Personal Identity Matching

摘要

Despite all existing methods to identify a person, such as fingerprint, iris, and facialrecognition, the personal name is still one of the most common ways to identify an individual. Inthis paper, we propose two novel algorithms: The first one uses sound techniques to create amulti-dimensional vector representation of names to compute a degree of similarity. Thisalgorithm compares names that are written in different languages (cross-language) andtransliterated names in English. The second algorithm builds on the first one and measures thesimilarities between full names, taking into account the full name structure. We evaluate thealgorithms for transliterated names and across languages using Arabic and English as anexample. Significant results are achieved by both algorithms compared with other existingalgorithms.