Thesis Details
Identifikace znaků na hloubkovém snímku pneumatiky
This thesis deals with the problem of detection, recognition and segmentation of characters on the depth scan of tire. The approach applied in the thesis horizontally splits the input depth scan into overlapping parts, in which the symbols are detected by the deep neural network Mask R-CNN. The duplicate detections emerging due to the overlap are discarded by the subsequent use of non-maximum suppression. The modification of Mask R-CNN, which utilises parallel segmentation branch with the aim of improving the quality of segmentation of symbols with thin lines or complex mask, is also proposed in the thesis. Applying the proposed approach on the prepared dataset, the values 0.877 and 0.738 were obtained as the mean average precision metrics for detection and segmentation in the IoU interval from 0.5 to 0.95.
depth scan of tire, deep learning, Mask R-CNN, U-Net, image segmentation, identification of characters, instance segmentation, semantic segmentation, imbalanced dataset, parallel segmentation layer
Kočí Radek, Ing., Ph.D. (DITS FIT BUT), člen
Křivka Zbyněk, Ing., Ph.D. (DIFS FIT BUT), člen
Španěl Michal, doc. Ing., Ph.D. (DCGM FIT BUT), člen
@bachelorsthesis{FITBT25095,
author = "Pavol Va\v{n}o Toth",
type = "Bachelor's thesis",
title = "Identifikace znak\r{u} na hloubkov\'{e}m sn\'{i}mku pneumatiky",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2022,
location = "Brno, CZ",
language = "czech",
url = "https://www.fit.vut.cz/study/thesis/25095/"
}