Interactive Wear Particle Image Annotation Method

Abstract

The invention discloses an interactive wear particle image annotation method, which comprises steps as follows: step 1, inputting a to-be-annotated image which contains a wear particle image; step 2, inputting interactive annotation information for the to-be-annotated image; step 3, segmenting the to-be-annotated image as per the interactive annotation information; step 4, judging whether the segmentation result is the wear particle image, if not, carrying out step 5, and if yes, carrying out step 6; step 5, inputting the interactive annotation information once more or for supplement, and then carrying out steps 3 and 4; step 6, outputting the wear particle image; and step 7, annotating category information to the wear particle image. Through the interactive wear particle image annotation method provided by the invention, an annotated image can be quickly and accurately obtained as per the to-be-annotated image, so that the efficiency of constructing a wear particle image sample bank can be greatly improved.

Description

technical field [0001] The invention relates to the field of oil monitoring, in particular to an interactive wear grain image labeling method, a wear grain map library construction method and a wear grain image automatic recognition system. Background technique [0002] Oil monitoring is an application technology that detects and analyzes oil samples in use to determine the state of oil products and equipment. Through early forecasting of abnormal signs of oil decay, pollution, and component wear, it allows equipment users and managers to perform maintenance and repairs in real time to avoid major accidents and extend the service life of equipment and oil. Oil wear particles (abbreviated as wear particles) map analysis is mainly based on microscopic observation and analysis of wear particles collected by technical means such as magnetic plug, oil filter and analytical ferrography. On the one hand, it can analyze abrasive grains ranging in size from 1um to 1000um, covering a...

AI Technical Summary

Problems solved by technology

At present, the wear particle map library established in China is mainly used for manual comparison and identification. Therefore, the wear particle image area is not accurately segmented, but only a local map area containing typical wear particle images and background images is given, which is not accurate. Applicable to the needs of establishing an automatic recognition system for wear grain images

[0004] For the establishment of an accurate wear particle image library, the existing technology mainly establishes an accurate wear particle image library by completely manual labeling, which requires a lot of labor and time, and is inefficient; and based on a fully automatic segmentation method ( Such as automatic threshold method, etc.), although it can accurately segment the abrasive grains with a simple background, it is ineffective for the complex abrasive grains that occupy most of the background

Images