Home > Conference materials > Papers > Statistical regression method of shape analysis, with application to classification of cross-sections of carbon fibers
Original title:
Statistical regression method of shape analysis, with application to classification of cross-sections of carbon fibers
Authors:
Linka, A. ; Volf, Petr Document type: Papers Conference/Event: ROBUST'2002 /12./, Hejnice (CZ), 2002-01-21 / 2002-01-25
Year:
2002
Language:
eng Abstract:
Unfolded contours of textile fibers cross-sections are described as a smooth periodical curve contaminated with local nonregularities, and are analyzed with the aid of the regression model. The corresponding regression curve is constructed as the combination of trigonometric functions, its complexity is optimized by methods of mathematical statistics. It is shown, by random sampling, that the parameters of the model correspond to different deformations of circular contour.
Keywords:
shape analysis; statistical methods; textile fibers Project no.: CEZ:AV0Z1075907 (CEP), GA106/01/0565 (CEP) Funding provider: GA ČR Host item entry: ROBUST'2002. Sborník prací dvanácté zimní školy JČMF
Institution: Institute of Information Theory and Automation AS ČR
(web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences. Original record: http://hdl.handle.net/11104/0131110