Pattern recognition of 1D and 2D signals using normalization and normal transformation
DOI:
https://doi.org/10.3103/S0735272716010027Keywords:
orthogonal transformation, matched filtering, classification, normalization, normal transformation, transformant ratioAbstract
Different classification methods for 1D signals using the normalization, including normalization in terms of level and in terms of step and the normal transformation, have been proposed. Normal filtering is a variant of special matched filtering. The application of normalization in terms of level and normal transformation for 2D signals was also considered. The filter formation and classification algorithms for the considered variants were presented. An algorithm for direct formation of the matrix operator of normal transformation for 1D signal was described. Case studies were used to illustrate the application of above methods. The possibility of a variable scale of input signals was also taken into account.References
ABAKUMOV, V.G.; RYBIN, A.I.; SVATOSH, Y. Biometrical Signals. Genesis, Processing, Monitoring. Kyiv: Nora-Print, 2001 [in Ukrainian].
YAN, I. Nonlinear matched filtering for differences analysis. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 1999, v.42, n.6, p.51-55 [Radioelectron. Commun. Syst., 1999, v.42, n.6, p.50-54].
FINK, L.M. The Theory of Discrete Messages. Moscow: Sov. Radio, 1970 [in Russian].
RYBIN, A.I.; NIZHEBETSKAYA, Y.K.; KUZ’MENKO, O.N.; RYBINA, I.A. Analysis of similarity and difference of images. Modified classification method on a basis of correlation matrix. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 2010, v.53, n.11, p.29-37 [Radioelectron. Commun. Syst., 2010, v.53, n.11, p.591-598, DOI: http://dx.doi.org/10.3103/S0735272710110038].
RYBIN, A.I.; NIZHEBETSKAYA, Y.K. Analysis of images similarity and difference using normal orthogonal conversion. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 2010, v.53, n.3, p.58-64, [Radioelectron. Commun. Syst., 2010, v.53, n.3, p.167-172, DOI: http://dx.doi.org/10.3103/S0735272710030076].
MELNYK, A.D.; RYBIN, A.I. Normalization of a reference signal with constant quantization step. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 2008, v.51, n.1, p.71-75, [Radioelectron. Commun. Syst., 2008, v.51, n.1, p.50-52, DOI: http://dx.doi.org/10.3103/S073527270801007X].
RYBIN, A.I.; MELNYK, A.D. Matched normalized signal filtering. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 2008, v.51, n.2, p.77-80 [Radioelectron. Commun. Syst., 2008, v.51, n.2, p.112-114, DOI: http://dx.doi.org/10.3103/S0735272708020106].
MELNYK, A.D.; RYBIN, A.I. Matched wavelet filtering of signals with change scale. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 2008, v.51, n.3, p.76-80 [Radioelectron. Commun. Syst., 2008, v.51, n.3, p.173-175, DOI: http://dx.doi.org/10.3103/S0735272708030114].
RYBIN, A.I. Normalization of discrete orthogonal transformations by a reference signal. Izv. Vyssh. Uchebn. Zaved., Radioelektron., 2004, v.47, n.7, p.39-46 [Radioelectron. Commun. Syst., 2004, v.47, n.7, p.33].
RYBIN, A.I.; NIZHEBETSKAYA, Y.K.; TKACHUK, A.P.; SHARPAN, O.B. Normal discrete orthogonal transformation of an arbitrary shape signal. Research Bulletin of NTUU KPI, 2008, n.4, p.34-40.
RYBIN, A.I.; NIZHEBETSKAYA, Y.K.; LUTSKIV, A.M. Authentification of person on the dinamically entered signature at the use of normal transformation. Visnyk NTUU KPI. Ser. Radiotekhnika. Radioaparatobuduvannya, 2010, n.40, p.26-30.
RYBIN, A.I.; SHARPAN, O.B. Diagnostic capabilities of the normalization procedure for orthogonal functions in pulsogram analysis. Visnyk ZhDTU, 2004, v.1, n.4, p.144-149.
RYBIN, A.I.; SAKALOSH, T.V.; SHARPAN, O.B. Analysis of pulsograms based on the normalization procedure for orthogonal transformations REX. Research Bulletin of NTUU KPI, 2005, n.4, p.29-33.
RYBIN, A.I.; MELNYK, A.D. Algorithm of classification of sound signals. Visnyk NTUU KPI. Ser. Radiotekhnika. Radioaparatobuduvannya, 2008, n.36, p.5-9.
MELNYK, A.D.; RYBIN, A.I. Recognition of vowel sounds ‘a’, ‘o’, ‘u’, ‘e’ of Ukrainian language. Research Bulletin of NTUU KPI, 2009, n.1, p.20-25.
