Please use this identifier to cite or link to this item:
DC FieldValueLanguage
dc.contributor.advisorDagher, Issamen_US
dc.contributor.authorAbi Fadel, Fady Azaren_US
dc.descriptionIncludes bibliographical references (p. 43-45).en_US
dc.descriptionSupervised by Dr. Issam Dagher.en_US
dc.description.abstractGender recognition has been playing a very important role in various applications such as human computer interaction, surveillance and security. In this context, this project aims to investigate a gender classification system and propose new models for a better performance. We have evaluated different learning algorithm; the SVM – RBF with a 5% outlier fraction outperformed other classifiers. We have examined the effectiveness of different feature selection methods. We have proposed two classification methods that focus on training subsets of images among the training images. Method 1 combines the outcome of different classifiers based on different image subsets, while method 2 is based on clustering the training data and building a classifier for each cluster. Experimental results showed that both methods might increase the classification accuracy. The first method performed better than the second one. In addition, results have shown that method 1 can reach 100% accuracy.en_US
dc.description.statementofresponsibilityby Fady Azar Abi Fadelen_US
dc.format.extentix, 54 p. :ill., tables ;30 cmen_US
dc.rightsThis object is protected by copyright, and is made available here for research and educational purposes. Permission to reuse, publish, or reproduce the object beyond the personal and educational use exceptions must be obtained from the copyright holderen_US
dc.subject.lcshHuman face recognition (Computer science)en_US
dc.titleGender classificationen_US
dc.contributor.departmentDepartment of Electrical Engineeringen_US
dc.contributor.facultyFaculty of Engineeringen_US
dc.contributor.institutionUniversity of Balamanden_US
dc.description.degreeMS in Electrical Engineeringen_US
Appears in Collections:UOB Theses and Projects
Show simple item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.