A multicriteria multitransform neural network classifier

    Authors

    W. B. Mikhael;M. M. Abdelwahab

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Circuits Syst. Signal Process.

    Keywords

    neural network; classification; transforms; multicriteria; IMAGE CLASSIFICATION; Engineering, Electrical & Electronic

    Abstract

    In this paper, we propose a novel one- and multi-dimensional signal classification neural network system that employs a set of criteria extracted from the signal representation in different transform domains, denoted the multicriteria multitransform neural network classifier. The signal projection, in each appropriately selected transform domain, reveals unique signal characteristics. The criteria in the different domains are properly formulated and their parameters adapted to obtain classification with desirable implementation properties such as speed and accuracy. Results for image classification confirm the improved classification performance relative to existing techniques. In addition to the improved computational efficiency and accuracy, preliminary results indicate that the proposed technique lends itself to higher classification accuracy in the presence of additive noise.

    Journal Title

    Circuits Systems and Signal Processing

    Volume

    21

    Issue/Number

    5

    Publication Date

    1-1-2002

    Document Type

    Article

    Language

    English

    First Page

    451

    Last Page

    460

    WOS Identifier

    WOS:000178889400001

    ISSN

    0278-081X

    Share

    COinS