Abstract
Recognizing materials and textures in realistic imaging conditions is a challenging computer vision problem. For many years, local features based orderless representations were a dominant approach for texture recognition. Recently deep local features, extracted from the intermediate layers of a Convolutional Neural Network (CNN), are used as filter banks. These dense local descriptors from a deep model, when encoded with Fisher Vectors, have shown to provide excellent results for texture recognition. The CNN models, employed in such approaches, take RGB patches as input and train on a large amount of labeled images. We show that CNN models, which we call TEX-Nets, trained using mapped coded images with explicit texture information provide complementary information to the standard deep models trained on RGB patches. We further investigate two deep architectures, namely early and late fusion, to combine the texture and color information. Experiments on benchmark texture datasets clearly demonstrate that TEX-Nets provide complementary information to standard RGB deep network. Our approach provides a large gain of 4:8%, 3:5%, 2:6% and 4:1% respectively in accuracy on the DTD, KTH-TIPS-2a, KTH-TIPS-2b and Texture-10 datasets, compared to the standard RGB network of the same architecture. Further, our final combination leads to consistent improvements over the state-of-the-art on all four datasets.
Original language | English |
---|---|
Title of host publication | ICMR 2017 - Proceedings of the 2017 ACM International Conference on Multimedia Retrieval |
Publisher | ACM |
Pages | 125-132 |
Number of pages | 8 |
ISBN (Electronic) | 9781450347013 |
DOIs | |
Publication status | Published - 6 Jun 2017 |
MoE publication type | A4 Conference publication |
Event | ACM International Conference on Multimedia Retrieval - Bucharest, Romania Duration: 6 Jun 2017 → 9 Jun 2017 Conference number: 17 |
Conference
Conference | ACM International Conference on Multimedia Retrieval |
---|---|
Abbreviated title | ICMR |
Country/Territory | Romania |
City | Bucharest |
Period | 06/06/2017 → 09/06/2017 |
Keywords
- Convolutional Neural Networks
- Local binary patterns
- Texture recognition