BRINT: Binary Rotation Invariant and Noise Tolerant Texture Classification

In this paper we propose a simple, efficient, yet robust multi-resolution approach to texture classification — Binary Rotation Invariant and Noise Tolerant (BRINT). The proposed approach is very fast to build, very compact while remaining robust to illumination variations, rotation changes and noise.
We develop a novel and simple strategy — averaging before binarization — to compute a local binary descriptor based on the conventional LBP approach, preserving the advantageous characteristics of uniform LBP. Points are sampled in a circular neighborhood, but keeping the number of bins in a single-scale LBP histogram constant and small, such that arbitrarily large circular neighborhoods can be sampled and compactly encoded over a number of scales. There is no need for a pre-training step at the feature extraction stage, no necessity to learn a texton dictionary, as in methods based on clustering, and no tuning of parameters is required to deal with different datasets. Extensive experimental results on several popular benchmark texture databases demonstrate that the proposed approach is very robust to noise and significantly outperforms the state-of-the-art in terms of classifying noise corrupted textures, while at the same time the proposed approach still improves the classification performance on the original texture databases, producing consistently good classification results, including what we believe to be the best reported results for CUReT and the three standard Outex test suites.