Loading...
Please wait, while we are loading the content...
Similar Documents
Multi-View Learning for Material Classification
| Content Provider | MDPI |
|---|---|
| Author | Alain, Trémeau Sumon, Borhan Uddin Muselet, Damien Xu, Sixiang |
| Copyright Year | 2022 |
| Description | Material classification is similar to texture classification and consists in predicting the material class of a surface in a color image, such as wood, metal, water, wool, or ceramic. It is very challenging because of the intra-class variability. Indeed, the visual appearance of a material is very sensitive to the acquisition conditions such as viewpoint or lighting conditions. Recent studies show that deep convolutional neural networks (CNNs) clearly outperform hand-crafted features in this context but suffer from a lack of data for training the models. In this paper, we propose two contributions to cope with this problem. First, we provide a new material dataset with a large range of acquisition conditions so that CNNs trained on these data can provide features that can adapt to the diverse appearances of the material samples encountered in real-world. Second, we leverage recent advances in multi-view learning methods to propose an original architecture designed to extract and combine features from several views of a single sample. We show that such multi-view CNNs significantly improve the performance of the classical alternatives for material classification. |
| Starting Page | 186 |
| e-ISSN | 2313433X |
| DOI | 10.3390/jimaging8070186 |
| Journal | Journal of Imaging |
| Issue Number | 7 |
| Volume Number | 8 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-07-07 |
| Access Restriction | Open |
| Subject Keyword | Journal of Imaging Artificial Intelligence Material Classification Multi-view Learning Texture Analysis Visual Appearance Material Dataset |
| Content Type | Text |
| Resource Type | Article |
