| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:ALGORITMI ZA PREDOBDELAVO SLIK IN PRIMERJAVA METOD ZA RAZPOZNAVO OBRAZOV
Authors:ID Gangl, Simon (Author)
ID Žalik, Borut (Mentor) More about this mentor... New window
ID Mongus, Domen (Comentor)
Files:.pdf UNI_Gangl_Simon_2010.pdf (2,73 MB)
MD5: 09A45A159375CF7EEB4762B01E2365CC
PID: 20.500.12556/dkum/dfa18556-6e14-4a80-826c-097482a5f4cd
 
Language:Slovenian
Work type:Undergraduate thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Zaradi visokih teženj trga po varnih sistemih, ki temeljijo na identifikaciji s pomočjo biometričnih podatkov, ostaja razpoznava obrazov atraktivno raziskovalno področje. V tem diplomskem delu obravnavamo razpoznavanje obrazov tako iz vidika predobdelave vhodnih podatkov kot tudi iz vidika analize uspešnosti različnih pristopov. Najprej predstavimo naš postopek za normalizacijo slike obraza. Ta za izločevanje šuma iz vhodnih podatkov združuje različne geometrijske tehnike s tehnikami umetne inteligence in računalniškega vida. Tako obdelane slike so vhod v postopke za razpoznavo obrazov, implementirane v okviru tega diplomskega dela. Ob splošni predstavitvi postopkov razpoznave obrazov natančneje opišemo tri izmed najpomembnejših. Podrobno predstavimo njihovo implementacijo in podamo primerjavo njihovih uspešnosti. Ker za razpoznavo obrazov uporabljamo tudi statistične pristope, ki so pogosto podvrženi vplivom učne množice, rezultate podrobneje analiziramo tudi iz tega vidika.
Keywords:razpoznava obrazov, normalizirana slika obraza, PCA, LDA, Gaborjeva valčna transformacija, vpliv učne množice
Place of publishing:Maribor
Publisher:[S. Gangl]
Year of publishing:2010
PID:20.500.12556/DKUM-14236 New window
UDC:004.932(043.2)
COBISS.SI-ID:14302486 New window
NUK URN:URN:SI:UM:DK:WUKGS0GI
Publication date in DKUM:07.06.2010
Views:3080
Downloads:385
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:ALGORITHMS FOR IMAGE PRE-PROCESSING AND COMPARISON OF METHODS FOR FACE RECOGNITION
Abstract:Because of market demands for secure systems based on biometrical identification, face recognition remains an appealing field in the research community. In this diploma work we discuss face recognition from the view of input data pre-processing and performance analysis of different methods. Initially, we present our method for the normalization of a face image. For the purpose of noise removal from input data, various geometric techniques are combined with techniques from artificial intelligence and computer vision. The images processed in that way are the input in the face recognition techniques, implemented in the course of this diploma work. Beside a general presentation of the face recognition techniques, three of them are described more precisely. Their implementation is given in detail and a comparison of their successfulness is presented. Because also statistical methods are used (they are often influenced by the learning sets), the results are analyzed from that point of view as well.
Keywords:face recognition, normalized facial image, PCA, LDA, Gabor wavelet transformation, influence of the learning set


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