Abstract
We have demonstrated recently that, by using an ultrastable optical interferometer together with artificial neural networks (ANNs), track widths down to can be measured with a 0.3 NA objective lens. We investigate the effective conditions for training ANNs. Experimental results will be used to show the characteristics of the training samples and the data format of the ANN inputs required to produce suitably trained ANNs. Results obtained with networks measuring double tracks, and classifying different structures, will be presented to illustrate the capability of the technique. We include a discussion on expansion of the application areas of the system, allowing it to be used as a general purpose instrument.
© 2007 Optical Society of America
Full Article | PDF ArticleMore Like This
Yuan-sheng Ma, Xu Liu, Pei-fu Gu, and Jin-fa Tang
Appl. Opt. 35(25) 5035-5039 (1996)
Niklas Wartha, Anton Stephan, Frank Holzäpfel, and Grigory Rotshteyn
Opt. Express 30(8) 13197-13225 (2022)
Shiming Wei and Lifeng Li
Appl. Opt. 47(13) 2524-2532 (2008)