Toward Robust Material Recognition for Everyday Objects
   Diane Hu, Liefeng Bo, Xiaofeng Ren, at BMVC 2011


Material recognition is a fundamental problem in perception that is receiving in- creasing attention. Following the recent work using Flickr [16, 23], we empirically study material recognition of real-world objects using a rich set of local features. We use the Kernel Descriptor framework [5] and extend the set of descriptors to include material- motivated attributes using variances of gradient orientation and magnitude. Large-Margin Nearest Neighbor learning is used for a 30-fold dimension reduction. We improve the state-of-the-art accuracy on the Flickr dataset [16] from 45% to 54%. We also introduce two new datasets using ImageNet and macro photos, extensively evaluating our set of features and showing promising connections between material and object recognition.