Abstract
Retinas are very important for human beings to get information about their environment. In this paper, we propose a new method to build artificial retinas which have many features similar to real ones. We use evolutionary cellular automata to extract some basic characteristics of objects, and use self-organizing neural networks to distinguish different objects. The results indicate a way to get computer vision by artificial life.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kuma K, Lange E et al. Artificial retinas—fast, versatile image processor. Nature 372(6502):197–198
Funatsu E, Hara K, Toyoda T et al An artificial retina chip made of a 128*128 pn-pn variable-sensitivity photodetector array. IEEE Photonics Technol Lett 7:188–190
Kim KI, Shin CW, Inoguchi, S (1995) Collision avoidance using artificial retina sensor in ALV. Proceedings of the Intelligent Vehicles 1995 Symposium
Casti JL (1992) Reality rules: picturing the world in mathematics. Wiley
Preston Jr K, Duff MJB (1984) Mordern cellular automata theory and applications. Plenum
Kuffler SW, Nicholls JG, Martin AR, (1984) From Neuron to Brain. 2nd edn. Sinauer
Kohonen T (1995) Self-organizing maps. Springer
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Wu, X., Zhang, Y. & Sugisaka, M. Developing an artificial retina by evolutionary cellular automata and self-organizing neural networks. Artif Life Robotics 3, 61–64 (1999). https://doi.org/10.1007/BF02481248
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02481248