Abstract
Key fields in image understanding are pattern processing and symbol processing. Often, these processes have been studied independently. In this paper, we propose a hybrid system for early stage image understanding in which symbol processing and pattern processing are used complementarily and in parallel. Here, the common knowledge that is necessary for their interaction is automatically acquired using the image recollection ability of the Selective Attention Model. Local pattern features are converted into a symbolic description. We have developed an image segmentation system which is able to recover the lacking part of given object using symbolic inference. The system was applied to an occluded image and the usefulness of the hybrid system was demonstrated.
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.
References
Brooks, R. A.: Symbolic Reasoning Among 3-D Models and 2-D Images, Artificial Intelligence Journal, Vol. 17 (1–3), pp. 285–348, 1981
T. Matsuyama: Knowledge-Based Aerial Image Understanding Systems and Expert Systems for Image Processing, IEEE Trans. on Geoscience and Remote Sensing Vol.GE-25, No.3, pp.305–316, 1987
Lee, Chen, Sun and Tseng: Occluded objects recognition using multiscale features and Hopfield neural network, Pattern Recognition vol.30 No.1 pp.113–122, 1997
Yeung and Chan: Incorporating production rules with spatial information onto a Neocognitron neural network, International Jurnal of Neural Systems, Vol.5 No.2 pp.131–142, 1994
Nishi, Ozeki, Sakurai, Omori: An Architecture for Image Understanding by Symbol and Pattern Integration—Mutual Conversion of Pattern and Symbolic Knowledge-, SICE, Vol.30, No.11, 1368–1377, 1994 (In Japanese)
Fukushima: “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position”, Biological Cybernetics, 36[4], pp. 193–202, 1980
Fukushima: A neural network model for selective attention in visual pattern recognition, Biological Cybernetics, 55[1], pp. 5–15, 1986
Tsuji, Mitsumori, Saeki, Omori: Image Understanding by Mutual Evaluation of Symbol and Pattern Processing, Meeting on Image Recognition and Understanding, No.2 pp.19–24, 1996, (In Japanese)
Mitsumori, Saeki, Tsuji and Omori: Hybrid Architecture for Image Understanding by Mutual Evaluation of Symbol and Pattern Processing, Proc. of ICONIP96, pp.444–449, 1996
Tanigawa, Fukushima: How to Adjust the Thresholds of Feature-Extracting Cells in the Neocognitron, IEICE, D-II, Vol. J76-D-II, No. 10 pp.2215–2222, 1993(In Japanese)
Lovell, Downs and Tsoi: An Evaluation of The Neocognitron, IEEE TRANSACTIONS ON NEURAL NETWORKS, Vol.8, No.5, pp. 1090–1105, 1997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mitsumori, Y., Omori, T. (1999). Segmentation of occluded objects using a hybrid of selective attention and symbolic knowledge. In: Mira, J., Sánchez-Andrés, J.V. (eds) Foundations and Tools for Neural Modeling. IWANN 1999. Lecture Notes in Computer Science, vol 1606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098241
Download citation
DOI: https://doi.org/10.1007/BFb0098241
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66069-9
Online ISBN: 978-3-540-48771-5
eBook Packages: Springer Book Archive