UAIC’s participation at Wikipedia Retrieval @

Abstract. This paper describes the participation of UAIC team at the ImageCLEF 2011 competition, Wikipedia Retrieval task. The aim of the task was to investigate retrieval approaches in the context of a large and heterogeneous collection of images and their noisy text annotations. We submitted a total of six runs, focusing our effort along the textual retrieval, query expansion on English language, combined with feature extraction (Color and Edge Directionality Descriptor, CEDD). Our intention was to build a CBIR (Content-based image retrieval) system that relies on a fast indexing and retrieval practice based not only on the textual multilingual metadata, but also on the images features. The results were satisfying in the multilingual mixed search (text and images) and query expansion approach