Multi-View Learning for Material Classification.

J Imaging

Univ Lyon, UJM-Saint-Etienne, CNRS, Institut Optique Graduate School, Laboratoire Hubert Curien UMR 5516, F-42023 Saint-Etienne, France.

Published: July 2022

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.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9315517PMC
http://dx.doi.org/10.3390/jimaging8070186DOI Listing

Publication Analysis

Top Keywords

material classification
12
multi-view learning
8
acquisition conditions
8
material
7
learning material
4
classification
4
classification material
4
classification texture
4
texture classification
4
classification consists
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!