Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.10353 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908318451105792 |
|---|---|
| author | Giordani, Jeremiah |
| author_facet | Giordani, Jeremiah |
| contents | Autonomous fabrication systems are transforming construction and manufacturing, yet they remain vulnerable to print errors. Texture classification is a key component of computer vision systems that enable real-time monitoring and adjustment during cementitious fabrication. Traditional classification methods often rely on global image features, which can bias the model toward semantic content rather than low-level textures. In this paper, we introduce a novel preprocessing technique called "patch and shuffle," which segments input images into smaller patches, shuffles them, and reconstructs a jumbled image before classification. This transformation removes semantic context, forcing the classifier to rely on local texture features.
We evaluate this approach on a dataset of extruded cement images, using a ResNet-18-based architecture. Our experiments compare the patch and shuffle method to a standard pipeline, holding all other factors constant. Results show a significant improvement in accuracy: the patch and shuffle model achieved 90.64% test accuracy versus 72.46% for the baseline. These findings suggest that disrupting global structure enhances performance in texture-based classification tasks.
This method has implications for broader vision tasks where low-level features matter more than high-level semantics. The technique may improve classification in applications ranging from fabrication monitoring to medical imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10353 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Patch and Shuffle: A Preprocessing Technique for Texture Classification in Autonomous Cementitious Fabrication Giordani, Jeremiah Computer Vision and Pattern Recognition Autonomous fabrication systems are transforming construction and manufacturing, yet they remain vulnerable to print errors. Texture classification is a key component of computer vision systems that enable real-time monitoring and adjustment during cementitious fabrication. Traditional classification methods often rely on global image features, which can bias the model toward semantic content rather than low-level textures. In this paper, we introduce a novel preprocessing technique called "patch and shuffle," which segments input images into smaller patches, shuffles them, and reconstructs a jumbled image before classification. This transformation removes semantic context, forcing the classifier to rely on local texture features. We evaluate this approach on a dataset of extruded cement images, using a ResNet-18-based architecture. Our experiments compare the patch and shuffle method to a standard pipeline, holding all other factors constant. Results show a significant improvement in accuracy: the patch and shuffle model achieved 90.64% test accuracy versus 72.46% for the baseline. These findings suggest that disrupting global structure enhances performance in texture-based classification tasks. This method has implications for broader vision tasks where low-level features matter more than high-level semantics. The technique may improve classification in applications ranging from fabrication monitoring to medical imaging. |
| title | Patch and Shuffle: A Preprocessing Technique for Texture Classification in Autonomous Cementitious Fabrication |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10353 |