1) La descarga del recurso depende de la página de origen
2) Para poder descargar el recurso, es necesario ser usuario registrado en Universia


Opción 1: Descargar recurso

Detalles del recurso

Descripción

Recognition systems based on biometrics (faces, hand shapes and fingerprints etc.) are finally taking off although it has taken a long way to come. Fingerprints have been a precious tool for law enforcement, forensics and recently in commercial use for over a century. Evaluate the performance of these emerging technologies is tricky problem. Most fingerprint verification algorithms rely on minutiae features, and these algorithms can only be as robust as the underlying minutiae features. Therefore, reliable minutiae extraction is vital to a system’s performance. Most of the feature extraction techniques extract features from thinned images but while dealing with binarization and skeletization of image it introduces noise or superfluous information, which creates troubles for genuine feature extraction. In this paper we have used the mathematical morphology to remove the superfluous information for genuine feature extraction and measure the feature extraction performance through sensitivity and specificity.

Pertenece a

CiteSeerX Scientific Literature Digital Library and Search Engine  

Autor(es)

Vikas Humbe -  S. S. Gornale -  Ramesh Manza -  K. V. Kale - 

Id.: 45682839

Idioma: inglés  - 

Versión: 1.0

Estado: Final

Tipo:  application/pdf - 

Palabras claveFeature Extraction - 

Tipo de recurso: Texto Narrativo  - 

Tipo de Interactividad: Expositivo

Nivel de Interactividad: muy bajo

Audiencia: Estudiante  -  Profesor  -  Autor  - 

Estructura: Atomic

Coste: no

Copyright: sí

: Metadata may be used without restrictions as long as the oai identifier remains attached to it.

Formatos:  application/pdf - 

Requerimientos técnicos:  Browser: Any - 

Relación: [IsBasedOn] http://ijcss.org/Volume1/Issue2/V1_I2_053.pdf
[References] 10.1.1.119.7009
[References] 10.1.1.6.7497
[References] 10.1.1.19.6417
[References] 10.1.1.104.690
[References] 10.1.1.19.6687

Fecha de contribución: 28-jul-2011

Contacto:

Localización:

Otros recursos del mismo autor(es)

  1. Mathematical Morphology Approach for Genuine Fingerprint Feature Extraction Recognition systems based on biometrics (faces, hand shapes and fingerprints etc.) are finally takin...
  2. Palmprint and Handgeometry Recognition using FAST features and Region properties Abstract: Biometrics recognition system is more reliable and popular. In this paper we describe a ...
  3. Using Genetic Algorithm for Automated Efficient Software Test Case Generation for Path Testing This paper discusses genetic algorithms that can automatically generate test cases to test selected ...
  4. Estimation of Crop and Forest Areas using Expert System based Knowledge Classifier Approach for Aurangabad District The present study demonstrates the application of remote sensing for the estimation of areas corresp...
  5. COMPARISON OF SVM AND FUZZY CLASSIFIER FOR AN INDIAN SCRIPT With the advent of technological era, conversion of scanned document (handwritten or printed) into m...

Otros recursos de la mismacolección

  1. Analog Neural Nets with Gaussian or Other Common Noise Distributions Cannot Recognize Arbitrary Regular Languages We consider recurrent analog neural nets where the output of each gate is subject to gaussian noise ...
  2. On the Effect of Analog Noise in Discrete-Time Analog Computations We introduce a model for analog computation with discrete time in the presence of analog noise that ...
  3. Generalized graphlet kernels for probabilistic inference in sparse graphs
  4. Scalable kernels for graphs with . . . While graphs with continuous node attributes arise in many applications, state-of-the-art graph kern...
  5. LEDA -- a Library of Efficient Data Types and Algorithms LEDA is a library of efficient data types and algorithms. At present, its strength is graph algorith...

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.