The paper presents numerical restrictions of Bayesian method to a pattern recognition. The maximum probability of local state correspondence to one of the basis patterns is defined through the expansion of examined vector over the patterns. The practical recognition example without errors is presented in the frame of nearest neighbor method for the case, when the probability interpretation of the expansion coefficients is not valid. The spectral portraits of solving matrices are constructed for the literature texts author identification problem. Also, the statistical properties of letters frequencies in European literature texts are investigated. The determination of logarithmic dependence of letters sequence for one-language and two language texts are examined. The Voynich Manuscript structure was considered for numerical analysis. After our numerical analysis, we suppose, that the Voynich Manuscript was written in two languages having the same alphabet without vowel letters: one of the Germanic languages (Danish or German) and one of the Romance languages (Latin or Spanish). Copyright © 2018 for the individual papers by the papers’ authors.