We propose a simple yet effective approach to content-based image retrieval: the signature matching distance. While recent approaches to content-based image retrieval utilize the bag-of-visual-words model, where image descriptors are matched through a common visual vocabulary, signature-based approaches use a distance between signatures, i.e. between image-specific bags of locally aggregated descriptors, in order to quantify image dissimilarity. In this paper, we focus on the signature-based approach to content-based image retrieval and propose a novel distance function, the signature matching distance. This distance matches coincident visual properties of images based on their signatures. In particular, by investigating different descriptor matching strategies and their suitability to match signatures, we show that our approach is able to outperform other signature-based approaches to content-based image retrieval. Moreover, in combination with a simple color and texture-based image descriptor, our approach is able to compete with the majority of bag-of-visual-words approaches.

Modeling image similarity for browsing and searching in voluminous image databases is a challenging task of nearly all content-based image retrieval systems. One promising way of defining image similarity consists in applying distance-based similarity measures on compact image representations. Beyond feature histograms and feature signatures, more general feature representations are mixture models of which the Gaussian mixture model is the most prominent one. This feature representation can be compared by employing approximations of the Kullback-Leibler Divergence. Although several of those approximations have been successfully applied to model image similarity, their applicability to mixture models based on high-dimensional feature descriptors is questionable. In this paper, we thus introduce the Signature Quadratic Form Distance to measure the distance between two Gaussian mixture models of high-dimensional feature descriptors. We show the analytical computation of the proposed Gaussian Quadratic Form Distance and evaluate its retrieval performance by making use of different benchmark image databases.

We introduce a new family of flexible feature representations for content-based multimedia retrieval: probabilistic feature signatures. While conventional feature histograms and feature signatures aggregate the multimedia objects' feature distributions exhibited in some feature space according to a partitioning, probabilistic feature signatures model these feature distributions by means of discrete or continuous probability distributions. In this way, they combine the advantages of high expressiveness and compactness, for instance through Gaussian mixture models. In this paper, we introduce the concept of probabilistic feature signatures and provide the empirical evidence of high retrieval performance when using this feature representation type. We show that probabilistic feature signatures are able to outperform conventional feature signatures.