Describing Textures in the Wild
This work addresses the challenge of texture recognition for computer vision applications, providing a dataset and method that enhance performance in material recognition tasks.
The paper tackled the problem of describing textures in images using semantic attributes, resulting in the creation of the Describable Textures Dataset (DTD) and showing that the Improved Fisher Vector (IFV) outperforms specialized texture descriptors, achieving over 8% improvement on benchmarks like FMD and KTHTIPS-2b.
Patterns and textures are defining 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 analytical dimension in image understanding, we address the challenging problem of describing textures with semantic attributes. We identify a rich 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 the basis to seek for the best texture representation for recognizing describable texture attributes in images. We port from object recognition to texture recognition the Improved Fisher Vector (IFV) and show that, surprisingly, it outperforms specialized texture descriptors not only on our problem, but also in established material recognition datasets. We also show that the describable attributes are excellent texture descriptors, transferring between datasets and tasks; in particular, combined with IFV, they significantly outperform the state-of-the-art by more than 8 percent on both FMD and KTHTIPS-2b benchmarks. We also demonstrate that they produce intuitive descriptions of materials and Internet images.