The goal of every computer vision system is to at least match human perceptual abilities at performing a desired task. Hence the need to have an interest in and be knowledgeable of human perceptual abilities is implicit to the discipline of computer vision. If one desires to create a general purpose computer vision system the best place to look to gain general insights into how to construct such a system would seemingly be to examine what is known about human perceptual mechanisms. With this in mind the general scene analysis and image analysis strategies of the human visual system will be reviewed. Based on an analysis of these strategies it will be argued that what is needed to create a general purpose vision system is a quantitative model of human preattentive vision. Further it will be argued that this quantitative model should be based on what has been classically called texture operators.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    The Need For A Quantitative Model Of Human Preattentive Vision


    Beteiligte:

    Kongress:

    Applications of Artificial Intelligence V ; 1987 ; Orlando,FL,United States


    Erschienen in:

    Erscheinungsdatum :

    1987-05-11





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Preattentive Computer Vision: A New Model

    Leavers, V. F. | British Library Conference Proceedings | 1995


    Perceptual learning in preattentive vision

    Sagi, D. | British Library Conference Proceedings | 1993


    Sensor fusion: a preattentive vision approach

    Watkins, Wendell R. / CuQlock-Knopp, V. Grayson / Jordan, Jay B. et al. | SPIE | 2000


    Preattentive computer vision:a new model

    Leavers,V.F. / Univ.of Manchester,GB | Kraftfahrwesen | 1995


    Fuzzy model for scene decomposition based on preattentive visual features

    Brown, R. A. / Pham, B. / Maeder, A. J. et al. | British Library Conference Proceedings | 1999