Formation spaces of informative features inherent in classes from properties of images of the training sample

The article sets the task of determining individual features and forming a space of informative features inherent in a class from the properties of images of the training sample, as well as constructing decision rules for pattern recognition. The problems of selecting and forming feature subsystems...

Full description

Saved in:
Bibliographic Details
Main Authors: Bekmuratov, Kosim, Fayziyev, Vokhid, Kholiyorov, Kholbek
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Pattern recognition
Subsystems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The article sets the task of determining individual features and forming a space of informative features inherent in a class from the properties of images of the training sample, as well as constructing decision rules for pattern recognition. The problems of selecting and forming feature subsystems inherent in the class are solved by sequentially checking the initial properties of the images of the training sample, as well as minimizing the generated feature subsystems and, based on them, constructing a decisive rule for pattern recognition. An algorithm was developed based on the proposed procedures. Conclusions on the study as a whole are also presented.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0210516