Fingerprints classification using artificial neural networks: a combined structural and statistical approach

Nagaty, Khaled Ahmed

doi:10.1016/s0893-6080(01)00086-7

Cited by 55 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EDM is computed between the energy vector E new M of the unknown fingerprint and the energy vector E j M of the template image j while EDD is computed between the energy vector E new D of the unknown fingerprint and E j D of the template image j. Then the Euclidean distance measures are given by the following formulae [3]:…”

Section: Adaptive Matchingmentioning

confidence: 99%

“…In the identification mode, AFIS recognizes an individual without a claimed identity. Its criminal applications include verifying the alleged identity of suspects, identifying known criminals, persons considered as potential criminals and detained suspects [3]. The manual matching of fingerprints is a very tedious task because of the size of the image database, which can vary from a few hundred to several million records.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An adaptive hybrid energy-based fingerprint matching technique

Nagaty

2005

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Section: Adaptive Matchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An adaptive hybrid energy-based fingerprint matching technique

Nagaty

2005

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

“…This reduction is usually quan- 81 tified with the ratio of penetration [99] in the database, which 82 measures the percentage of the database that is searched before 83 matching the fingerprint. Classification is the most extended 84 method to reduce the ratio of penetration, which is also directly 85 related with the classification accuracy (percentage of correctly 86 classified examples) obtained by the classification methods. This 87 paper focuses on this type of methods to reduce the search space 88 even though other techniques have also been developed such as 89 indexing [6,64,14], continuous classification [15,17,19] or cluster- 90 ing and classification [47,68,69].…”

mentioning

confidence: 99%

“…12 method, which can be found in Table 1. approach, Nagaty [86] considered to process these strings further, 638 transforming them into binary codified ones. Even two of them have also carried out the alignment with the ori-689 entation of the reference point [4,63].…”

mentioning

confidence: 99%

A survey of fingerprint classification Part I: Taxonomies on feature extraction methods and learning models

Galar

Derrac²,

Peralta

et al. 2015

Knowledge-Based Systems

View full text Add to dashboard Cite

Orientation map 35 Singular points 36 3 7 a b s t r a c t 38 This paper reviews the fingerprint classification literature looking at the problem from a double perspec-39 tive. We first deal with feature extraction methods, including the different models considered for singular 40 point detection and for orientation map extraction. Then, we focus on the different learning models con-41 sidered to build the classifiers used to label new fingerprints. Taxonomies and classifications for the fea-42 ture extraction, singular point detection, orientation extraction and learning methods are presented. A 43 critical view of the existing literature have led us to present a discussion on the existing methods and 44 their drawbacks such as difficulty in their reimplementation, lack of details or major differences in their 45 evaluations procedures. On this account, an experimental analysis of the most relevant methods is car-46 ried out in the second part of this paper, and a new method based on their combination is presented.47

show abstract

“…where ( These detected spurious directions within ( ) p O I will be corrected one-by-one by analyzing the statistical number pattern of neighbor directions [9][10]. In this paper, the spurious direction is restored to the center of the range of the class that appears most frequently in the 3 3 × neighborhood structure.…”

mentioning

confidence: 99%

Fingerprint Orientation Field Estimation: Model of Primary Ridge for Global Structure and Model of Secondary Ridge for Correction

Liu

et al. 2010

Computer Vision – ACCV 2009

View full text Add to dashboard Cite

Abstract. Although many algorithms have been proposed for orientation field estimation, the results are not so satisfactory and the computational cost is expensive. In this paper, a novel algorithm based on straight-line model of ridge is proposed for the orientation field estimation. The algorithm comprises four steps, preprocessing original fingerprint image, determining the primary and secondary ridges of fingerprint foreground block using the top semi-neighbor searching algorithm, estimating block direction based on straight-line model of such a primary ridge and correcting the spurious block directions. Experimental results show that it achieves satisfying estimation accuracy with low computational time expense.

show abstract

Fingerprints classification using artificial neural networks: a combined structural and statistical approach

Cited by 55 publications

References 16 publications

An adaptive hybrid energy-based fingerprint matching technique

An adaptive hybrid energy-based fingerprint matching technique

A survey of fingerprint classification Part I: Taxonomies on feature extraction methods and learning models

Fingerprint Orientation Field Estimation: Model of Primary Ridge for Global Structure and Model of Secondary Ridge for Correction

Contact Info

Product

Resources

About