Improving the accuracy of estimating the measure of proximity between objects during recognition

Authors

DOI:

https://doi.org/10.18372/2073-4751.69.16805

Keywords:

pattern recognition, proximity measures between objects, error, recognition reliability, invariance

Abstract

The article analyzes the problem of the occurrence of errors in measuring the geometric parameters of objects in pattern recognition, possible ways to minimize them, and as a result of this analysis, an algorithm is proposed for effectively increasing the reliability of pattern recognition by adequately estimating the measure of proximity between recognized and standard objects. The article considers a model for the process of estimating the measure of proximity between objects and the resulting errors, proposes conditions and an algorithm for minimizing these errors, and recommends measures to improve the accuracy of estimating the measure of proximity between objects.

References

Faure A. Perception and pattern recognition / Translated from French. A.V. Seredinsky. Under the editorship of G.P. Katys.M. // Mechanical Engineering. – 1989. – 272 p.

Mamedov R.K. Analysis of methods for improving the reliability of image recognition by technical vision systems. Automation and modern technologies. – 1998. – No. 9. – P. 21-26.

Mamedov R.K. Fundamentals of building vision systems with invariant image recognition. Automation and modern technologies. – 1998. – No. 6. – P. 9-12.

Mamedov R.K. Using the Euclidean distance for an accurate assessment of the measure of proximity between objects in pattern recognition. Metrology. – 1998. – No. 3. – P. 10-14.

Downloads

Published

2022-02-17

Issue

Section

Статті