Вдосконалення цифрової обробки зображень кольорової капілярної дефектоскопії

Abstract

Penetrant inspection (capillary inspection or capillary flaw detection) is primarily aimed at the industrial sector to inspect metal objects such as oil and gas pipelines, as well as various components of machinery to prevent malfunctions and accidents. Among the defects that can be detected using this method are fatigue cracks, hairlines, pores, and pore clusters. An analytical review of technical literature sources and major publications on the topic of algorithms for digital image processing of indicator traces in capillary flaw detection was carried out. As a result of the analysis of the obtained digital images, the color features of indicator traces in capillary flaw detection were revealed, which led to the development of an algorithm for binary conversion of the digital image of the indicator trace.