Multilayer perceptron as the primary instrument for image clustering

Abstract

A multilayer perceptron as an instrument of the primary analysis of the image, in particular, its application to search for regions of interest or clusterization is described. Various implementations of training procedures to receive a minimum structure of a net, select size of areas effectively and choose the step size between the regions are considered. Coefficient for comparison of matrixes with class labels is proposed, examples of its usage are shown. Experimental investigations have confirmed the effectiveness of the proposed methods. Tabl.: 4. Fig.: 7. Refs: 9 titles.

Authors and Affiliations

O. Gorokhovatskiy

Keywords

Related Articles

Development of representations of hyperbolic and trigonometric nonlinearities inside the system of generalized quaternions

It is considered the process of mathematical modeling for representations of hyperbolic and trigonometric nonlinearities in hypercomplex number system of generalized quaternions by the method of associated system of diff...

Problems of Expert Data Representation in Decision Support Systems

It has been described the basic peculiarities of interaction with an expert, characterizing different expert examination stages. It is shown that at each examination stage, involving the physical expert, certain problems...

Multi-agent approach to modeling an information and analytical system

It is considered some questions of realization of multi-agent approach to modeling of information and analytical system which is realized in the form of the appropriate information technology, for to utilize further appl...

Actual problems of long-term preservation of documentation in insurance fund of documentation of Ukraine

The directions in which the research is conducted to ensure long-term preservation of copies of documents in the insurance fund of documentation of Ukraine are presented. It is shown that in the state system of insurance...

A model of functioning process of the aircraft’s cross-correlation extreme navigation system and the factors affecting on the accuracy and productivity of the image processing

A generalized model of functioning process of the cross-correlation extreme navigation systems taking into account basic factors of the indeterminacy of functioning conditions due to the influence of various interference...

Download PDF file
  • EP ID EP177983
  • DOI -
  • Views 97
  • Downloads 0

How To Cite

O. Gorokhovatskiy (2016). Multilayer perceptron as the primary instrument for image clustering. Реєстрація, зберігання і обробка даних, 18(4), 33-43. https://europub.co.uk/articles/-A-177983