Metadata Augmentation for Semantic- and Context- Based Retrieval of Digital Cultural Objects

Cultural objects are increasingly stored and generated in digital form, yet effective methods for their indexing and retrieval still remain an open area of research. The main problem arises from the disconnection between the content-based indexing approach used by computer scientists and the description-based approach used by information scientists. There is also a lack of representational schemes that allow the alignment of the semantics and context with keywords and low-level features that can be automatically extracted from the content of these cultural objects. This paper presents an integrated approach to address these problems, taking advantage of both computer science and information science approaches. The focus is on the rationale and conceptual design of the system and its various components. In particular, we discuss techniques for augmenting commonly used metadata with visual features and domain knowledge to generate high-level abstract metadata which in turn can be used for semantic and context-based indexing and retrieval. We use a sample collection of Vietnamese traditional woodcuts to demonstrate the usefulness of this approach.