Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.10496 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909291596742656 |
|---|---|
| author | Lu, Yu Chen, YuYu Zhou, Gang Lan, Zhenghua |
| author_facet | Lu, Yu Chen, YuYu Zhou, Gang Lan, Zhenghua |
| contents | Textile pilling assessment is critical for textile quality control. We collect thousands of 3D point cloud images in the actual test environment of textiles and organize and label them as TextileNet8 dataset. To the best of our knowledge, it is the first publicly available eight-categories 3D point cloud dataset in the field of textile pilling assessment. Based on PointGPT, the GPT-like big model of point cloud analysis, we incorporate the global features of the input point cloud extracted from the non-parametric network into it, thus proposing the PointGPT+NN model. Using TextileNet8 as a benchmark, the experimental results show that the proposed PointGPT+NN model achieves an overall accuracy (OA) of 91.8% and a mean per-class accuracy (mAcc) of 92.2%. Test results on other publicly available datasets also validate the competitive performance of the proposed PointGPT+NN model. The proposed TextileNet8 dataset will be publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10496 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPT-based Textile Pilling Classification Using 3D Point Cloud Data Lu, Yu Chen, YuYu Zhou, Gang Lan, Zhenghua Computer Vision and Pattern Recognition Textile pilling assessment is critical for textile quality control. We collect thousands of 3D point cloud images in the actual test environment of textiles and organize and label them as TextileNet8 dataset. To the best of our knowledge, it is the first publicly available eight-categories 3D point cloud dataset in the field of textile pilling assessment. Based on PointGPT, the GPT-like big model of point cloud analysis, we incorporate the global features of the input point cloud extracted from the non-parametric network into it, thus proposing the PointGPT+NN model. Using TextileNet8 as a benchmark, the experimental results show that the proposed PointGPT+NN model achieves an overall accuracy (OA) of 91.8% and a mean per-class accuracy (mAcc) of 92.2%. Test results on other publicly available datasets also validate the competitive performance of the proposed PointGPT+NN model. The proposed TextileNet8 dataset will be publicly available. |
| title | GPT-based Textile Pilling Classification Using 3D Point Cloud Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.10496 |