ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 12. Vol. 26. 2020

DOI: 10.17587/it.26.683-687

G. K. Bukalov, Professor, e-mail: gk.bukalov44@yandex.ru, A. O. Burygin, PhD student, e-mail: g.t.m.p@yandex.ru,
I. G. Panin, Professor, e-mail: igpanin@list.ru, A. B. Tortsev, student, e-mail: fullfulk47458@gmail.com, Kostroma State University

Defect Detection Using FCN Modification for Finding Rare Defects on Large Areas

There is problem of finding defects on a textile sling on large areas. For this purpose, the image goes through several stages: creation of a convolutional U-Net network, extraction of U-Net features, classification by the Random Forest algorithm, and identification of defective areas via MSER. The Random Forest classifier is used to segment parts of the input image obtained from U-Net. Computational experiments were conducted to study the effectiveness of the proposed method in comparison with existing methods.
Keywords: sling, image, CNN, U-Net, MSER, Random Forest

P. 683–687

To the contents