VIR (Visual Information Retrieval) is a library for content based image retrieval and classification based on global and local features. The library allows comparing images considering their global and/or local features. It includes local features matching, RANSAC, MPEG-7 global features comparisons, kNN classification, Bag-of-Words (or Bag-of-Features) approach. It is an ongoing project.
The Story Map Building and Visualising Tool (SMBVT) is a semi-automatic tool to construct and visualise narratives, intended as semantic networks of events related to each other through semantic relations. This tool obeys an ontology for narratives we developed. SMBVT uses Wikidata as a reference knowledge base for importing entities, and Wikimedia Commons as an external source of images. The user of SMBVT can build each event of the narrative and attach to them the participating entities from Wikidata. The knowledge collected by the tool is exported as Linked Open Data, and is automatically saved as an OWL (Web Ontology Language) graph in a Fuseki triple store. The tool allows visualising the collected knowledge in simple formats like story maps, timelines, and network graphs. Furthermore, an automatic search functionality allows event exploration and inter-story correlation analyses.
The tool is open source at: https://github.com/EmanueleLenzi92/SMBVT