رکورد قبلیرکورد بعدی

" ROBUST PRE-PROCESSING TECHNIQUES FOR NON-IDEAL IRIS IMAGES_RU`QHbaYdHPJUL(egfUOQhNiPMjOQHbaYgk+LN`l[nmo[jLpOlfqr[jHPOs[ ctRU`Wur`l`QTVL_fHCY7HKJULvijLNw "


Document Type : Latin Dissertation
Language of Document : English
Record Number : 152083
Doc. No : ET23875
Main Entry : Purva M Barve
Title Proper : ROBUST PRE-PROCESSING TECHNIQUES FOR NON-IDEAL IRIS IMAGES_RU`QHbaYdHPJUL(egfUOQhNiPMjOQHbaYgk+LN`l[nmo[jLpOlfqr[jHPOs[ ctRU`Wur`l`QTVL_fHCY7HKJULvijLNw
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : The human iris has been demonstrated to be a very accurate, non-invasiveand easy-to-use biometric for personal identification. Most of the currentstate-of-the-art iris recognition systems require the iris acquisition to beideal. A lot of constraints are hence put on the user and the acquisitionprocess.Our aim in this research is to relax these conditions and to develop a preprocessingalgorithm, which can be used in conjunction with any matchingalgorithm to handle the so-called non-ideal iris images. In this thesis wepresent a few robust techniques to process the non-ideal iris images so as togive a segmented iris image to the matching algorithm. The motivationbehind this work is to reduce the false reject rates of the current recognitionsystems and to reduce the intra-class variability. A new technique forestimating and compensating the angle in non-frontal iris images ispresented. We have also developed a novel segmentation algorithm, whichuses an ellipse-fitting approach for localizing the pupil. A fast and simplelimbus boundary segmentation algorithm is also presented.,.............-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject : Electericl tess
: برق
electronic file name : TL47136.pdf
Title and statement of responsibility and : ROBUST PRE-PROCESSING TECHNIQUES FOR NON-IDEAL IRIS IMAGES_RU`QHbaYdHPJUL(egfUOQhNiPMjOQHbaYgk+LN`l[nmo[jLpOlfqr[jHPOs[ ctRU`Wur`l`QTVL_fHCY7HKJULvijLNw [Thesis]
آدرس ثابت

پیوستها
عنوان :
نام فایل :
نوع عام محتوا :
نوع ماده :
فرمت :
سایز :
عرض :
طول :
TL47136.pdf
TL47136.pdf
پایان نامه لاتین
متن
application/octet-stream
5.65 MB
85
85
نظرسنجی