3D face recognition

Üstün, Bülend
In this thesis, the effect of registration process is evaluated as well as several methods proposed for 3D face recognition. Input faces are in point cloud form and have noises due to the nature of scanner technologies. These inputs are noise filtered and smoothed before registration step. In order to register the faces an average face model is obtained from all the images in the database. All the faces are registered to the average model and stored to the database. Registration is performed by using a rigid registration technique called ICP (Iterative Closest Point), probably the most popular technique for registering two 3D shapes. Furthermore some variants of ICP are implemented and they are evaluated in terms of accuracy, time and number of iterations needed for convergence. At the recognition step, several recognition methods, namely Eigenface, Fisherface, NMF (Nonnegative Matrix Factorization) and ICA (Independent Component Analysis) are tested on registered and non-registered faces and the performances are evaluated.


Moving Object Detction in 2D and 3D Scenes
Sırtkaya, Salim; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2004)
This thesis describes the theoretical bases, development and testing of an integrated moving object detection framework in 2D and 3D scenes. The detection problem is analyzed in stationary and non-stationary camera sequences and different algorithms are developed for each case. Two methods are proposed in stationary camera sequences: background extraction followed by differencing and thresholding, and motion detection using optical flow field calculated by أKanade-Lucas Feature Trackerؤ. For non-stationary ...
Developing a GIS based methodology for decision making for multiobjectiverecreational areas, case study : Eastern Black Sea Region
Kaya, Zehra Gözde; Akyürek, Sevda Zuhal; Department of Geodetic and Geographical Information Technologies (2006)
In this study, a method is proposed for decision making for multiobjective recreational areas, by using multi attribute decision making rules within GIS. The method provides integration of ecological, sociocultural and economic considerations of an ecologically valuable area in a systematic way. The first stage of the methodology includes determination of suitable areas for three usages of forest area; outdoor recreation, timber production and protection needed areas. The second stage comprises decision mak...
A workflow based online software review system
Çifci, Hasan; Demirörs, Onur; Department of Information Systems (2004)
Software review is an effective and efficient way for detecting defects in software artifacts. To improve the effectiveness and the efficiency of software review, a variety of software review techniques have been developed. Furthermore, computer support has been used to facilitate the software review process. Accordingly, several software review tools have been developed. Although existing tools provide new solutions to support software review, in general they suffer from a number of shortcomings. In this s...
The tools transporter movements problem in flexible manufacturing sysems
Kılınç, Fatma; Azizoğlu, Meral; Department of Industrial Engineering (2005)
In this study, we address job sequencing and tool switching problem arising in Flexible Manufacturing Systems. We consider a single machine with limited tool slots on its tool magazine. The available tool slots cannot accommodate all the tools required by all jobs, therefore tool switches between jobs are required. A single tool transporter with limited capacity is used in transporting the tools from the storage area to the machine. Our aim is to minimize the number of tool transporter movements. We provide...
Well test model identification by artificial neural networks
Kök, Mustafa Verşan (Informa UK Limited, 2000-01-01)
The aim of this research is to investigate the performance of artificial neural networks computing technology, to identify preliminary well test interpretation model based on derivative plot. The approach is based on training the neural network simulator uses back-propagation as the learning algorithm for a predefined range of analytically generated well test response. The trained network is then requested to identify the well test identification model for test data, which is not used during training sessio...
Citation Formats
B. Üstün, “3D face recognition,” M.S. - Master of Science, Middle East Technical University, 2007.