Pattern-Based Retrieval of Cultural Heritage Images

Conventional Content-Based Image Retrieval (CBIR) systems make use of similarity measures estimated directly from low-level image features, involving multidimensional and exhaustive, nearest neighbor searching. In this paper we present an image retrieval methodology suited for efficient search in cultural heritage images that utilizes similarity measures defined over higher-level patterns associated with clusters of low-level image features. The similarity between two patterns is estimated as a function of the similarity between both the structure and the measure components of the patterns. We evaluate our system using cultural heritage images derived from the repository of the Foundation of Hellenic World (FHW). For the experiments we use Local Binary Pattern (LBP) and contrast distributions as image features and the results show that the proposed pattern-based approach efficiently retrieves images compared to commonly employed methods.