Describing Textures in the Wild

Patterns and textures are key characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can be scaly. Aiming at supporting this dimension in image understanding, we address the problem of describing textures with semantic attri...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2014 IEEE Conference on Computer Vision and Pattern Recognition s. 3606 - 3613
Hlavní autoři: Cimpoi, Mircea, Maji, Subhransu, Kokkinos, Iasonas, Mohamed, Sammy, Vedaldi, Andrea
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.06.2014
Témata:
Activation
attribute
Computer vision
convolutional neural network
Fisher Vector
Image color analysis
Internet
material
Materials
Object recognition
Pattern recognition
recognition
Semantics
Surface layer
Texture
Texture recognition
Vectors
Visualization
Vocabulary
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Patterns and textures are key characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can be scaly. Aiming at supporting this dimension in image understanding, we address the problem of describing textures with semantic attributes. We identify a vocabulary of forty-seven texture terms and use them to describe a large dataset of patterns collected "in the wild". The resulting Describable Textures Dataset (DTD) is a basis to seek the best representation for recognizing describable texture attributes in images. We port from object recognition to texture recognition the Improved Fisher Vector (IFV) and Deep Convolutional-network Activation Features (DeCAF), and show that surprisingly, they both outperform specialized texture descriptors not only on our problem, but also in established material recognition datasets. We also show that our describable attributes are excellent texture descriptors, transferring between datasets and tasks, in particular, combined with IFV and DeCAF, they significantly outperform the state-of-the-art by more than 10% on both FMD and KTH-TIPS-2b benchmarks. We also demonstrate that they produce intuitive descriptions of materials and Internet images.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2014.461