1 February 1991 Neural net selection of features for defect inspection
Author Affiliations +
Proceedings Volume 1384, High-Speed Inspection Architectures, Barcoding, and Character Recognition; (1991) https://doi.org/10.1117/12.25327
Event: Advances in Intelligent Robotics Systems, 1990, Boston, MA, United States
Abstract
An artificial neural network (ANN) fed with optically generated features is applied to IC inspection. The data used are characters with defects in them that model those expected in IC patterns. The ANN is used in training to select the best features. This results the required number of neurons needed during defect testing. Simulation results are provided for four types of defects using optical Fourier Wedge-Ring (WR) sampled Fourier and Hough feature spaces.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kenji Sasaki, Kenji Sasaki, David P. Casasent, David P. Casasent, Sanjay S. Natarajan, Sanjay S. Natarajan, } "Neural net selection of features for defect inspection", Proc. SPIE 1384, High-Speed Inspection Architectures, Barcoding, and Character Recognition, (1 February 1991); doi: 10.1117/12.25327; https://doi.org/10.1117/12.25327
PROCEEDINGS
6 PAGES


SHARE
Back to Top