Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
149 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Metadata only 3D face recognition(Institute of Electrical and Electronics Engineers (IEEE), 2006) Dutaǧaci, H.; Sankur, B.; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907In this paper, we compare face recognition performances of various features applied on registered 3D scans of faces. The features we compare are DFT or DCT- based features, ICA-based features and NNMF-based features. We apply the feature extraction techniques to three different representations of registered faces: 3D point clouds, 2D depth images and 3D voxel representations. We also consider block-based DFT or DCT-based local features on 2D depth images and their fusion schemes. Experiments using different combinations of representation types and feature vectors are conducted on the 3D-RMA dataset. / Bu bildiride, kayıtlı 3B yüz taramalarında uygulanan çeşitli özelliklerin yüz tanıma performanslarını karşılaştırıyoruz. Karşılaştırdığımız özellikler, DFT veya DCT tabanlı özellikler, ICA tabanlı özellikler ve NNMF tabanlı özelliklerdir. Öznitelik çıkarma tekniklerini kayıtlı yüzlerin üç farklı temsiline uyguluyoruz: 3B nokta bulutları, 2B derinlik görüntüleri ve 3B voksel temsilleri. Ayrıca, 2D derinlik görüntüleri ve bunların füzyon şemaları üzerindeki blok tabanlı DFT veya DCT tabanlı yerel özellikleri de dikkate alıyoruz. 3D-RMA veri seti üzerinde farklı temsil türleri ve özellik vektörleri kombinasyonları kullanılarak deneyler yapılmıştır.Publication Metadata only 3D model retrieval using probability density-based shape descriptors(IEEE Computer Society, 2009) Akgul, Ceyhun Burak; Sankur, Buelent; Schmitt, Francis; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907We address content-based retrieval of complete 3D object models by a probabilistic generative description of local shape properties. The proposed shape description framework characterizes a 3D object with sampled multivariate probability density functions of its local surface features. This density-based descriptor can be efficiently computed via kernel density estimation (KDE) coupled with fast Gauss transform. The nonparametric KDE technique allows reliable characterization of a diverse set of shapes and yields descriptors which remain relatively insensitive to small shape perturbations and mesh resolution. Density-based characterization also induces a permutation property which can be used to guarantee invariance at the shape matching stage. As proven by extensive retrieval experiments on several 3D databases, our framework provides state-of-the-art discrimination over a broad and heterogeneous set of shape categories.Publication Metadata only 3D object matching via multivariate shape distributions(Institute of Electrical and Electronics Engineers (IEEE), 2005) Akgül, C.B.; Sankur, B.; Schmitt, F.; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of Engineering; 1079073B nesne eşleştirme literatüründe, problemi şekil dağılımlarının karşılaştırılmasına indirgeyen yöntemler bulunmaktadır. Şekil dağılımı, 3B nesne yüzeyi üzerinde hesaplanan bir işlevin değerlerinin olasılık dağılımı olarak tanımlanır. Bu çalışmada varolan yöntemi, birden çok işlevin getirdiği şekil bilgisinden aynı anda yararlanacak şekilde genişletiyoruz. Çokboyutlu şekil dağılımları adını verdiğimiz bu 3B nesne betimleyicilerini, örnek bir 3B nesne veri tabanındaki nesneler için parametrik olmayan yaklaşımlarla kestiriyor, karşılaştırmaları alternatif metrikler yoluyla yapıyoruz. Elde edilen kesinlik-geri getirme eğrileri çokboyutlu şekil dağılımlarının karşılaştırılmasının yeni bir 3B nesne eşleştirme paradigması olabileceğini göstermektedir.Publication Metadata only 3D reconstruction of real objects with high resolution shape and texture(Elsevier, 2004) Schmitt, F; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907We present a robust and accurate system for 3D reconstruction of real objects with high resolution shape and texture. Our reconstruction method is passive, the only information needed being 2D images obtained with a calibrated camera from different view angles as the object rotates on a turntable. The triangle surface model is obtained by a scheme combining octree construction and marching cubes algorithm, which is adapted to the shape from silhouette problem. We develop a texture mapping strategy based on surface particles to adequately address photography related problems such as inhomogeneous lighting, highlights and occlusion. Reconstruction results are included to demonstrate the attained quality.Publication Metadata only 3D shape recovery and tracking from multi-camera video sequences via surface deformation(Institute of Electrical and Electronics Engineers (IEEE), 2006) Skala, V.; N/A; Department of Computer Engineering; Sahillioğlu, Yusuf; Yemez, Yücel; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; 215195; 107907This paper addresses 3D reconstruction and modeling of time-varying real objects using multicamera video. The work consists of two phases. In the first phase, the initial shape of the object is recovered from its silhouettes using a surface deformation model. The same deformation model is also employed in the second phase to track the recovered initial shape through the time-varying silhouette information by surface evolution. The surface deformation/evolution model allows us to construct a spatially and temporally smooth surface mesh representation having fixed connectivity. This eventually leads to an overall space-time representation that preserves the semantics of the underlying motion and that is much more efficient to process, to visualize, to store and to transmit. / Bu makale, çok kameralı video kullanarak zamanla değişen gerçek nesnelerin 3B yeniden yapılandırılmasını ve modellenmesini ele almaktadır. Çalışma iki aşamadan oluşmaktadır. İlk aşamada, nesnenin ilk şekli, bir yüzey deformasyon modeli kullanılarak silüetlerinden kurtarılır. Aynı deformasyon modeli, ikinci aşamada, yüzey evrimi yoluyla zamanla değişen siluet bilgisi yoluyla geri kazanılan ilk şekli izlemek için de kullanılır. Yüzey deformasyonu/evrimi modeli, sabit bağlantıya sahip uzamsal ve zamansal olarak pürüzsüz bir yüzey ağ temsili oluşturmamıza izin verir. Bu, sonunda, altta yatan hareketin anlamını koruyan ve işlemesi, görselleştirmesi, depolaması ve iletmesi çok daha verimli olan genel bir uzay-zaman temsiline yol açar.Publication Metadata only A chain-binomial model for pull and push-based information diffusion(IEEE, 2006) Department of Mathematics; Department of Computer Engineering; Çağlar, Mine; Özkasap, Öznur; Faculty Member; Faculty Member; Department of Mathematics; Department of Computer Engineering; College of Sciences; College of Engineering; 105131; 113507We compare pull and push-based epidemic paradigms for information diffusion in large scale networks. Key benefits of these approaches are that they are fully distributed, utilize local information only via pair-wise interactions, and provide eventual consistency, scalability and communication topology-independence, which make them suitable for peer-to-peer distributed systems. We develop a chain-Binomial epidemic probability model for these algorithms. Our main contribution is the exact computation of message delivery latency observed by each peer, which corresponds to a first passage time of the underlying Markov chain. Such an analytical tool facilitates the comparison of pull and push-based spread for different group sizes, initial number of infectious peers and fan-out values which are also accomplished in this study. Via our analytical stochastic model, we show that push-based approach is expected to facilitate faster information spread both for the whole group and as experienced by each member.Publication Metadata only A classification and performance comparison of mobility models for ad hoc networks(Springer-Verlag Berlin, 2006) N/A; Department of Computer Engineering; Atsan, Emre; Özkasap, Öznur; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 113507In mobile ad hoc network research, simulation plays an important role in determining the network characteristics and measuring performance. On the other hand, unrealistic simulation conditions may be misleading, instead of being explanatory. For this reason, constructing simulation models closer to the real circumstances is very significant. Movement behavior of mobile entities is one of the most important concepts for the realistic simulation scenarios in mobile ad hoc networks. In this study, we first provide a survey and a new hybrid classification of existing mobility models in the literature. We implemented the random direction and boundless simulation area models on Scalable Wireless Ad Hoc Network Simulator (SWANS) and conducted simulations of Ad Hoc On-Demand Distance Vector (AODV) protocol for these as well as the random walk and random waypoint models. Our comparative results for the mobility models are discussed on a variety of simulation settings and parameters.Publication Metadata only A classification of concurrency bugs in java benchmarks by developer intent(Association for Computing Machinery (ACM), 2006) Department of Computer Engineering; Department of Computer Engineering; N/A; Keremoğlu, M. Erkan; Taşıran, Serdar; Elmas, Tayfun; Researcher; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; N/A; N/A; N/AThis work addresses the issue of selecting the formal correctness criterion for a concurrent Java program that best corresponds to the developer's intent. We study a set of concurrency-related bugs detected in Java benchmarks reported in the literature. On these programs, we determine whether race-freedom, atomicity or refinement is the simplest and most appropriate criterion for program correctness. Our purpose is to demonstrate empirically the fact that the appropriate fix for a concurrency error and the selection of a program analysis tool for detecting such an error must be based on the proper expression of the designer's intent using a formal correctness criterion.Publication Metadata only A combined interval and floating-point comparator/selector(IEEE Computer Soc, 2002) Department of Computer Engineering; Akkaş, Ahmet; Faculty Member; Department of Computer Engineering; College of Engineering; N/AInterval arithmetic provides a robust method for automatically monitoring numerical errors and can be used to solve problems that cannot be efficiently solved with floating-point arithmetic. This paper presents the design and implementation of a combined interval and floating-point comparator/selector, which performs interval intersection, hull, mignitude, magnitude, minimum, maximum, and comparisons, As well as floating-point minimum, maximum and comparisons. area and delay estimates indicate that the combined interval and floating-point comparator/selector has 98% more area and a worst case delay that is 42% greater than a conventional floating point comparator/selector. the combined interval and floating-point comparator/selector greatly improves the performance of interval selection operations.Publication Metadata only A comparison of data representation types, feature types and fusion techniques for 3D face biometry(European Association for Signal Processing, 2006) Dutaǧaci, H.; Sankur, B.; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907This paper focuses on the problems of person identification and authentication using registered 3D face data. The face surface geometry is represented alternately as a point cloud, a depth image or as voxel data. Various local or global feature sets are extracted, such as DFT/DCT coefficients, ICA- and NMF- projections, which results in a rich repertoire of representations/features. The identification and authentication performance of the individual schemes are compared. Fusion schemes are invoked, to improve the performance especially in the case when there are only few samples per subject.