| Title |
Giliuoju mokymu grindžiamas paviršių defektų aptikimo tyrimas / |
| Translation of Title |
Study of deep learning based detection of surface defects. |
| Authors |
Mikalauskienė, Edita |
| Full Text |
|
| Pages |
76 |
| Keywords [eng] |
defect ; neural network ; defection method |
| Abstract [eng] |
The aim of the research is to investigate the methods of defect detection that would more accurately and more quickly detect a defect on different surfaces. In order to achieve the set goal, the artificially formed DAGM database of different surfaces, different neural networks and defect detection studies performed by other scientists were examined. In the examined studies, defect detections are performed from the DAGM database but the detection is performed for each image class separately. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2020 |
