000 04667na a2200877 4500
001 63719
003 koha_MIRAKIL
005 20221103135316.0
008 180313b tu 000 0
040 _aCY-NiCIU
_btur
_cCY-NiCIU
_erda
041 _aeng
090 _aYL 287
_bC25 2010
100 _aÇakır, Demet
245 _aFacial expression recognision based on scale invariant feature transform
_cDemet Çakır; Supervisor: Mehmet Kuşaf
260 _aNicosia
_bCyprus International University
_c2010
300 _aX, 59 p
_bill, fig
_c30.5 cm
336 _2rdacontent
_atext
_btxt
337 _2rdamedia
_aunmediated
_bn
338 _2rdacarrier
_avolume
_bnc
504 _ainclude references (55-59 p.)
520 _a' Human computer interaction (HCL) is an active research area since the early days of computers. HCL aims to ease computer usage through various methods. One of the most important method is to act on human behavior. In this problem of person independent facial expression recognition from Scale Invariant Features Transform (SIFT) is investigated. Since human communication is mainly performed by face, we have chosen to extract facial expressions. Our primary objective is to increase available identification performance in the literature, while trying to solve problems related to external facts, such as lighting orientation and scaling. In our research, we propose a feature selection methodology that uses key point descriptors of the SIFT features features extracted from the expression images to improve classifications. The selection algorithm aims to derive a set of SIFT features from the original expression images which minimizes the within-class variance. The proposed methodology is evaluated using 3D facial expression data base BU-3DFE (Binghamton University 3D Facial Expression). Kullback Leibler Divergence (KLD) is used as a distance measure for computing the dissimilar score between histograms. Facial expression such as anger, fear, happiness, sadness and surprise are successfully recognized. '
650 _aScale invariant feature transform
650 _aÖlçek değişmez özellik dönüşümü
650 _aKullback Leibler Divergence
650 _aKullback Leibler Divergence
700 _aSupervisor: Kuşaf, Mehmet
_91656
942 _2ddc
_cTS
505 1 _g1
_tCHAPTER 1-INTRODUCTION
505 1 _g1
_tOverview
505 1 _g2
_tProblem Statement and Its Significance
505 1 _g4
_tLiterature Survey
505 1 _g5
_tGeometric Features
505 1 _g6
_tApperance Features
505 1 _g9
_tModel Template-Based Approaches
505 1 _g11
_tLocal Descriptors
505 1 _g12
_tContribution to Facial Representaion
505 1 _g12
_tFeature Representation
505 1 _g13
_tFeature Extraction and Selection
505 1 _g13
_tClassifier Design
505 1 _g14
_tThesis Overview
505 1 _g16
_tCHAPTER 2-SIFT METHODOLOGY
505 1 _g16
_tScale-Space Extreme Detection
505 1 _g19
_tKeypoint Localization
505 1 _g21
_tKeypoint Descriptor
505 1 _g24
_tCHAPTER 3-FEATURE REPRESENTATION FOR MATCHING
505 1 _g24
_tBasic Concepts of Feature Representation
505 1 _g24
_tSIFT Feature Representation using Face Descriptors
505 1 _g26
_tFeature Matching
505 1 _g27
_tFace Descriptor Matching
505 1 _g29
_tImproved SIFT Matching Using Kullback-Leibler Divergence
505 1 _g30
_tEvaluation and Experiment Results
505 1 _g32
_tConclusions
505 1 _g33
_tCHAPTER 4: FEATURE EXTRACTION AND SELECTION
505 1 _g33
_tFeature Selection
505 1 _g34
_tFeature Selection
505 1 _g34
_tPurpose and Importance of Feature Selection
505 1 _g35
_tChoosing among Features
505 1 _g36
_tRelated Work
505 1 _g37
_tDiscriminating Power Estimation of SIFT Features
505 1 _g38
_tBU-3DFE Database
505 1 _g39
_tEvaluation and Experiment Result
505 1 _g44
_tConclusions
505 1 _g45
_tCHAPTER 5-CLASSIFIER DESIGN FOR SIFT FEATURES
505 1 _g45
_tClassifier Design
505 1 _g45
_tImage Matching using Regular SIFT
505 1 _g46
_tMinimum Pair Distance (MPD)
505 1 _g47
_tSub-region Construction for Feature Matching
505 1 _g48
_tRegular Grid Base Face Descriptor Matching
505 1 _g49
_tEvaluation and Experimental Results
505 1 _g51
_tConclusion
505 1 _g53
_tCHAPTER 6-CONCLUSION AND FUTURE WORKS
505 1 _g53
_tConclusions
505 1 _g53
_tFuture Works
505 1 _g55
_tREFERENCES
999 _c324
_d324