Tomsk, Tomsk, Russian Federation
Tomsk, Tomsk, Russian Federation
Tomsk, Tomsk, Russian Federation
Tomsk, Tomsk, Russian Federation
The features of the metrics for assessing the quality of the work of the classifier for recognizing small-sized objects on the radar image are considered, they are compared and the most universal and informative ones are identified.
recognition of small objects on a radar image, metrics
1. V. I. Weber, V. Y. Kuprits, A. A. Mescheryakov, and M. V. Kuprits, “Recognition of ground objects on a radar image using convolutional neural network,” Ural Radio Engineering Journal, vol. 6(1), pp. 93-101, 2022, doi:https://doi.org/10.15826/urej.2022.6.1.005. (In Russ.).
2. P. V. Dudchenko, “Metrics for evaluating classifiers in the problems of medical diagnostics,” Youth and modern information technologies: Proceedings of the XVI International scientific and practical conference of students, graduate students and young scientists, Tomsk, December 3-7, 2018. Tomsk: TPU publishing house, [pp. 164-165], 2019. (In Russ.).
3. S. Yu. Gus’kov and V. V. Lyovin, “Confidence interval estimation for quality factors of binary classifiers - ROC curves, AUC for small samples,” Engineering Journal: Science and Innovation, no. 3 (39), p. 3, 2015, URL: http://engjournal.ru/catalog/mesc/idme/1376.html. (In Russ.).
