape features used are independent of perspective transformation, and that, when combined with a fuzzy ART classifier, unknown features can be efficiently learned on-line to identify multiple distinct objects. An illustrative example is used to demonstrate effectiveness of the proposed algorithm.

    Journal Title

    Neural Processing Letters

    Volume

    18

    Issue/Number

    2

    Publication Date

    1-1-2003

    Document Type

    Article

    Language

    English

    First Page

    81

    Last Page

    95

    WOS Identifier

    WOS:000186045100001

    ISSN

    1370-4621

    Share

    COinS