Challenges in Content-Based Image Indexing of Cultural Heritage Collections: Support vector machine active learning with applications to text classification

Abstract

Cultural heritage collections are being digitized and made available through online tools. Due to the large volume of documents being digitized, not enough manpower is available to provide useful annotations. Is this article, we discuss the use of automatic tools to both automatically index the documents (i.e., provide labels) and search through the collections. We detail the challenges specific to these collections as well as research directions that must be followed to answer the questions raised by these new data.