Abstract
This paper presents a log-polar image representation composed of low-level features extracted using a connectionist approach. The low level features (edges, bars, blobs and ends) are based on Marr’s primal sketch hypothesis for the human visual system [3] and are used as the entry point of an iconic vision system [1]. This unusual image representation has been created using a neural network that learns examples of the features in a window of receptive fields of the image representation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
T. D. Grove and R. B. Fisher. Attention in iconic object matching. In R. B. Fisher and E. Trucco, editors, 7th British Machine Vision Conf., volume 1, pages 293–302, 1996.
A. C. Hurlbert. Neural network approaches to color vision. In H. Wechsler, editor, Neural Networks for Perception, volume 1 (Human and Machine Perception), chapter II.5, pages 265–284. Academic Press, 1992.
D. Marr. Vision. W. H. Freeman and Co., 1982.
J. P. Siebert and I. Eising. Scale-space recognition based on the retino-cortical transform. In Proc. IEE Conference on Image Processing and its Applications, 1995. Edinburgh.
R. Watt. Understanding Vision. Academic Press, 1991.
S. W. Wilson. On the retino-cortical mapping. Int. J. Man-Machine Studies, 18:361–389, 1983.
A. L. Yarbus. Eye Movements and Vision. Plenum Press, 1967.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gomes, H.M., Fisher, R.B., Hallam, J. (1998). A Retina-like Image Representation of Primal Sketch Features Extracted using a Neural Network Approach. In: Marshall, S., Harvey, N.R., Shah, D. (eds) Noblesse Workshop on Non-Linear Model Based Image Analysis. Springer, London. https://doi.org/10.1007/978-1-4471-1597-7_39
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1597-7_39
Publisher Name: Springer, London
Print ISBN: 978-3-540-76258-4
Online ISBN: 978-1-4471-1597-7
eBook Packages: Springer Book Archive