| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document

Title:IZDVAJANJE POZICIJE OČESNEGA ZRKLA S POMOČJO SPLETNE KAMERE
Authors:Spagnolo, Gregor (Author)
Holobar, Aleš (Mentor) More about this mentor... New window
Divjak, Matjaž (Co-mentor)
Files:.pdf UNI_Spagnolo_Gregor_2011.pdf (1,99 MB)
 
Language:Slovenian
Work type:Bachelor thesis/paper (mb11)
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Diplomsko delo opisuje dva postopeka za zaznavanje pozicije očesnega zrkla na digitalnih slikah in obširno analizo rezultatov. Najprej je predstavljen postopek za zaznavanje obraza in oči, nato pa sta podrobneje opisana algoritma Houghove transformacije in radialne simetrije. Večji poudarek je na radialni simetriji, saj smo algoritem implementirali sami s pomočjo odprtokodne knjižnice Emgu.CV in okolja .NET. Zaradi natančnejše analize smo oba postopka ovrednotili na dveh različnih zbirkah slik. Prva vsebuje slike z nizko ločljivostjo 384 x 286 pikslov, ki so po kvaliteti podobne slikam s povprečne spletne kamere, druga pa vsebuje slike z višjo ločljivostjo 512 x 768 pikslov. Rezultati kažejo, da sta oba predstavljena postopka primerna za izdvajanje pozicije zrkla v realnem času, pri čemer je povprečna napaka zaznave približno 5 % razdalje med zunanjima kotičkoma očes.
Keywords:Računalniški vid, detektor obraza, detektor oči, algoritem radialne simetrije, Houghova transformacija, kaskada Viola-Jones, odstranjevanje odseva, Emgu.CV
Year of publishing:2011
Publisher:[G. Spagnolo]
Source:Šempeter pri Gorici
UDC:004.932(043.2)
COBISS_ID:15617558 Link is opened in a new window
NUK URN:URN:SI:UM:DK:0HJX2AZU
Views:1633
Downloads:130
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:KTFMB - FERI
:
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:EYE TRACKING WITH WEB CAMERA
Abstract:The diploma presents two methods for detection of eye position on digital images and extensive analysis of the results. First, the method for detecting faces and eyes is presented. Then, the algorithms for Hough transformation and radial symmetry are described. The emphasis is on radial symmetry, because the algorithm was implemented by us with help of the open source library Emgu.CV and the .NET framework. For more representative and thorough analysis we evaluated both methods on two different image datasets. First dataset contains low quality photos with 384 x 286 pixels that are similar to output of the average web cam. The second dataset contains higher resolution photos with 512 x 768 pixels. Results show that both presented methods are suitable for eye tracking in real time, with average error of detection is equal to approximately 5 % of the distance between outer eye corners.
Keywords:Computer vision, face detection, eye detection, radial symmetry algorithm, Hough transformation, Viola – Jones cascade, reflection removal, Emgu.CV


Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica