An application of neural networks to an ultrasonic 3-D visual sensor
Shinji Watanabe, Hiroki Watanabe, Akihiko Saitou, M. Yoneyama · 1991
An ultrasonic 3-D visual sensor is devised using multilayered neural networks. Neural networks improve acoustic images and identify objects' categories. Despite low image resolution fine images are restored and high recognition rates are obtained. A practical application of this neural ultrasonic sensor to automatic object recognition is also reported.>