An Analog VLSI Neural Network for Phase-based Machine Vision

We describe the design, fabrication and test results of an analog CMOS VLSI neural network prototype chip intended for phase-based machine vision algorithms. The chip implements an image filtering operation similar to Gabor-filtering. Because a Gabor filter's output is complex valued, it can be used to define a phase at every pixel in an image. This phase can be used in robust algorithms for disparity estimation and binocular stereo vergence control in stereo vision and for image motion analysis. The chip reported here takes an input image and generates two outputs at every pixel corresponding to the real and imaginary parts of the output.