Wyniki wyszukiwania - BazTech

1

Application of scale-invariant feature transform to fingerprint classification

Sobek J., Cetnarowicz D., Dąbrowski A.

Elektronika : konstrukcje, technologie, zastosowania

|

2012

|

Vol. 53, nr 5

40-45

EN

In this paper an application of SIFT (Scale-Invariant Feature Transform) is presented. Even though the SIFT is a computer vision algorithm, its properties confirmed by the described algorithm allow for classification of the fingerprints. The described experiment was performed using FVC2004 fingerprints database. We obtained FRR (False Rejection Ratio) of about 15% and FAR (False Acceptance Ratio) equal to 0%. This result allows for application in the access control to restricted areas, i.e., if FAR has to be Iow. In generał, SIFT can be considered as the first stage of classification of fingerprints in the database searching.

PL

Artykuł prezentuje zastosowanie algorytmu SIFT (z ang. Scale Inwariant Feature Transform - skaloniezmiennicze przekształcenie cech). Pomimo iż SIFT jest algorytmem do kojarzenia pewnych obiektów w obrazach, jego cechy pozwalają na wykorzystanie go przy klasyfikacji odcisków palców. Opisany eksperyment został przeprowadzony przy użyciu testowej bazy danych o nazwie FVC2004, która zawiera materiał daktyloskopijny. Współczynnik FRR (współczynnik błędnego odrzucenia) został uzyskany na poziomie ok. 15%, a współczynnik FAR (współczynnik błędnej akceptacji) równy 0%. Rezultaty te pozwalają stosować taki algorytm np. w systemach ochrony stref chronionych. Algorytm SIFT może być także pierwszym etapem przeszukiwania bazy danych w celu wstępnej selekcji obrazów z dużej bazy danych.

2

Fingerprint classification using computational intelligence algorithms in medical diagnostics

Wajs W., Wojtowicz H., Wojtowicz J.

Bio-Algorithms and Med-Systems

|

2011

|

Vol. 7, no. 2

95--100

EN

Fingerprint classification is used by anthropologist in detection of genetic disorders in infants.This paper describes application of image processing and pattern recognition methods in classification of fingerprints. Fingerprint classifiers, which are part of an automatic system for rapid screen diagnosing of trisomy 21 (Down Syndrome) in infants, are created and discussed. The system is a tool supporting medical decision by automatic processing of dermatoglyphic prints and detecting features indicating presence of genetic disorder. Images of dermatoglyphic prints are pre-processed before the classification stage to extract features analyzed by the Support Vector Machines algorithm. Application of an algorithm based on multi-scale pyramid decomposition of the image is proposed for the ridge orientation calculation. RBF and triangular kernel types are used in the training of SVM multi-class systems generated with the one–vs–one scheme. The experiments conducted on the database of the Collegium Medicum Jagiellonian University in Cracow show the effectiveness of the proposed approach in classification of infants’ fingerprints.

3

A novel approach for fingerprint classification system based on new feature area search

Abd Allah M. M.

Machine Graphics and Vision

|

2005

|

Vol. 14, No. 2

201-212

EN

The paper presents a new fast fingerprint classification method based on direction patterns. The method is designed to be applicable to today's embedded systems for fingerprint authentication, in which small area sensors are employed (large enough to capture all the core and delta points of a fingerprint). The proposed procedure consists of four steps. First, ridge direction is determined at the pixel level. Second, average orientation field flow is assessed within 8x8 blocks. Then pattern matching is applied to determine presence of either of three "feature areas". Finally, the target classes are identified through a novel classification approach, called generally a pattern area. We prove that the search of direction pattern in a specific area is able to classify fingerprints clearly and quickly. With our algorithm, the classification accuracy of 94% is achieved over 4000 images in the NIST-4 database, slightly lower than the conventional approaches. However, the classification speed has improved tremendously, up to about 10 times faster than the conventional singular point approaches at the pixel level.

4

Inexact graph matching for fingerprint classification

Lumini A., Maio D., Maltoni D.

Machine Graphics and Vision

|

1999

|

Vol. 8, No. 2

231-248

EN

In this work we introduce a new structural approach to automatic fingerprint classification. The fingerprint directional image is partitioned into "homogeneous" connected regions according to the fingerprint topology. A relational graph is constructed in order to compactly summarize the fingerprint macro-structure resulting from the partitioning process. An inexact graph matching technique is adopted to compare this graph with a set of prototype graphs which have been a-priori derived starting from a well-known classification scheme.