Identifying the same records across multiple Ukiyo-e image databases using textual data in different languages

Abstract

This paper proposes a novel method for identifying the same records across multiple databases in different languages. In order to identify the same records, we calculate the similarities between records by comparing the text values of metadata elements. The proposed method, i.e. finding the same records across multiple databases, will help users to know which organization has a certain record and its customized versions regardless of languages and differences in formats. Although the proposed approach was demonstrated on Japanese Ukiyo-e databases, it might be applicable to other disciplines for bridging the gaps between databases in different languages.