Thesis (Selection of subject)Thesis (Selection of subject)(version: 368)
Thesis details
   Login via CAS
Zpracování obrazu pro detekci trhlin v betonu
Thesis title in Czech: Zpracování obrazu pro detekci trhlin v betonu
Thesis title in English: Image processing for concrete cracks analysis
Key words: detekce trhlin|zpracování obrazu|analýza betonu|deep learning
English key words: crack detection|image processing|concrete analysis|deep learning
Academic year of topic announcement: 2023/2024
Thesis type: Bachelor's thesis
Thesis language:
Department: Department of Software and Computer Science Education (32-KSVI)
Supervisor: RNDr. Jan Blažek, Ph.D.
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 01.11.2023
Date of assignment: 22.02.2024
Confirmed by Study dept. on: 23.02.2024
Guidelines
The goal of this thesis is research and implementation of image processing algorithms useful for analysis of concrete cracks. Analyzed samples are digitalized in form of video sequence where concrete grained sample rotates 360° with fixed camera and light. Dataset contains video pairs with concrete samples before and after aging. The target of this thesis is construction of a digital image processing pipeline leading to
⁃ detection of structural changes in samples
⁃ visualization for expert based evaluation
⁃ quantification of changes and comparison of samples in dataset
Thesis will focus on data normalization, registration and visualization. And in second part on image segmentation and metric development.
Because of the real dataset and steps dependencies, the last step, quantification and comparison, is not crucial for evaluation in case of data quality issues.
References
U-Net: Convolutional Networks for Biomedical Image Segmentation, Olaf Ronneberger, Philipp Fischer, Thomas Brox, Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, LNCS, Vol.9351: 234--241, 2015, available at arXiv:1505.04597

Goodfellow, Ian, Bengio, Yoshua and Courville, Aaron. Deep Learning. : MIT Press, 2016.

Rafael C. Gonzalez and Richard E. Woods. 2006. Digital Image Processing (3rd Edition). Prentice-Hall, Inc., USA.
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html