A score-level fusion fingerprint indexing approach based on minutiae vicinity and minutia cylinder-code

Li, Guoqiang; Yang, Bian; Busch, Christoph

doi:10.1109/iwbf.2014.6914238

Cited by 13 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional minutiae descriptors can be divided into three categories: image based, texture based, and minutiae based descriptors. Image based [15,16] and texture based [17,18] descriptors use image intensity or ridge orientation information, while minutiae based descriptors [19][20][21][22][23][24] make use of the relationships between neighboring minutiae. These methods use manually designed features and thus are difficult to optimize to separate mated minutiae pairs from non-mated pairs, especially under challenging situations.…”

Section: B Descriptorsmentioning

confidence: 99%

Latent Fingerprint Registration via Matching Densely Sampled Points

Feng

et al. 2021

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Latent fingerprint matching is a very important but unsolved problem. As a key step of fingerprint matching, fingerprint registration has a great impact on the recognition performance. Existing latent fingerprint registration approaches are mainly based on establishing correspondences between minutiae, and hence will certainly fail when there are no sufficient number of extracted minutiae due to small fingerprint area or poor image quality. Minutiae extraction has become the bottleneck of latent fingerprint registration. In this paper, we propose a non-minutia latent fingerprint registration method which estimates the spatial transformation between a pair of fingerprints through a dense fingerprint patch alignment and matching procedure. Given a pair of fingerprints to match, we bypass the minutiae extraction step and take uniformly sampled points as key points. Then the proposed patch alignment and matching algorithm compares all pairs of sampling points and produces their similarities along with alignment parameters. Finally, a set of consistent correspondences are found by spectral clustering. Extensive experiments on NIST27 database and MOLF database show that the proposed method achieves the state-of-the-art registration performance, especially under challenging conditions.

show abstract

Section: B Descriptorsmentioning

confidence: 99%

Latent Fingerprint Registration via Matching Densely Sampled Points

Feng

et al. 2021

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…Fingerprint indexing is applied to reduce the search space and thus to reduce the search time in a large database. Lot of fingerprint indexing techniques have been proposed and applied by researchers to reduce the response time for improving the effectiveness of the identification system (Li et al, 2014;Iloanusi et al, 2011;Zhou et al, 2014;Mngenge et al, 2015). Another indexing method known as Minutiae Cylinder Code (MCC) uses a 3D data structure known as cylinder to speed up the fingerprint identification (Cappelli et al, 2010).…”

Section: Related Workmentioning

confidence: 99%

Enrolment and Matching of Fingerprints using Minutiae Tree

Praseetha¹,

Vadivel²

2019

Journal of Computer Science

View full text Add to dashboard Cite

Automated fingerprint matching is considered as the most challenging phase of fingerprint recognition since it can be affected by a variety of factors such as noise, skin condition, rotation, distortions and displacements. When there is a large database, the search time to get a matching fingerprint will be relatively high. To reduce the searching time in the database, we have proposed a minutiae tree based indexing method in this paper. The database is represented in the form of a minutiae tree and the fingerprint matching is done by visiting the nodes in the tree where the local configuration of the minutiae is stored. By using this tree structure it is found that the search time or matching time can be considerably reduced and the matching time is independent of the number of fingerprints enrolled in the database. Our framework is scalable and the experiments conducted explores its ability to find correct matches with minimal search time.

show abstract

“…However, their worst case searching is almost similar to linear search due to their unbalanced structure. Thus, several clustering approaches were proposed to enhance the efficiency of the storage systems, amongst which kmeans clustering is most popular [13][14][15]. However, in such clustering, the speed and accuracy of a system are highly dependent on the number of clusters and as a result, clustering is barely effective for identification purpose with a high volume of data.…”

Section: Introductionmentioning

confidence: 99%