Object detecting artificial retina

This paper describes the novel use of agent and cellular neural Hopfield ne twork techniques in the design of a self-contained, object detecting retina . The agents, which are used to detect features within an image, are traine d using the Hebbian method which has been modified for the cellular archite cture. The success of each agent is communicated with adjacent agents in or der to verify, the detection of an object. Initial work used the method to process bipolar images. This has now been extended to handle grey scale ima ges. Simulations have demonstrated the success of the method and further wo rk is planned in which the device is to be implemented in hardware.