Analytical method for processing digital images of technical objects

Andrzej Kotyra, Тамара Антоновна Манько, Iryna Husarova, Вікторія Огоренко, I. I. Derevianko, Г. В. Лисачук, Ruslan Kryvobok, Оlena Lapuzina, Saule S. Smailova

2018

Closed access Metadata (CSL-JSON)

DOI 10.1117/12.2501695

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The paper presents a method of processing digital images of technical objects whose surfaces are inaccessible. An analytical method of vision data preparation for supporting the decision making about the presence of abnormal areas is presented. The method takes into account the changes of some statistical brightness parameters (intensity, correlation, coordinates, sizes, and shapes) by analyzing matrices of brightness fluctuation, differences (estimates of the rate of brightness changes), variances and correlations, containing information about their state.