| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:RAZPOZNAVANJE OBRAZOV IN OČI V DIGITALNIH SLIKAH
Authors:ID Mlakar, Uroš (Author)
ID Potočnik, Božidar (Mentor) More about this mentor... New window
Files:.pdf UNI_Mlakar_Uros_2010.pdf (1,20 MB)
MD5: B441742A3A4FD0C4EBCA67AB901876EB
PID: 20.500.12556/dkum/ce60120b-b882-4d52-8246-23bf0ce88755
 
Language:Slovenian
Work type:Bachelor thesis/paper
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V tem diplomskem delu se ukvarjamo z razpoznavanjem obrazov in oči na digitalnih slikah. Najprej pregledamo obstoječe metode s tega področja, zatem pa razvijemo in implementiramo lasten algoritem za omenjen problem. Pri načrtovanju algoritma smo privzeli, da mora biti vhodna slika dobro osvetljena, na sliki se lahko nahaja zgolj ena oseba, pogled osebe pa je lahko poljuben. Algoritem sestoji iz treh zaporednih korakov. V prvem koraku ločimo obraz od ozadja, nato pa obraz izrežemo iz vhodne slike. V tretjem koraku še v zgornji polovici izrezane slike poiščemo oči. Uporabljena segmentacijska in klasifikacijska metoda je pragovna operacija. Algoritem smo preizkusili na 70 testnih slikah velikosti 255 x 300 slikovnih elementov, ki smo jih zajeli z digitalnim fotoaparatom. Uspešnost razpoznavanja oči je bila 85 % pri poljubnem pogledu osebe, pri frontalnem pogledu osebe pa je ta uspešnost narastla na 92,4 %.
Keywords:digitalna obdelava slik, razpoznavanje obrazov, razpoznavanje oči, segmentacija
Place of publishing:Maribor
Publisher:[U. Mlakar]
Year of publishing:2010
PID:20.500.12556/DKUM-15640 New window
UDC:004.93.021(043.2)
COBISS.SI-ID:14707990 New window
NUK URN:URN:SI:UM:DK:AB7ZU0JA
Publication date in DKUM:06.12.2010
Views:3047
Downloads:293
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



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:FACE AND EYE RECOGNITION IN DIGITAL IMAGES
Abstract:In this thesis we deal with recognition of faces and eyes in digital images. Firstly, existing methods from this research area are reviewed, afterwards we develop and implement our own algorithm for the mentioned problem. We presume by designing this algorithm that the input image is well illuminated; that only one person may appear in the image; whereas person’s look can be arbitrary oriented. This algorithm consists of three sequential steps. In the first step, we separate the face from the background, followed by cropping the face out of the input image. In the third step, we search for eyes in the upper part of the face image. The used segmentation and classification method is thresholding. The algorithm was tested on 70 testing images with dimension of 255 x 300 pixels, which were captured by using a digital camera. Eye recognition efficiency was 85 % at arbitrary person’s look, at frontal person’s look this efficiency rose to 92.4 %.
Keywords:digital image processing, face recognition, eye recognition, segmentation


Comments

Leave comment

You must 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