Fast Discriminative Visual Codebooks using Randomized Clustering Forests

Some of the most effective recent methods for content-based image classification work by extracting dense or sparse local image descriptors, quantizing them according to a coding rule such as k-means vector quantization, accumulating histograms of the resulting "visual word" codes over the image, and classifying these with a conventional classifier such as an SVM. Large numbers of descriptors and large codebooks are needed for good results and this becomes slow using k-means. We introduce Extremely Randomized Clustering Forests ensembles of randomly created clustering trees and show that these provide more accurate results, much faster training and testing and good resistance to background clutter in several state-of-the-art image classification tasks.