Fingerprint Classification by Directional Image Partitioning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons
International Journal of Computer Vision
Similarity Search in High Dimensions via Hashing
VLDB '99 Proceedings of the 25th International Conference on Very Large Data Bases
Fingerprint Indexing Based on Novel Features of Minutiae Triplets
IEEE Transactions on Pattern Analysis and Machine Intelligence
Handbook of Fingerprint Recognition
Handbook of Fingerprint Recognition
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
An efficient parts-based near-duplicate and sub-image retrieval system
Proceedings of the 12th annual ACM international conference on Multimedia
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pores and Ridges: High-Resolution Fingerprint Matching Using Level 3 Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient fingerprint search based on database clustering
Pattern Recognition
Pruning SIFT for scalable near-duplicate image matching
ADC '07 Proceedings of the eighteenth conference on Australasian database - Volume 63
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
Fingerprint indexing with bad quality areas
Expert Systems with Applications: An International Journal
Indexing and retrieving in fingerprint databases under structural distortions
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
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.