TEX-Nets: Binary patterns encoded convolutional neural networks for texture recognition

Rao Muhammad Anwer, Fahad Shahbaz Khan, Joost van de Weijer, Jorma Laaksonen

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

6 Sitaatiot (Scopus)

Abstrakti

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.

AlkuperäiskieliEnglanti
OtsikkoICMR 2017 - Proceedings of the 2017 ACM International Conference on Multimedia Retrieval
KustantajaACM
Sivut125-132
Sivumäärä8
ISBN (elektroninen)9781450347013
DOI - pysyväislinkit
TilaJulkaistu - 6 kesäkuuta 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaACM International Conference on Multimedia Retrieval - Bucharest, Romania
Kesto: 6 kesäkuuta 20179 kesäkuuta 2017
Konferenssinumero: 17

Conference

ConferenceACM International Conference on Multimedia Retrieval
LyhennettäICMR
MaaRomania
KaupunkiBucharest
Ajanjakso06/06/201709/06/2017

Sormenjälki Sukella tutkimusaiheisiin 'TEX-Nets: Binary patterns encoded convolutional neural networks for texture recognition'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Laitteet

    Science-IT

    Mikko Hakala (Manager)

    Perustieteiden korkeakoulu

    Laitteistot/tilat: Facility

  • Siteeraa tätä

    Anwer, R. M., Khan, F. S., van de Weijer, J., & Laaksonen, J. (2017). TEX-Nets: Binary patterns encoded convolutional neural networks for texture recognition. teoksessa ICMR 2017 - Proceedings of the 2017 ACM International Conference on Multimedia Retrieval (Sivut 125-132). ACM. https://doi.org/10.1145/3078971.3079001