Large-scale document image retrieval and classification with runlength histograms and binary embeddings

We present a new document image descriptor based on multi-scale runlength histograms. This descriptor does not rely on layout analysis and can be computed efficiently. We show how this descriptor can achieve state-of-the-art results on two very different public datasets in classification and retrieval tasks. Moreover, we show how we can compress and binarize these descriptors to make them suitable for large-scale applications. We can achieve state-of-the-art results in classification using binary descriptors of as few as 16–64 bits.