Translational rotational scaling invariant (TRSI) pattern recognition is an important problem in the automatic target recognition (ATR) field. Recent research has shown that the higher order neural networks (HONN) have numerous advantages over other neural network approaches in respect of the object recognition with invariant of the object's position size, and in-plane rotation. The major limitation of HONNs is that the number of connected weights is too large to store on most machines. For N/spl times/N image, the memory needed to store the connections is proportional to N/sup 6/. This huge memory requirement limits the HONN's application to large scale images. In this paper, we have developed an integrated method which combines the bi-directional log-polar mapping and HONN pattern recognizer. It reduces the HONN memory requirement from O(N/sup 6/) to O(N/sup 2/). The proposed method has been successfully verified. Finally, the results are compared with those of coarse-coding method, traditional log-polar method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Automatic target recognition using higher order neural network


    Contributors:
    Liqing Wan (author) / Longhe Sun (author)


    Publication date :

    1996-01-01


    Size :

    311484 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Automatic Target Recognition Using Higher Order Neural Network

    Wan, L. / Sun, L. / IEEE; Dayton Section et al. | British Library Conference Proceedings | 1996


    Neural network based automatic target processing and recognition

    Vasconcelos, G.C. / Adeodato, P.J.L. / Carvalho Filho, E.C.B. et al. | Tema Archive | 1999


    Neural Network Based Automatic Target Processing and Recognition

    Vasconcelos, G. C. / Adeodato, P. J. L. / Filho, E. C. B. C. et al. | British Library Conference Proceedings | 1999


    Neural networks for automatic target recognition

    Chaudhuri, S.P. / Sequeira, C. | Tema Archive | 1990