3-DIMENSIONAL SHAPE-RECOGNITION USING A CHARGE-SIMULATION METHOD TO PROCESS PRIMARY IMAGE FEATURES

The feasibility of the charge-simulation method (CSM) algorithm to pro cess primary image features for three-dimensional shape recognition is examined. To achieve this, a machine vision system was developed whic h consists of a light source, light beam conditioner, artificial retin a installed with photo-sensors, data transfer unit and a computer inst alled with analogue-to-digital converter peripherals. The system was u sed to acquire primary image features for oranges and eggplants. The f eatures were transferred to a retina model identical to the prototype artificial retina and were compressed using the CSM by computing outpu t signals at work cells located in the retina. With these signals, neu ral networks were trained to classify each image sample in order to id entify their shape. An overall classification rate of 94.0% was obtain ed when the prototype artificial retina discriminated between distinct shapes of oranges and eggplants. An overall rate of 75% was achieved when discriminating between less distinct shapes of straight and curve d eggplants. The results show that it is feasible for the artificial r etina based on the CSM algorithm to process primary image features for three-dimensional shape recognition. (C) 1998 Silsoe Research Institu te.