DocumentCode
3291538
Title
An ultrasonic visual sensor using a neural network and its application for automatic object recognition
Author
Watanabe, Sumio ; Yoneyama, Masahide
Author_Institution
Ricoh Co Ltd., Yokohama, Japan
fYear
1991
fDate
8-11 Dec 1991
Firstpage
781
Abstract
An ultrasonic visual sensor using a neural network is proposed and improved by reducing both the size of the neural network and the number of teaching samples. A 3-D image calculated by acoustic imaging is transformed into position and rotation invariant values, and then reorganized by a multilayered neural network. Many categories of metal or glass objects can easily be classified with this system, even when they are placed at unknown positions or rotation angles
Keywords
acoustic imaging; acoustic signal processing; computer vision; feedforward neural nets; image recognition; ultrasonic applications; 3-D image; US robot eye; acoustic imaging; automatic object recognition; glass objects; metal object; multilayered neural network; position invariant values; robotic vision; rotation invariant values; ultrasonic visual sensor; Acoustic imaging; Acoustic sensors; Gas detectors; Glass; Multi-layer neural network; Neural networks; Optical imaging; Optical receivers; Research and development; Robot vision systems;
fLanguage
English
Publisher
ieee
Conference_Titel
Ultrasonics Symposium, 1991. Proceedings., IEEE 1991
Conference_Location
Orlando, FL
Type
conf
DOI
10.1109/ULTSYM.1991.234084
Filename
234084
Link To Document