The Use of Machine Learning Methods to Detect Defects in Images of Metal Structures

Dementiev, Vitaly; Gaponova, Maria; Suetin, Marat R.; Streltzova, Anastasia S.

doi:10.1007/978-3-030-68821-9_12

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous work [17,18], an approach for detecting defects based on the use of an artificial neural network U-Net [11] has already been described. At the same time, we used the classical approach associated with the formation of a training sample, optimizing the weights and network structure for this sample, as well as checking the quality of the network on images that were not included in the training sample.…”

Section: Processing Architecture Synthesismentioning

confidence: 99%

Using Machine Learning Methods to Solve Problems of Monitoring the State of Steel Structure Elements

Gaponova

Dementiev

Suetin

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The paper considers the issues related to the monitoring of the state of steel structures. Such monitoring is proposed to be based on the processing of video images obtained during the inspection of structural elements. The pro-cessing is performed using combinations of artificial neural networks that have passed special training procedures based on transfer learning technologies. This approach allows to overcome the problems of training and post-training of neural networks on small volume samples. The received results allow to claim the possibility of using the developed procedures for searching important classes of defects (in particular, cracks) on images and defining their parameters (size, class, danger degree, etc.). Thus work quality of these procedures (in particular the probability of correct detection and false alarms) appears to be close to the quality of work of competent personnel.

show abstract

Section: Processing Architecture Synthesismentioning

confidence: 99%