Electronic Implementation of Biologically Inspired Neuromorphic Vision Sensor

Neuromophic vision sensor is an electronic implementation of vision algorithm on semiconductor. Neuromophic systems are biologically inspired artificial neural systems that mimic algorithmic behavior of biological systems. The focus of this paper is to highlight photo transduction operation and conversion of optical information into the neuronal signal in the similar fashion as it takes place in biological retina. These systems have efficient adaptive and intelligent control techniques resembling with biological nervous system based on optical and electronic signal processing properties of semiconductor materials. Proposed electronic model contains adaptive photoreceptors as light sensors and other circuit components such as averaging circuits; circuits representing ganglion cells; neuronal firing circuits etc these entire elements junction to sense brightness, size, shape and orientation to distinguish objects in closer proximity. Neuromophic vision chip can lead towards development of sensory based artificial systems having parallel collective computation, adaptation, learning and memory implemented locally at each stage of processing of information.