• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 2
  • Tagged with
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Akies dugno kraujagyslių vingiuotumo įvertinimo metodai / The methods for estimation of eye fundus blood vessel tortuosity

Patašius, Martynas 24 May 2006 (has links)
Tortuosity of eye fundus blood vessels is one of parameters that describe state of the blood vessels. It can be detected from fundus images. The increase in vessel tortuosity was observed in eyes of patients with advanced background diabetic retinopathy, papilloedema, arterial hypertension, even in some completely healthy eyes (in this case tortuosity does not change in time). Thus the feature of the line – tortousity – could be used as the diagnostic feature in medical applications. Unfortunately, completely reliable definition and numerical estimation of tortuosity of line (blood vessel) does not exist, although there were some more or less successful attempts to define it. This work presents a new way to estimate the tortuosity using the integral of square derivative of curvature. It is compared with the existing methods both theoretically and experimentally. Three types of lines have been used for experimental comparison: theoretical models of retinal vessels (straight line, parabola, sinusoid and their combinations), lines extracted from real fundus images and lines extracted from optometric scale for retinal vessel evaluation. To ease the extraction of the lines from these images a new version of one of the methods for vessel tracking has been created and implemented.
2

Biometrinės autentifikacijos modelio automobiliams sukūrimas ir tyrimas / Development and research of biometric authentication model for cars

Kulikauskas, Kristijonas 31 August 2011 (has links)
Automobilių apsauga visada buvo, yra ir bus aktuali. Esamos apsaugos priemonės nesunkiai apeinamos ir nesudaro didelių kliūčių, norint transporto priemonę pasisavinti. Reikalinga naujoviška vairuotojo autentifikavimo sistema, galinti sumažinti šią, pasisavinimo tikimybę. Tam tinka biometrija – asmens bruožų ar charakteristikų statistinė analizė ir nustatymas. Juos nustačius, gali būti naudojami asmens autentifikacijai. Tai daroma lyginant su anksčiau užfiksuotu šablonu. Naudojama šioms autentifikacijoms: kompiuteriuose tinklų, praėjimo kontrolės, bankomatuose, apsipirkimams kreditinėmis kortelėmis, mobiliuosiuose telefonuose, delniniuose kompiuteriuose, medicininių įrašų valdymui, nuotoliniame mokymesi ir t.t. Pirštų kraujagyslės – nauja biometrinės autentifikacijos forma. Kadangi kraujagyslės yra po oda, jos yra nematomos apšviečiant natūralia šviesa. Tačiau jos puikiai matomos apšvietus artima infraraudoniems spinduliams šviesa. Šiame tyrime buvo sukurtas ir ištirtas biometrinės autentifikacijos automobiliams modelis. Ištirtas trijų atvaizdų apdorojimo algoritmų tinkamums, nustatant kuris jų mažiausia jautrus raiškos ir triukšmo pasikeitimams. Jį ir siūlome naudoti šiame autentifikacijos modelyje. / Automobile security is always relevant. Existing security systems could be easily bypassed and are not a big barrier for thieves. So there is a necessity for a innovative authentication system. Biometrics consist of methods for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits. In computer science, in particular, biometrics is used as a form of identity access management and access control. It could be also used for automobile security. Finger vein comparison is a relatively new form of biometrics, which could also be used for authentication. Images of finger veins could be obtained illuminating fingers with near-infrared light. Those images are very unique and different for every person and every finger. In this research biometric authentication model for automobiles is developed and researched. Three image recognition algorythms were tested in the experiment, determining which one is less sensitive to resolution changes and noise. The results were given, proposing use of one algorythm, in our model of biometric authentication system for automobiles.

Page generated in 0.0326 seconds