Deep learning for x-ray vision
Recent discussions have surfaced that the location of a crack in additive material begins from a pore. The resulting stress on the pore initiates a crack growing towards the next nearest pore, which eventually leads to a point of failure. The objective of the study is to evaluate the feasibility of...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/147951 |
| _version_ | 1811693764693983232 |
|---|---|
| author | Ng, Kenneth Chen Ee |
| author2 | Qian Kemao |
| author_facet | Qian Kemao Ng, Kenneth Chen Ee |
| author_sort | Ng, Kenneth Chen Ee |
| collection | NTU |
| description | Recent discussions have surfaced that the location of a crack in additive material begins from a pore. The resulting stress on the pore initiates a crack growing towards the next nearest pore, which eventually leads to a point of failure. The objective of the study is to evaluate the feasibility of using simulated X-ray CT scans as a possible addition to real images for training data in detection of pores in CT images. A 3D model consisting of realistic pore-like structures were created in TinkerCAD and uploaded to aRTist where the simulated CT scan was performed to yield simulated CT images. The images were then pre-processed using VGStudio MAX and ImageJ software. Using the trainable weka segmentation plugin, each image was labelled semi-automatically. The images were then manually corrected and transformed into mask images for training. Different segmentation models such as U-net and DeepLabV3 were then explored to perform the segmentation task. Comparing the results using the probability of detection score, we arrive on the conclusion that detection of pores heavily relies on real data as opposed to simulated data. |
| first_indexed | 2024-10-01T06:56:52Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/147951 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:56:52Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1479512021-05-18T11:41:15Z Deep learning for x-ray vision Ng, Kenneth Chen Ee Qian Kemao School of Computer Science and Engineering Advanced Remanufacturing and Technology Centre - A* STAR MKMQian@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Recent discussions have surfaced that the location of a crack in additive material begins from a pore. The resulting stress on the pore initiates a crack growing towards the next nearest pore, which eventually leads to a point of failure. The objective of the study is to evaluate the feasibility of using simulated X-ray CT scans as a possible addition to real images for training data in detection of pores in CT images. A 3D model consisting of realistic pore-like structures were created in TinkerCAD and uploaded to aRTist where the simulated CT scan was performed to yield simulated CT images. The images were then pre-processed using VGStudio MAX and ImageJ software. Using the trainable weka segmentation plugin, each image was labelled semi-automatically. The images were then manually corrected and transformed into mask images for training. Different segmentation models such as U-net and DeepLabV3 were then explored to perform the segmentation task. Comparing the results using the probability of detection score, we arrive on the conclusion that detection of pores heavily relies on real data as opposed to simulated data. Bachelor of Engineering (Computer Science) 2021-05-18T11:41:15Z 2021-05-18T11:41:15Z 2021 Final Year Project (FYP) Ng, K. C. E. (2021). Deep learning for x-ray vision. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/147951 https://hdl.handle.net/10356/147951 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Ng, Kenneth Chen Ee Deep learning for x-ray vision |
| title | Deep learning for x-ray vision |
| title_full | Deep learning for x-ray vision |
| title_fullStr | Deep learning for x-ray vision |
| title_full_unstemmed | Deep learning for x-ray vision |
| title_short | Deep learning for x-ray vision |
| title_sort | deep learning for x ray vision |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/147951 |
| work_keys_str_mv | AT ngkennethchenee deeplearningforxrayvision |