Optical track width measurements below 100 nm using artificial neural networks

R. J. Smith, C. W. See, Michael Geoffrey Somekh, A. Yacoot, E. Choi

Research output: Journal article publicationJournal articleAcademic researchpeer-review

3 Citations (Scopus)


This paper discusses the feasibility of using artificial neural networks (ANNs), together with a high precision scanning optical profiler, to measure very fine track widths that are considerably below the conventional diffraction limit of a conventional optical microscope. The ANN is trained using optical profiles obtained from tracks of known widths, the network is then assessed by applying it to test profiles. The optical profiler is an ultra-stable common path scanning interferometer, which provides extremely precise surface measurements. Preliminary results, obtained with a 0.3 NA objective lens and a laser wavelength of 633 nm, show that the system is capable of measuring a 50 nm track width, with a standard deviation less than 4 nm.
Original languageEnglish
Pages (from-to)2397-2404
Number of pages8
JournalMeasurement Science and Technology
Issue number12
Publication statusPublished - 1 Dec 2005
Externally publishedYes


  • Artificial neural networks
  • Common path scanning interferometer
  • Optical track-width measurements

ASJC Scopus subject areas

  • Instrumentation
  • Engineering (miscellaneous)
  • Applied Mathematics

Cite this