Neural network visual recognition for automation of the microelectromechanical systems assembly

A neural network visual recognition system is developed. The system is intended for automation of microsystem assembly process. The recognition of microparts is insensitive on their position. This feature is enabled by calculation of the moment properties of the image during preprocessing. The system takes grey-level images and produces recognition code as the output. A feed-forward neural network is used for recognition. Learning of the neural network is performed by combination of standard backpropagation and resilient propagation rule. The system performance is satisfactory with respect to recognition accuracy and recognition time.