Abstract
In order to improve visual pattern recognition capability, this paper focuses on top-down selective attention at feature space. The baseline recognition system consists of local feature extractors and a multi-layer Perceptron (MLP) classifier. An attention layer is added just in front of the multi-layer Perceptron. Attention gains are adjusted to cope with the top-down attention process and ellucidate expected input features. After attention adaptation, the distance between original input features and expected features becomes an important measure for the confidence of the attended class. The proposed algorithms improves recognition accuracy for handwritten digit recognition tasks, and is capable of recognizing 2 superimposed patterns one by one.
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
Broadbent, D. E.: Perception and Communication. Pergamon Press. (1958)
Cowan, N.: Evolving conceptions of memory storage, selective attention, and their mutual constraints within the human information processing system. Psychological Bulletin 104 (1988) 163–191
Parasuraman, R. (Ed.) The Attentive Brain, MIT Press (1998)
Anderson, C., Olshausen, B., and Essen, D.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. Journal of Neuroscience 13 (1993) 4700–4719
Ltti, L., Kock, C., and Niebur, E.: A Model of saliency-Based Visual Attention for rapid Scene Analysis. IEEE Trans. Pattern Analysis and machine Intelligence 20 (1998)
Fukushima, K.: Neural network model for selective attention in visual pattern recognition and association recall. Applied Optics 26 (1987) 4985–4992
Park, K.Y, Lee, S.Y.: Selective Attention for Noise Robust Speech Recognition, International Joint Conference on Neural Networks, Washington, D.C., July (1999)
Lee, S.Y., Michael C.M. Robust Recognition of Noisy and Superimposed Patterns via Selective Attention. Neural Information Processing Systems 12 (2000)
Arbib, M.A. (Ed.) The handbook of Brain Theory and Neural Networks. MIT Press (1998)
Kim, J.W.: Isolated Word Recognition Using SOFFA Neural Network, Master Thesis, Korea Advanced Institute of Science and Technology (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, SI., Lee, SY. (2000). Top-Down Attention Control at Feature Space for Robust Pattern Recognition. In: Lee, SW., Bülthoff, H.H., Poggio, T. (eds) Biologically Motivated Computer Vision. BMCV 2000. Lecture Notes in Computer Science, vol 1811. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45482-9_13
Download citation
DOI: https://doi.org/10.1007/3-540-45482-9_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67560-0
Online ISBN: 978-3-540-45482-3
eBook Packages: Springer Book Archive