Human identification systems are commonly used for security issues. Most of them are based on ID card. However, using an ID card for identification may not be safe enough since people may not have any protection against the theft. Another solution to the identification problem is to use iris or fingerprints. However, systems based on the iris or fingerprints need close interaction to identification machine. Identifying someone from his photograph overcomes all these problems which can be called as face recognition. Common face recognition systems are based on the 2D image recognition but success rates of these methods are strictly depending on the environment. Variations on brightness and pose, complex background are the main problems for 2D image recognition systems. At this point, three dimensional face recognition techniques gain importance. Although there are a lot of methods developed for 3D face recognition, many of them assume that face is not rotated and there is not any destructive (i.e. beard, moustache, hair, hat, and eyeglasses) on the face. However, identification needs to be done though these destructives. Basic step for the face recognition is the determination of the anchor points (i.e. nose tip, inner eye points). In this study, the goal is to implement previously proposed four face recognition methods based on anchor point detection / &ldquo / Multimodal Facial Feature Extraction for Automatic 3D Face Recognition&rdquo / , &ldquo / Automatic Feature Extraction for Multiview 3D Face Recognition&rdquo / , &ldquo / Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression&rdquo / , &ldquo / 3D face detection using curvature analysis&rdquo / , to compare the success rates of them for rotated and destructed images and finally to propose improvements on these methods.

In this study, a 3D face representation and recognition method based on spherical harmonics expansion is proposed. The input data to the method is range image of the face. This data is called 2.5 dimensional. Input faces are manually marked on the two eyes, nose and chin points. In two dimensions, using the marker points, the human face is modeled as two concentric half ellipses for the selection of region of interest. These marker points are also used in three dimensions to register the faces so that the nose point tip is at the origin and the line across the two eyes lies parallel to the horizontal plane. A PCA based component analysis is done to further align the faces vertically. The aligned face is stitched and mapped to an ellipsoid and transformed using real spherical harmonics expansion. The real harmonics expansion coefficients are labeled and stored into a gallery. Using these coefficients as input, several classification algorithms are applied and the results are reported.

3D modeling of real objects has an increasing importance in numerous areas. Although many methods and solutions are already proposed for 3D data acquisition, research continuing in this area is still intense. However, a crucial drawback about 3D data extraction algorithms is their testing and validation difficulty. Additionally, obtaining calibrated 2D and 3D imaging systems is troublesome due to their high effort demand for calibration and high cost. In this thesis, a 2D/3D Imaging Simulator is proposed in order to ease development and testing of 3D data interpretations of different methods and also to generate synthetic images for miscellaneous use. Furthermore, an example application on FRGC database is explained in detail.

Video annotation has become an important issue due to the rapidly increasing amount of video available. For efficient video content searches, annotation has to be done beforehand, which is a time-consuming process if done manually. Automatic annotation of faces for person identification is a major challenge in the context of content-based video retrieval. This thesis work focuses on the development of a semi-automatic face annotation system which benefits from online learning methods. The system creates a face database by using face detection and tracking algorithms to collect samples of the encountered faces in the video and by receiving labels from the user. Using this database a learner model is trained. While the training session continues, the system starts offering labels for the newly encountered faces and lets the user acknowledge or correct the suggested labels hence a learner is updated online throughout the video. The user is free to train the learner until satisfactory results are obtained. In order to create a face database, a shot boundary algorithm is implemented to partition the video into semantically meaningful segments and the user browses through the video from one shot boundary to the next. A face detector followed by a face tracker is implemented to collect face samples within two shot boundary frames. For online learning, feature extraction and classification methods which are computationally efficient are investigated and evaluated. Sequential variants of some robust batch classification algorithms are implemented. Combinations of feature extraction and classification methods have been tested and compared according to their face recognition accuracy and computational performances.

This thesis represents two approaches for three dimensional face recognition. In the first approach, a generic face model is fitted to human face. Local shape descriptors are located on the nodes of generic model mesh. Discriminative local shape descriptors on the nodes are selected and fed as input into the face recognition system. In the second approach, local shape descriptors which are uniformly distributed across the face are calculated. Among the calculated shape descriptors that are discriminative for recognition process are selected and used for three dimensional face recognition. Both approaches are tested with widely accepted FRGCv2.0 database and experiment protocol. Reported results are better than the state-of-theart systems. Recognition performances for neutral and non-neutral faces are also reported.

¡@¡@It has been for a long time to develop systems of eye control, which are related to a variety of techniques, such as signal/image processing, characteristics of face identifying/tracking, action-mappings, etc. In terms of implementations, the acquisition of data can be done by either special instruments or by general devices. Such systems can be applied to many fields, for instance, military, medicine, entertainments, and other tasks that are fitted. And for the similar system, the performance differs due to the disparity of distinct situations and the way to use it. ¡@¡@In this thesis, we present a system that takes a sequence of images of a user as inputs, and then integrates methods of elliptical model of head, dual states of eyes, deformable templates, and the most yield filter to track the user¡¦s eyes. A coarse-to-fine strategy is used to rapidly locate the region of eyes and to get the information of eyes in order to translate into corresponding operations on machines. The experiment shows that our system is quite robust and fast so that it can help people who are unable to use physical body well.

<p>Face detection and pose estimation are two widely studied problems - mainly because of their use as subcomponents in important applications, e.g. face recognition. In this thesis I investigate a new approach to the general problem of object detection and pose estimation and apply it to faces. Face detection can be considered a special case of this general problem, but is complicated by the fact that faces are non-rigid objects. The basis of the new approach is the use of scale and orientation invariant feature structures - feature triplets - extracted from the image, as well as a biologically inspired associative structure which maps from feature triplets to desired responses (position, pose, etc.). The feature triplets are constructed from curvature features in the image and coded in a way to represent distances between major facial features (eyes, nose and mouth). The final system has been evaluated on different sets of face images.</p>

<p>In today’s society, people often find themselves in situations where they need to be identified;for example when we buy alcohol, need to use an ATM or log on to our e-mail account. The most common methods today that are used for these kinds of matters are antiquated, and in</p><p>the meantime, criminals all over the world get more sophisticated. Companies invest billions every day in order to protect their interests. Maybe it’s time that we finally give biometrics the</p><p>attention that it deserves.</p><p>This essay aims to describe the biometric methods that are available today, find some of the most effective when it comes to physical access and make a comparison. Face recognition and fingerprint scanning will be described more thoroughly. Pros and cons will be analyzed and the theory will be linked to interviews with three Swedish organisations.</p> / <p>I dagens samhälle hamnar vi människor regelbundet i situationer där vi blir tvungna att identifiera oss. Det kan till exempelvis vara när vi köper alkohol, tar ut pengar eller loggar in på vårt e-mailkonto. De vanligaste metoderna, som idag används för dessa identifieringar, har funnits länge och är föråldrade och i takt med detta blir brottslingar världen allt mer sofistikerade. Dagligen investerar företag världen över miljarder för att skydda exempelvis</p><p>data med hjälp av koder och andra mjukvaruinstallationer. Kanske är det istället dags för att vi ger biometrin en ordentlig chans.</p><p>Den här uppsatsen syftar till att redogöra för de biometriska säkerhetsmetoder som finns tillgängliga, identifiera några av de effektivaste när det gäller fysisk access och jämföra dessa med varandra. Det är framförallt ansiktsigenkänning och fingeravtrycksavläsning som kommer att ges mycket plats i studien. För- och nackdelar kommer att tas upp och teorin kommer att kopplas till intervjuer gjorda med tre svenska företag.</p>

Ultra-high molecular weight polyethylene (UHMWPE) is used worldwide as a bearing material in total joint replacement prostheses. Despite its excellent biocompatibility and high wear resistance, wear of UHMWPE components continues to be a major problem limiting the clinical lifespan of UHMWPE-containing orthopaedic implant devices. Multi-directional motion or cross-path motion is known to affect wear rates of UHMWPE in total knee and hip replacement prostheses. The purpose of this study was to quantify the effect of counterface roughness on the cross-path wear of UHMWPE and to determine if the previously established unified theory of wear model could accurately predict wear rates in an abrasive wear environment. UHMWPE pins were articulated against both smooth (centerline roughness, Ra, of 0.015 µm) and rough (Ra = 0.450µm) cobalt-chromium counterfaces in a series of six rectangular wear paths (width = A, length = B) with systematically increasing aspect ratios (B/A) and linear tracking (A = 0), all with identical path lengths (20mm) per cycle. Gravimetric weight loss was converted into volumetric wear rates and wear factors, k. The results showed that for both smooth and rough-counterface tests, wear reached a maximum when a 3mmx7mm wear path was employed. The unified theory of wear was generally accurate in predicting wear rates; however, for rough-counterface tests there was a larger increase in the wear factor for higher aspect ratio rectangular wear paths. The ratio [k rough/ k smooth] decreased monotonically as a function of increasing width of rectangles, normalized by total path length, or A/(A +B). This study showed that wear of UHMWPE articulating in a rectangular motion path likely occurs via a two-step mechanism beginning with molecular orientation followed by material fracture from the UHMWPE surface. The models inability to accurately predict UHMWPE wear for rectangular paths with lower aspect ratios suggests that there may be other operative wear mechanisms including significant re-orientation in the perpendicular sliding direction. In conclusion, it is possible to predict the wear behavior of UHMWPE using mathematical models. A robust model would have an important role in characterizing and predicting performance of currently used and potential future orthopaedic implant materials.

Texte remanié de: Th.--Méd.--Bordeaux 2, 2001. / Bibliogr. p. 351-363.