Email this article Segmentation and defect detection on large areas in several frames
- Authors: Bukalov G.K.1, Burygin A.O.1, Panin I.G.1, Tortsev A.V.1
-
Affiliations:
- Kostroma State University
- Issue: Vol 28, No 1 (2022)
- Pages: 20-25
- Section: Digital processing of signals and images
- Published: 15.01.2022
- URL: https://journals.eco-vector.com/1684-6400/article/view/702693
- DOI: https://doi.org/10.17587/it.28.20-25
- ID: 702693
Cite item
Full Text
Abstract
In article we consider the problem of finding defects on large areas with a limited set of defective images. Two regularization methods are presented that help to significantly increase the result of defect segmentation, namely, the operation of inserting defects into non-abnormal images and the operation of normal. Computational experiments aimed at investigating the effectiveness of the proposed method in comparison with existing techniques have been carried out.
About the authors
G. K. Bukalov
Kostroma State University
Author for correspondence.
Email: gk.bukalov44@yandex.ru
Professor
Russian Federation, KostromaA. O. Burygin
Kostroma State University
Email: g.t.m.p@yandex.ru
PhD Student
Russian Federation, KostromaI. G. Panin
Kostroma State University
Email: igpanin@list.ru
Professor
Russian Federation, KostromaA. V. Tortsev
Kostroma State University
Email: fullfulk47458@gmail.com
PhD Student
Russian Federation, KostromaReferences
- Ruff L., Vandermeulen R., Goernitz N., Deecke L., Siddiqui S. A., Binder A., Müller E., Kloft M. Deep one-class classification, International conference on machine learning, 2018, pp. 4393—4402.
- Schlegl T., Seeböck P., Waldstein S. M., SchmidtErfurth U., Langs G. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery, International conference on information processing in medical imagin, Springer, 2017, pp. 146—157.
- Lin M., Chen Q., Yan S. Network in network, arXiv:1312.4400, 2013.
- Zhou Z., Siddiquee M. M. R., Tajbakhsh N., Liang J. UNet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging, 2019.
- Iglovikov V., Shvets A. Ternausnet: U-Net with VGG11 encoder pre-trained on imagenet for image segmentation, arXiv:1801.05746, 2018.
- Shvets A. A., Rakhlin A., Kalinin A. A., Iglovikov V. I. Automatic instrument segmentation in robot-assisted surgery using deep learning, 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018, pp. 624—628.
- Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation, International Conference on Medical image computing and computer-assisted intervention, 2015, pp. 234—241.
- Rezatofighi H., Tsoi N., Gwak J., Sadeghian A., Reid I., Savarese S. Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression, arXiv: 1902.09630, 2019.
- Karimollah Hajian-Tilaki. Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation, PMCID: PMC375582, 2013.
- Bukalov G. K., Burygin A. O, Panin I. G, Tortsev A. B. Defect detection using FCN modification for finding rare defects on large areas, Informatsionnye tekhnologii, 2020, vol. 26, no. 12, pp. 683—687 (in Russian), doi: 10.17587/it.26.683-687.
Supplementary files
