Design and basic blocks of a neuromorphic VLSI analogue vision system

In this paper we present a complete neuromorphic image processing system and we report the development of an integrated CMOS low-power circuit to test the feasibility of its different stages. The image system consists of different parallel-processing stages: phototransduction, non-linear filtering, oscillatory segmentation network and post-processing to extract fundamental characteristics. The circuit presented emulates parts of the behaviour of biological neural networks as found in the retina and the visual cortex of living beings, adopting the neuromorphic approach that takes advantage of analogue VLSI electronics. The final objective is to develop a small and low-power system embedded in a single focal-plane integrated circuit to be used in portable applications. Each stage is briefly described. Simulations and experimental results of some basic blocks are also reported. 1. Introduction The commonly used digital approach to solving electronic problems has some important advantages as flexibility, precision and moderate design complexity compared to other alternatives as analogue ones. However, the latter have some advantages that should be considered for small and low-power electronic systems which are required for the increasing market of portable applications. The main advantage is the possibility of reducing power consumption and area overhead, which are improved when used in large scale of integration technologies.