DEPARTMENT OF ELECTRICAL AND ELECTRONIC ENGINEERING
Permanent URI for this communityhttps://repository.ui.edu.ng/handle/123456789/478
Browse
5 results
Search Results
Item Optimised fisher discriminant analysis for recongnition of faces having black features.(Medwell Journals, 2008) Omidiora, E. O.; Fakolujo, O. A.; Ayeni, R. O.; Adeyanju, I. A.A face recognition system is one of the most desirable biometric identification such as computerized access control, document control and database retrieval. Although, several researches have been done on face recognition, most (if not all) have made use of non-black faces or very few numbers of black faces in their experiments. This study presents results of experiments based on black African faces (with and without tribal marks) using the optimized Fisher Discriminant Analysis. In the experiment, different sizes of gray scale images were used for recognition performance accuracy of between 88 and 99% were obtained. Also, taking into consideration was the rate of identifying an image using the same number of images to test the face recognition system. While, a completely robust real-time face recognition system is still under heavy investigation and development, the implemented system serves as an extendable foundation for future research.Item Quantitative evaluation of principal component analysis and fisher discriminant analysis techniques in face images.(Nigeria Computer Society, 2008) Omidiora, E. O.; Fakolujo, O. A.; Ayeni, R. O.; Olabiyisi, S. O.; Arulogun, O. T."Face recognition is an attractive field in enhancing both the security and the image retrieval activities in the multimedia world. Its natural basis in verification or identification purposes is a major factor of its wide acceptance in this evolving world of information technology. In this paper, experiments based on black African faces using Principal Component Analysis (OPCA) and Fisher Discriminant Analysis (OFDA) techniques were carried out. The design of the face recognition system was separated into three major sections - image acquisition and standardisation, dimensionality reduction, training and testing for recognition. Under static mode, experiments were performed on single scaled images without rotation, OPCA and OFDA both give recognition accuracies of between 89% and 97%;and) 88% and 98% respectively. These have been achieved at different levels of cropping. Despite the constraint created by the resources available, different results got showed that standard face recognition system could be developed using both algorithms. "Item Nature-inspired optimisation methods: the ant algorithm.(Duncan Science Company, 2008) Bello, O. A.; Ayeni, R. O.; Fakolujo, O. A.Nature has inspired many optimization techniques/ methods. This paper is directed to introduce some of these methods to the reader and emphasis was laid on the ant algorithm by discussing its properties and what it entails. Also some of the problems that ant algorism has been used to solve was listed while two of them were discussed in full,the TSP which the writer worked on and network routingItem A survey of face recognition techniques(Faculty of Technology, University of Ibadan, 2007) Omidiora, E. O.; Fakolujo, O. A.; Ayeni, R. O.; Ajila, T. M.A review of face recognition techniques has been carried out.Face recongition has been an attractive field in the society of both biological and computer vision of research. It exhibits the characteristics of being natural and low-intrusive. In this paper, an updated survey of techniques for face recognition is made. Methods of face regonition , such as geometric, statistical and neural networks approaches are presented and analyzed. The comparative performance of the variaous approaches is discussed.Item A prototype of a robust and secured access control system using principal component analysis(2007) Omidiora, E. O.; Fakolujo, O. A.; Olabiyisi, S. O.; Ayeni, R. O.The need for a robust and secured access control system using a suitable algorithm is highly inevitable to forestall daily online harkers that are responsible in defrauding people of invaluable information and transactions worth billions of dollars in the process. In this paper, faces were employed as the only control means of right of entrance and usage of information on the super-highway. Principal Component Analysis (PCA) was used to perform dimensionality reduction on the feature vectors of the digitized face images. Also, Euclidean distance was the required similarity measure employed to match the tested face with the trained faces inside the database for actual recognition. The result obtained showed that its avarage percentage of rightly classified face was 90.43% and FAR and FRR were 0.1077 &0.0609. An evaluation of the results demostrated PCA to be a very good algorithm for a robust and secured access control and recognition system.