By Topic

Pattern recognition techniques for hybrid microcircuits

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Nakashima, M. ; Fujitsu Laboratories Ltd., Atsugi, Kanagawa, Japan ; Koezuka, T. ; Tsukahara, H. ; Inagaki, T.

The paper discusses pattern recognition techniques for automatic hybrid IC assembling systems. The problems concerning recognition systems are flexibility and high recognition rates for various object patterns comprised of hybrid ICs. To overcome these problems we developed two new recognition algorithms based on pattern matching methods. One method recognizes speckle pattern (printed thick-film conductor patterns) locations using matrix filtering. The other method increases the matching SNR to 4.5 times greater than previous methods using peak sharpening of the matching degree curve. These algorithms enable recognition of more than 99% (99.8% on average) of all semiconductor chip patterns (ICs, transistors, and diodes) and printed thick-film conductor patterns.

Published in:

Robotics and Automation. Proceedings. 1984 IEEE International Conference on  (Volume:1 )

Date of Conference:

Mar 1984