Optoelectronic neural system for vision applications

We present the first implementation, results, and performance analysis of a vision system whose processing core is a prototype hardware neural network based on an optical broadcast architecture. The system captures an image by a CMOS image sensor, compares it with a set of sample patterns (classes), and provides an output that indicates the class which the input image corresponds to. Due to the optoelectronic neural processor characteristics, the number of classes can be enlarged without penalty on the operation speed of the system. © 2004 Society of Photo-Optical Instrumentation Engineers.