Clustering-Based Descriptors for Fingerprint Indexing and Fast Retrieval

This paper addresses the problem of fast fingerprint retrieval in a large database using clustering-based descriptors. Most current fingerprint indexing frameworks utilize global textures and minutiae structures. To extend the existing methods for feature extraction, previous work focusing on SIFT features has yielded high performance. In our work, other local descriptors such as SURF and DAISY are studied and a comparison of performance is made. A clustering method is used to partition the descriptors into groups to speed up retrieval. PCA is used to reduce the dimensionality of the cluster prototypes before selecting the closest prototype to an input descriptor. In the index instruction phase, the locality-sensitive hashing (LSH) is implemented for each descriptor cluster to efficiently retrieve similarity queries in a small fraction of the cluster. Experiments on public fingerprint databases show that the performance suffers little while the speed of retrieval is improved much using clustering-based SURF descriptors.