Latent fingerprint indexing: Fusion of level 1 and level 2 features

Paulino, Alessandra A.; Liu, Eryun; Cao, Kai; Jain, Anil K.

doi:10.1109/btas.2013.6712748

Cited by 25 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore in proposed approach we fixed the penetration rate to 39 % and observed the hit ratio is 96.7 %. The comparison of our result with Yuan et.al [21] proposed approach and Paulino et al [22] is shown in fig.5. From the graph it is clear that we have reach a higher hit rate as compare to other algorithms.…”

Section: B Indexing Results-mentioning

confidence: 51%

See 1 more Smart Citation

Adaptive latent fingerprint indexing

Pandey

Singh

2014

2014 5th International Conference - Confluence the Next Generation Information Technology Summit (Confluence)

View full text Add to dashboard Cite

Based on biometric system, identification of individual is complex and very interesting task. In law and forensic applications, fingerprint plays an important role in person recognition. Earlier focus was on full fingerprint but today latent fingerprint matching which is poor in quality, having non-linear distortion and small overlapping area is still a challenge for researchers. Latent prints contains noise in it, therefore to deal with latent matching having larger database, indexing techniques are required. Using indexing technique, matching process is speeded up because it places most possible match at the top from large database therefore reduces the time required for matching. In this paper, we have proposed an efficient latent indexing technique that reduces manual intervention and maintain latent matching accuracy. In this technique we have used manually extracted features as well as automatically extracted features and applied three approaches i.e. MCC, triplets, hybrid orientation field on both manually marked and derived minutiae and orientation field for indexing. We have carried out our implementation on NIST SD27 Database, to determine the performance of proposed approach by using large background database of approximately 200K of fingerprints. The results of this proposed algorithm has 96.7% hit rate at penetration rate of 39%, which is better than Paulino et al. and the latent matching accuracy was also maintained.

show abstract

Section: B Indexing Results-mentioning

confidence: 51%

“…Paulino et al [22]: In their proposed work they have used the fusion of level-1 and level-2 features to improve indexing performance. In their approach firstly, they have performed the encoding of orientation field.…”

Section: Related Workmentioning

confidence: 99%

Adaptive latent fingerprint indexing

Pandey

Singh

2014

2014 5th International Conference - Confluence the Next Generation Information Technology Summit (Confluence)

View full text Add to dashboard Cite

show abstract

“…Experiments on NIST SD 27 against a large background database of 240,258 rolled prints achieved a hit rate of 92.7 % at a penetration rate of 40 % (80.7 % at 10 % penetration rate). Alessandra et al indexed latent fingerprints by fusion of levels 1 and 2 features. This method combines the scores on a constrained version of triplet indexing, Minutia Cylinder Code (MCC) indexing, a new OF descriptor indexing technique that uses a hash function, filtering based on singular points, and averaged ridge period comparison.…”

Section: Related Workmentioning

confidence: 99%

“…A number of fingerprint indexing schemes based on all levels of features have been proposed for both full fingerprint and partial fingerprint indexing since 1997. However, the indexing techniques for full fingerprint are not applicable to partial fingerprint identification because the missing parts of a partial fingerprint are simply ignored (considered void).…”

Section: Introductionmentioning

confidence: 99%

Partial fingerprint indexing: a combination of local and reconstructed global features

Zhou

Wang

et al. 2015

Concurrency and Computation

View full text Add to dashboard Cite

Existing work on partial fingerprint indexing attempts to make full use of the extracted features from the partial segments, such as singular points, minutiae, orientation field, and ridge count. However, singular points may not exist in partial fingerprints, and none of these features can form a complete set of feature vectors that can be used for matching with those derived from the corresponding full fingerprints for indexing. Our former work on fingerprint orientation model based on two-dimensional Fourier expansion (FOMFE) coefficients-based fingerprint indexing and global orientation field reconstruction has demonstrated the possibility of reconstructing a global feature vector for partial fingerprint indexing. In this paper, we design some novel features of minutiae triplets in addition to some commonly used features to constitute the local minutiae triplet features. Experiments carried out on fingerprint verification competition (FVC) 2000 DB2a, FVC 2002 DB1a, and National Institute of Standards and Technology (NIST) SD 14 demonstrate the performance improvement after adding the new features to minutiae triplet feature set. We then propose to combine the reconstructed global feature and local minutiae triplet features to improve the performance of partial fingerprint indexing. Specifically, the minutiae triplet-based indexing scheme and the FOMFE coefficients-based indexing scheme are applied separately to generate two candidate lists; then, a fuzzy-based fusion scheme is designed to generate the final candidate list for matching. Experiments carried out on the public database NIST SD 14 show that the proposed approach can improve the performance that has been achieved by individual partial fingerprint indexing algorithms before fusion. SPECIAL ISSUE ON SECURITY AND PRIVACY IN BIG DATA: SPBD2014 2941 investigating partial fingerprint indexing is very important, which is the focus of this paper. We emphasize on the indexing performance in terms of partialness aspect rather than other aspects such as noise removal or texture separation.To facilitate the description, storage, and exchange of fingerprint information, the American National Standards Institute/National Institute of Standards and Technology (NIST) standard committee has recommended to describe fingerprints by a complete fingerprint feature set in three incremental levels. Level 1 features the following: friction ridge flows, pattern type, and general morphological information. These features can describe the fingerprint in a global view, such as the orientation field (OF). Level 2 features individual friction ridge paths and associated events, including bifurcations or endings (namely, minutiae). Minutiae are local features and are generally stable and highly distinctive. Level 3 features are friction ridge dimensional attributes, such as width, edge shapes, and pores. Currently, some level 3 features, such as pores, are only detectable on high quality and high resolution fingerprint images, and they are not major features that are used in today...

show abstract

“…In [18] Paulino et al, have proposed an indexing approach, primarily for latent fingerprints, which combines multiple, level 1 and level 2 features to filter out a large portion of the background database while maintaining the accuracy of latent matching. Rolled fingerprints are achieved by rolling a finger from nail to nail to capture the complete ridge details of a finger, while plain or slap fingerprints are obtained by pressing a finger onto a flat surface without movement.…”

Section: Fingerprint Indexing Based On Global Featuresmentioning

confidence: 99%

Fingerprint Indexing Approaches for Biometric Database: A Review

Parmar¹,

Degadwala²

2015

IJCA

View full text Add to dashboard Cite

Due to the uniqueness and persistent properties of the biometric fingerprint characteristics, large scale in border control and governmental applications such as the Aadhaar project in India, the Visa Information System (VIS) in Europe and US-VISIT / IDENT system in the USA are based on fingerprint recognition and generally contain millions of fingerprint samples. The study of fingerprint indexing techniques is inevitable, to improve the effectiveness in searching for satisfactory candidate reference list in such large biometric databases. In systems using biometric identification, the identity associated with the input data is decided by its comparison against every single entry in the database. This matching process is exhaustive which leads to increase in the rate of erroneous identification and the response time of the system. This paper presents a survey on the fingerprint indexing methods that are currently available and some of them are presented. Fingerprint indexing is based on the local ridge line orientation, global feature, minutiae and other features.

show abstract

Latent fingerprint indexing: Fusion of level 1 and level 2 features

Cited by 25 publications

References 21 publications

Adaptive latent fingerprint indexing

Adaptive latent fingerprint indexing

Partial fingerprint indexing: a combination of local and reconstructed global features

Fingerprint Indexing Approaches for Biometric Database: A Review

Contact Info

Product

Resources

About