Computer Engineering

Local symmetry axis based schemes have been used for generic shape recognition as they lead to articulation insensitive representations. Despite their strengths, purely syntactic level of axial representations precludes the possibility of distinguishing a likely articulation from an unlikely one. In order to overcome this weakness, syntax should be combined with pragmatics and/or semantics. As a solution we propose a novel articulation space which enables inferences on the likelihood of possible articulations. Articulation priors can be constructed directly from examples (pragmatics) or set externally (semantics). We incorporate articulation priors to a skeletal matching scheme to arrive at an enriched axial representation which is sensitive to unlikely articulations but insensitive to likely ones.

Shape skeletons are commonly used in generic shape recognition as they capture part hierarchy, providing a structural representation of shapes. However, their potential for shape classification has not been investigated much. In this study, we present a similarity based approach for classifying 2D shapes based on their Aslan skeletons . The coarse structure of this skeleton representation allows us to represent each shape category in the form of a reduced set of prototypical trees, offering an alternative solution to the problem of selecting the best representative examples. The ensemble of these category prototypes is then used to form a similarity based representation space in which the similarities between a given shape and the prototypes are computed using a tree edit distance algorithm, and Support Vector Machine (SVM) classifiers are used to predict the category membership of the shape based on computed similarities.

Skeletal trees are commonly used in order to express geometric properties of the shape. Accordingly, tree edit distance is used to compute a dissimilarity between two given shapes. We present a new tree edit based shape matching method which uses a recent coarse skeleton representation. The coarse skeleton representation allows us to represent both shapes and shape categories in the form of depth-1 trees.

We present a new skeletal representation along with a matching framework to address the deformable shape recognition problem. The disconnectedness arises as a result of excessive regularization that we use to describe a shape at an attainably coarse scale. Our motivation is to rely on the stable properties of the shape instead of inaccurately measured secondary details. The new representation does not suffer from the common instability problems of traditional connected skeletons, and the matching process gives quite successful results on a diverse database of 2D shapes. An important difference of our approach from the conventional use of the skeleton is that we replace the local coordinate frame with a global Euclidean frame supported by additional mechanisms to handle articulations and local boundary deformations. As a result, we can produce descriptions that are sensitive to any combination of changes in scale, position, orientation and articulation, as well as invariant ones.

We describe a computer vision based mouse, which can control and command the cursor of a computer or a computerized system using a camera. In order to move the cursor on the computer screen the user simply moves the mouse shaped passive device placed on a surface within the viewing area of the camera. The video generated by the camera is analyzed using computer vision techniques and the computer moves the cursor according to mouse movements. The computer vision based mouse has regions corresponding to buttons for clicking. To click a button the user simply covers one of these regions with his/her finger.

Many applications of computer vision requires segmenting out of an object of interest from a given image. Motivated by unlevel-sets formulation of Raviv, Kiryati and Sochen [8] and statistical formulation of Leventon, Grimson and Faugeras [6], we present a new image segmentation method which accounts for prior shape information. Our method depends on Ambrosio-Tortorelli approximation of Mumford-Shah functional. The prior shape is represented by a by-product of this functional, a smooth edge indicator function, known as the “edge strength function”, which provides a distance-like surface for the shape boundary. Our method can handle arbitrary deformations due to shape variability as well as plane Euclidean transformations. The method is also robust with respect to noise and missing parts. Furthermore, this formulation does not require simple closed curves as in a typical level set formulation.

We present a new skeletal representation along with a matching framework to address the deformable shape recognition problem. The disconnectedness arises as a result of excessive regularization that we use to describe a shape at an attainably coarse scale. Our motivation is to rely on the stable properties of the shape instead of inaccurately measured secondary details. The new representation does not suffer from the common instability problems of traditional connected skeletons, and the matching process gives quite successful results on a diverse database of 2D shapes. An important difference of our approach from the conventional use of the skeleton is that we replace the local coordinate frame with a global Euclidean frame supported by additional mechanisms to handle articulations and local boundary deformations. As a result, we can produce descriptions that are sensitive to any combination of changes in scale, position, orientation and articulation, as well as invariant ones.

Graph transduction is a popular class of semi-supervised learning techniques, which aims to estimate a classification function defined over a graph of labeled and unlabeled data points. The general idea is to propagate the provided label information to unlabeled nodes in a consistent way. In contrast to the traditional view, in which the process of label propagation is defined as a graph Laplacian regularization, here we propose a radically different perspective that is based on game-theoretic notions. Within our framework, the transduction problem is formulated in terms of a non-cooperative multi-player game where any equilibrium of the proposed game corresponds to a consistent labeling of the data. An attractive feature of our formulation is that it is inherently a multi-class approach and imposes no constraint whatsoever on the structure of the pairwise similarity matrix, being able to naturally deal with asymmetric and negative similarities alike. We evaluated our approach on some real-world problems involving symmetric or asymmetric similarities and obtained competitive results against state-of-the-art algorithms.

In this paper, we introduce the notion of a bounded parameter Markov decision process as a generalization of the traditional exact MDP. A bounded parameter MDP is a set of exact MDPs speci ed by giving upper and lower bounds on transition probabilities and rewards (all the MDPs in the set share the same state and action space). Bounded parameter MDPs can be used to represent variation or uncertainty concerning the parameters of sequential decision problems. Bounded parameter MDPs can also be used in aggregation schemes to represent the variation in the transition probabilities for di erent base states aggregated together in the same aggregate state.

In this paper, we introduce the notion of a bounded parameter Markov decision process as a generalization of the traditional exact MDP. A bounded parameter MDP is a set of exact MDPs speci ed by giving upper and lower bounds on transition probabilities and rewards (all the MDPs in the set share the same state and action space). Bounded parameter MDPs can be used to represent variation or uncertainty concerning the parameters of sequential decision problems. Bounded parameter MDPs can also be used in aggregation schemes to represent the variation in the transition probabilities for di erent base states aggregated together in the same aggregate state.

Psychology studies from the late 70s showed that our perception of similarities is strongly influenced by the underlying category structure . Further, the search of a model for representing and evaluating the similarities between shapes in a perceptually coherent way is still an open issue . Starting from these observations, we aim at jointly learning the categories from examples and the similarity measures related to them. There is a chicken and egg dilemma here: class knowledge is required to determine perceived similarities, while the similarities are needed to extract class knowledge in an unsupervised way. In this paper, we present a game theoretic approach to compute 2D shape categories using disconnected skeletons . The approach, based on [20], provides us with both the cluster information needed to extract the categories, and the relevance information needed to compute the category model and, thus, the similarities. The approach has been tested on a database of 1000 shapes and compared favorably with the pairwise clustering approaches working on similarities that do not make use of the underlying contextual information and a feature-based approach similar to ours.

The search of a model for representing and evaluating the similarities between shapes in a perceptually coherent way is still an open issue. One reason for this is that our perception of similarities is strongly influenced by the underlying category structure. In this paper we aim at jointly learning the categories from examples and the similarity measures related to them. There is a chicken and egg dilemma here: class knowledge is required to determine perceived similarities, while the similarities are needed to extract class knowledge in an unsupervised way. The problem is addressed through a game theoretic approach which allows us to compute 2D shape categories based on a skeletal representation. The approach provides us with both the cluster information needed to extract the categories, and the relevance information needed to compute the category model and, thus, the similarities. Experiments on a database of 1000 shapes showed that the approach outperform other clustering approaches that do not make use of the underlying contextual information and provides similarities comparable with a state-of-the-art label-propagation approach which, however, cannot extract categories.

New matrix multiplication algorithms are proposed for massively parallel supercomputers with 2D/3D, all-port torus interconnection networks. The proposed algorithms are based on the traditional row-by-column multiplication matrix product model and employ a special routing pattern for better scalability. They compare favorably to the variants of Cannon's and DNS algorithms since they allow matrices of the same size to be multiplied on a higher number of processors due to lower data communication overhead.

ÖZ Doğru akım özdirenç görüntüleme tekniği son otuz yıl içinde hem mekanik anlamda hem de edinilen bilgilerin işlenmesi anlamında oldukça gelişmiş ve gelişmeye devam etmektedir. Gelişme, daha çok elektrot ile mekanik yerdeğiştirmenin azaltılması ve buna bağlı olarak sayıca daha çok örnek alabilme yöntemlerinin iyileştirilmesi biçiminde olmaktadır. Görüntüleme tekniği, ya klasik anlamda merkezi bir anahtarlama sistemi ile yıldız bağlantı biçiminde ya da anahtarlamanın elektrotlar üzerine yapılmasına olanak sağlayacak dağılmış-akıllı elektrot olarak adlandırılan anahtarlama sistemleri ile yapılmaktadır. Arazi uygulamaları açısından her iki sistemin de bazı getirileri ve götürüleri vardır. Ancak kullanıcılar açısından arazi şartlarındaki en büyük etken sistemin toplam ağırlığı olmaktadır. Akıllı elektrot sistemleri kablo ağırlığını azalttığı için uzun hatlı ölçümlerde avantaj sağlayabilir. Hacettepe Üniversitesinde geliştirilen akıllı elektrot sistemi, benzeri olan merkezi anahtarlama sistemlerine göre yaklaşık %75 daha hafiftir. Sistem temelde küçük bir merkezi kontrol ünitesi, elektrotlar üzerine monte edilen akıllı elektrot üniteleri ve ana kablodan oluşmaktadır. Ana kablo içinden, ikisi girişim etkisine karşı yalıtımlı olan 6 adet kablo geçmektedir. Sistem, denetim ünitesine seri bağlanan bir dizüstü bilgisayar aracılığıyla denetlenmektedir. Sistemin kısa ve uzun profillerde denemeleri yapılmış, sorunsuz çalıştığı gözlenmiştir. Sistem, hafifliği nedeniyle özellikle uzun hatlı ölçümlerde büyük kolaylık sağlamaktadır, ayrıca bilgi giriş/çıkış ve tetikleme kapasitesine sahip her tür özdirenç aletine adapte edilebilir özelliktedir. Düşük sayıda kablodan oluşması nedeniyle çok kanallı ölçüm yapabilen bir sistem haline de dönüştürülmesi çalışmaları da yapılmaktadır.

Rapid and automated mineral identification is compulsory in certain applications concerning natural rocks. Among all microscopic and spectrometric methods, energy dispersive X-ray spectrometers (EDS) integrated with scanning electron microscopes produce rapid information with reliable chemical data. Although obtaining elemental data with EDS analyses is fast and easy by the help of improving technology, it is rather challenging to perform accurate and rapid identification considering the large quantity of minerals in a rock sample with varying dimensions ranging between nanometer to centimeter. Furthermore, the physical properties of the specimen (roughness, thickness, electrical conductivity, position in the instrument etc.) and the incident electron beam (accelerating voltage, beam current, spot size etc.) control the produced characteristic X-ray, which in turn affect the elemental analyses. In order to minimize the effects of these physical constraints and develop an automated m...

Fast and accurate mineral analysis became a necessity in all branches of science interested in rocks. Energy Dispersive X-ray Spectrometer (EDS) integrated with Scanning Electron Microscope (SEM) measures the energy of characteristic X-rays which are generated due to the excitation of the sample surface, thus calculates the element content under the spot. Obtaining elemental contents of a mineral using EDS is fast and easy however time required becomes longer when number of analyzed data increases. At the same time, accurate classification becomes difficult when similar elemental composition is similar in different mineral samples. In addition, the properties of the analyzed minerals (topography, electric conductivity) and electron beam (accelerating voltage, beam current, spot size etc.) can be different in each practice which affect the produced X-rays. These properties may vary from to study to study and make differences in elemental contents of the same mineral. Hence, fast and ...