Indexing Fingerprint Databases Based on Multiple Features

In a fingerprint identification system, a person is identified only by his fingerprint. To accomplish this, a database is searched by matching all entries to the given fingerprint. However, the maximum size of the database is limited, since each match takes some amount of time and has a small probability of error. A solution to this problem is to reduce the number of fingerprints that have to be matched. This is achieved by extracting features from the fingerprints and first matching the fingerprints that have the smallest feature distance to the query fingerprint. Using this indexing method, modern systems are able to search databases up to a few hundred fingerprints. In this paper, three possible fingerprint indexing features are discussed: the registered directional field estimate, FingerCode and minutiae triplets. It is shown that indexing schemes that are based on these features, are able to search a database more effectively than a simple linear scan. Next, a new indexing scheme is constructed that is based on advanced methods of combining these features. It is shown that this scheme results in a considerably better performance than the schemes that are based on the individual features or on more naive methods of combining the features, thus allowing much larger fingerprint databases to be searched. Keywords—image processing, fingerprint image classification, database search, multiple classifiers.