Publication:
Face recognition using integrated discrete cosine transform and kernel fisher discriminant analysis

Simple item page
dc.citedby0
dc.contributor.authorJanahiraman T.V.en_US
dc.contributor.authorOmar J.en_US
dc.contributor.authorFarukh H.N.en_US
dc.contributor.authorid35198314400en_US
dc.contributor.authorid24463418200en_US
dc.contributor.authorid35198080900en_US
dc.date.accessioned2023-12-28T08:57:54Z
dc.date.available2023-12-28T08:57:54Z
dc.date.issued2006
dc.description.abstractIn face recognition applications, the dimension of the sample space is usually larger than the number of the samples in a training set. As a result, Fisher Linear Discriminant Analysis (FLD) based methods suffers due to singularity problem (of scatter matrix). This situation is often referred as "small sample size" (SSS) problem. Moreover, FLD is a linear algorithm by nature. Hence, it fails to extract important information from nonlinear and complex data such as face image. To remedy this problem, this paper presents a new face recognition approach by integrating Discrete Cosine Transform (DCT) and Kernel Fisher Discriminant Analysis (KFDA). The DCT has the capability to compact the energy in an image and let the dimensionality of the input sample space to be reduced. Then, KFDA, a new variant of FLD, will be used to extract the most discriminating feature. This is performed by transforming the reduced DCT subset using a nonlinear kernel function to a high dimensional nonlinear feature space and then followed by the FLD step. Based on the extensive experiments performed on ORL Database, the highest recognition accuracy of 95.375% is achieved with only 24 features. �2006 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo5276535
dc.identifier.doi10.1109/ICOCI.2006.5276535
dc.identifier.scopus2-s2.0-71249128487
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-71249128487&doi=10.1109%2fICOCI.2006.5276535&partnerID=40&md5=53d7047c6ff2b1ae8c76ecf6b1f18dca
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/29842
dc.sourceScopus
dc.sourcetitle2006 International Conference on Computing and Informatics, ICOCI '06
dc.subjectComputer science
dc.subjectCosine transforms
dc.subjectDiscrete cosine transforms
dc.subjectDiscriminant analysis
dc.subjectFeature extraction
dc.subjectFisher information matrix
dc.subjectLearning algorithms
dc.subjectNonlinear analysis
dc.subjectComplex data
dc.subjectFace images
dc.subjectFisher linear discriminant analysis
dc.subjectHigh-dimensional
dc.subjectInput sample
dc.subjectKernel fisher discriminant analysis
dc.subjectLinear algorithms
dc.subjectNonlinear features
dc.subjectNonlinear kernel functions
dc.subjectORL database
dc.subjectRecognition accuracy
dc.subjectSample space
dc.subjectScatter matrix
dc.subjectSingularity problems
dc.subjectSmall Sample Size
dc.subjectTraining sets
dc.subjectFace recognition
dc.titleFace recognition using integrated discrete cosine transform and kernel fisher discriminant analysisen_US
dc.typeConference paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS