Bochis, Horea Alexandru (2023) Improving AI-based crack detection on masonry structural surfaces. Bachelor's Thesis, Computing Science.
|
Text
Bachelor_s_Thesis_2023-10_horea_bochis.pdf Download (10MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (460kB) |
Abstract
The detection of cracks in different masonry surfaces, which represents the highest stock of buildings worldwide, is quite important since mostly this labour is done manually and it is quite expensive and subjective. The purpose of this research is to improve an existing crack detection model by using multiclass prediction with U-Net that has a MobileNetV2 encoder, which has been trained for a period of 50 epochs. U-Net is an architecture for semantic segmentation and MobileNetV2 is a computer vision model open-sourced by Google and designed for training classifiers. In this paper you shall get a detailed view of the whole process and how well it performed.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Karastoyanova, D. and Azzopardi, G. |
| Degree programme: | Computing Science |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 04 Sep 2023 11:47 |
| Last Modified: | 04 Sep 2023 11:47 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/31405 |
Actions (login required)
 |
View Item |