Machine learning based image analysis for surface defect inspection
The progress in computer vision technology has significantly improved the reliability, effectiveness, and efficiency of defect detection. This is attributed to the availability of advanced optical illumination systems and appropriate image capturing devices that produce high-quality images. Addition...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/165900 |
| _version_ | 1811692698022707200 |
|---|---|
| author | Lee, Yong Xian |
| author2 | Zheng Jianmin |
| author_facet | Zheng Jianmin Lee, Yong Xian |
| author_sort | Lee, Yong Xian |
| collection | NTU |
| description | The progress in computer vision technology has significantly improved the reliability, effectiveness, and efficiency of defect detection. This is attributed to the availability of advanced optical illumination systems and appropriate image capturing devices that produce high-quality images. Additionally, deep learning, which is a crucial technology in visual inspection, has contributed to this progress. An approach called DifferNet [6] has been introduced, which estimates the density of feature descriptors extracted by a convolutional neural network (CNN) using normalizing flows. Although normalizing flow struggles with images that have high dimensionality, its key purpose is to handle data distributions with low dimensions. To overcome this challenge, a multiscale extractor can be employed, enabling normalizing flow to assign meaningful likelihoods that can identify defects through a scoring function. In this report, the objective is to explore how various pre-trained CNN models can help improve the features extracted for normalizing flows to be optimized further. To achieve that, different transfer learning models such as ResNet-50 [16], VGG16 [14], and EfficientNetV2 [28] trained on the ImageNet dataset [7] will replace AlexNet in the original paper. This report also explores the idea of utilizing the lower hierarchy of the pre-trained model to preserve localized nominal information loss mentioned in PatchCore [22]. |
| first_indexed | 2024-10-01T06:39:55Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/165900 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:39:55Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1659002023-04-21T15:36:51Z Machine learning based image analysis for surface defect inspection Lee, Yong Xian Zheng Jianmin School of Computer Science and Engineering ASJMZheng@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Pattern recognition The progress in computer vision technology has significantly improved the reliability, effectiveness, and efficiency of defect detection. This is attributed to the availability of advanced optical illumination systems and appropriate image capturing devices that produce high-quality images. Additionally, deep learning, which is a crucial technology in visual inspection, has contributed to this progress. An approach called DifferNet [6] has been introduced, which estimates the density of feature descriptors extracted by a convolutional neural network (CNN) using normalizing flows. Although normalizing flow struggles with images that have high dimensionality, its key purpose is to handle data distributions with low dimensions. To overcome this challenge, a multiscale extractor can be employed, enabling normalizing flow to assign meaningful likelihoods that can identify defects through a scoring function. In this report, the objective is to explore how various pre-trained CNN models can help improve the features extracted for normalizing flows to be optimized further. To achieve that, different transfer learning models such as ResNet-50 [16], VGG16 [14], and EfficientNetV2 [28] trained on the ImageNet dataset [7] will replace AlexNet in the original paper. This report also explores the idea of utilizing the lower hierarchy of the pre-trained model to preserve localized nominal information loss mentioned in PatchCore [22]. Bachelor of Engineering (Computer Science) 2023-04-16T08:57:23Z 2023-04-16T08:57:23Z 2023 Final Year Project (FYP) Lee, Y. X. (2023). Machine learning based image analysis for surface defect inspection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165900 https://hdl.handle.net/10356/165900 en SCSE22-0055 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Lee, Yong Xian Machine learning based image analysis for surface defect inspection |
| title | Machine learning based image analysis for surface defect inspection |
| title_full | Machine learning based image analysis for surface defect inspection |
| title_fullStr | Machine learning based image analysis for surface defect inspection |
| title_full_unstemmed | Machine learning based image analysis for surface defect inspection |
| title_short | Machine learning based image analysis for surface defect inspection |
| title_sort | machine learning based image analysis for surface defect inspection |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Pattern recognition |
| url | https://hdl.handle.net/10356/165900 |
| work_keys_str_mv | AT leeyongxian machinelearningbasedimageanalysisforsurfacedefectinspection |