Extracting semantic meaning from photographic annotations using a hybrid approach

This paper evaluates singular then hybrid methodologies for extracting semantics relevant to users in cataloguing and searching of personal photographs. It concentrates upon extraction of meaningful concepts within textual annotations focusing around geographical identification, together with references to people and objects concerning each image. A number of approaches are considered; machine learning, rule based and a novel hybrid approach encompassing previous techniques. This evaluation identifies the strengths of the singular approaches and defines rules best suited to differing extractions providing a higher performing hybrid method.