Class-specific material categorisation

By Barbara Caputo, Eric Hayman, P. Mallikarjuna. 2005

343 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Describing Textures in the Wild (2013, methodology): “Surpris-ingly, these descriptors outperform specialized state-of-the-art texture representations not only in recognizing our de-scribable attributes, but also in a variety of datasets for material recognition, achieving an accuracy of 63.3% on FMD and 67.5% on KTH-TIPS2-b dataset (Sect.”
Material recognition in the wild with the Materials in Context Database (2014, background): “Later, databases with more diverse examples from each material category began to appear, such as KTH-TIPS [10] and KTH-TIPS2 [2], and led explorations of how to generalize from one example of a material to another—from one sample of wood to a completely different sample, for instance.”
Bilinear CNN Models for Fine-Grained Visual Recognition (2015, methodology): “We experiment on three texture datasets – the Describable Texture Dataset (DTD) [8], Flickr Material Dataset (FMD) [49], and KTH-TISP2-b (KTH-T2b) [4].”
Bilinear CNNs for Fine-grained Visual Recognition (2015, methodology): “We experiment on three texture datasets – the Describable Texture Dataset (DTD) [10], Flickr Material Dataset (FMD) [56], and KTH-TISP2-b (KTH-T2b) [7].”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, background): “CUReT (Dana et al. 1999) (5612 images, 61 classes), UIUC (Lazebnik et al. 2005) (1000 images, 25 classes), KTH-TIPS (Burghouts and Geusebroek 2009) (810 images, 10 classes) are collected in controlled conditions, by photographing the same instance of a material, under varying scale, viewing angle an”
Learning LBP structure by maximizing the conditional mutual information (2015, methodology): “Texture Classification on the KTH-TIPS-2a Dataset We now compare the proposed approach with others on the KTH-TIPS-2a dataset [52] for texture classification using basic experimental settings.”
Bregman Divergences for Infinite Dimensional Covariance Matrices (2014, methodology): “Our Figure 2: Samples from the KTH-TIPS2b material dataset [4].”
Local Higher-Order Statistics (LHS) for Texture Categorization and Facial Analysis (2012, methodology): “KTH TIPS 2a Dataset(2) [14] is a dataset for material categorization.”
An Efficient Algorithm for Fractal Analysis of Textures (2012, methodology): “The two remaining datasets, KTH-TIPS [6] and Textured Surfaces [7] are publicly available and widely employed to evaluate texture analysis methods [8], [9], [10].”
Deep Structure-Revealed Network for Texture Recognition (2020, methodology): “To get a com pact global representation, some studies such as BoWs [4], VLAD [ 1 0], and FV [ 19] are presented to encode and aggre gate local features.”
Deep filter banks for texture recognition and segmentation (2015, background): “Perhaps the most studied task in texture understanding is the one of material recognition, as captured in benchmarks such as CuRET [8], KTH-TIPS [5], and, more recently, FMD [38].”
Visualizing and Understanding Deep Texture Representations (2015, methodology): “Using the Flickr Material Dataset (FMD) [34], Describable Texture Dataset (DTD) [3] and KTH-T2b [1] we show that it performs favorably to Fisher vector CNN model [4], which is the current state of the art.”
Rotation Invariant Image Description with Local Binary Pattern Histogram Fourier Features (2009, methodology): “This test setup resembles the most difficult setup used in [8].”
Log-Hilbert-Schmidt metric between positive definite operators on Hilbert spaces (2014, methodology): “Material classification: For this task, we used the KTH-TIPS2b dataset [6], which contains images of 11 materials captured under 4 different illuminations, in 3 poses, and at 9 scales.”
Local binary features for texture classification: Taxonomy and experimental study (2017, methodology): “For KTHTIPS2b, we follow the training and testing scheme of [125]: training on three samples”
Recognizing Materials Using Perceptually Inspired Features (2013, background): “Their SVM-based recognition system is equally successful for a variety of image features ( ∼ 90 % accuracy), and their KTH-TIPS2 database, unlike CURET, contains multiple examples in each 3-”