Abstract
Visual recognition of microelectromechanical parts is necessary for automation of the assembly process. The visual recognition system that we have developed is based partly on neural networks and partly on digital image-processing techniques. The system takes grey-level microscope images and produces recognition code as the output as well as information about micropart position. The recognition procedure is not sensitive to micropart position. This is ensured by preprocessing based on calculation of the image moment properties. For the recognition, a supervised feedforward neural network is utilized. A combination of standard backpropagation and resilient propagation is chosen for learning the network. The performance of the system is tested on recognition of the parts of a microvalve system. The results are satisfactory with respect to recognition accuracy and recognition time.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
