Abstract
Singularities in visual cortex have been proved to be invariant to orientation. Modelling the mechanism, we explore a recurrent network to realize rotation invariant object recognition. Images sequences as inputs are used to form distinctive features, similar to responses of complex cells. Then recurrent connections decrease distinction of these complex cells leading to emergence of singularities. Invariant features from the singularities acting with memory trace perform object recognition. Memory trace extracts correlations of different views of the same objects from continual sequences, and therefore is fit for performing recognition tasks in visual information processing systems. We testify efficacy of the model by benchmark recognition problem. Our model’s plausibility in neurobiology view and practicality in recognition are also discussed.
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
Marr, D.: Vision. W.H. Freeman and company, San Francisco (1982)
Hasselmo, M.E., Rolls, E., Baylis, G.: The Role of Expression and Identity in the Faceselective Responses of Neurons in the Temporal Visual Cortex of the Monkey. Behav. Brain Res. 32, 203–218 (1989)
Peters, A., Payne, B.R.: A Numerical Analysis of the Geniculocortical Input to Striate Cortex in the Monkey. Cereb. Cortex. 4, 215–229 (1994)
Furmanski, C.S., Engel, S.A.: Perceptual Learning in Object Recognition: Object Specificity and Size Invariance. Vision-Research 40(5), 473–484 (2000)
Fordiak, P.: Learning Invariance from Transformation Sequences. Neural Computation 3(2), 194–200 (1991)
Morrone, M.C., Burr, D.C.: Feature Detection in Human Vision: a phase-dependent energy model. Proc. Royal soc. London ser. B 235(1280), 221–245 (1988)
Wiskott, L., Sejnowski, T.: Slow Feature Analysis: Unsupervised learning of Invariances. Neural Computation 14, 715–770 (2003)
Frances, S., Chance, S.B., Nelson, L.F.: Abbott: Complex Cells as Cortically Amplified Simple Cells. Nature neuroscience 2(3), 277–282 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qi, Z., Luo, S. (2004). Modelling Singularity in Vision to Learn Rotation Invariance toward Recognition. In: Tawfik, A.Y., Goodwin, S.D. (eds) Advances in Artificial Intelligence. Canadian AI 2004. Lecture Notes in Computer Science(), vol 3060. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24840-8_51
Download citation
DOI: https://doi.org/10.1007/978-3-540-24840-8_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22004-6
Online ISBN: 978-3-540-24840-8
eBook Packages: Springer Book Archive