Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
580 results
Search Results
Publication Metadata only 3D articulated shape segmentation using motion information(Institute of Electrical and Electronics Engineers (IEEE), 2010) Department of Computer Engineering; N/A; Yemez, Yücel; Kalafatlar, Emre; Faculty Member; Master Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; 107907; N/AWe present a method for segmentation of articulated 3D shapes by incorporating the motion information obtained from time-varying models. We assume that the articulated shape is given in the form of a mesh sequence with fixed connectivity so that the inter-frame vertex correspondences, hence the vertex movements, are known a priori. We use different postures of an articulated shape in multiple frames to constitute an affinity matrix which encodes both temporal and spatial similarities between surface points. The shape is then decomposed into segments in spectral domain based on the affinity matrix using a standard K-means clustering algorithm. The performance of the proposed segmentation method is demonstrated on the mesh sequence of a human actor.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 Open Access 3D face recognition by projection based methods(Society of Photo-optical Instrumentation Engineers (SPIE), 2006) Dutaǧaci, Helin; Sankur, Bülent; Department of Computer Engineering; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of EngineeringIn this paper, we investigate recognition performances of various projection-based features applied on registered 3D scans of faces. Some features are data driven, such as ICA-based features or NNMF-based features. Other features are obtained using DFT or DCT-based schemes. We apply the feature extraction techniques to three different representations of registered faces, namely, 3D point clouds, 2D depth images and 3D voxel. We consider both global and local features. Global features are extracted from the whole face data, whereas local features are computed over the blocks partitioned from 2D depth images. The block-based local features are fused both at feature level and at decision level. The resulting feature vectors are matched using Linear Discriminant Analysis. Experiments using different combinations of representation types and feature vectors are conducted on the 3D-RMA dataset.Publication Metadata only 3D isometric shape correspondence(IEEE, 2010) Department of Computer Engineering; Yemez, Yücel; Sahillioğlu, Yusuf; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; 107907; 215195We address the problem of correspondence between 3D isometric shapes. We present an automatic method that finds the optimal correspondence between two given (nearly) isometric shapes by minimizing the amount of deviation from isometry. We optimize the isometry error in two steps. In the first step, the 3D points uniformly sampled from the shape surfaces are transformed into spectral domain based on geodesic affinity, where the isometry errors are minimized in polynomial time by complete bipartite graph matching. The second step of optimization, which is well-initialized by the resulting correspondence of the first step, explicitly minimizes the isometry cost via an iterative greedy algorithm in the original 3D Euclidean space. Our method is put to test using (nearly) isometric pairs of shapes and its performance is measured via ground-truth correspondence information when available.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 progressive compression with octree particles(Akademische Verlagsgesellsch Aka Gmbh, 2002) Schmitt, Francis; Department of Computer Engineering; N/A; Yemez, Yücel; Faculty Member; Department of Computer Engineering; College of Engineering; N/A; 107907; N/AThis paper improves the storage efficiency of the progressive particle-based modeling scheme presented in [14, 15] by using entropy coding techniques. This scheme encodes the surface geometry and attributes in terms of appropriately ordered oc-tree particles, which can then progressively be decoded and rendered by the-viewer by means of a fast direct triangulation technique. With the introduced entropy coding technique, the bitload of the multi-level representation for geometry encoding reduces to 9-14 bits per particle (or 4.5-7 bits per triangle) for 12-bit quantized geometry.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 correspondence by isometry-driven greedy optimization(IEEE Computer Soc, 2010) 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; 107907We present an automatic method that establishes 3D correspondence between isometric shapes. Our goal is to find an optimal correspondence between two given (nearly) isometric shapes, that minimizes the amount of deviation from isometry. We cast the problem as a complete surface correspondence problem. Our method first divides the given shapes to be matched into surface patches of equal area and then seeks for a mapping between the patch centers which we refer to as base vertices. Hence the correspondence is established in a fast and robust manner at a relatively coarse level as imposed by the patch radius. We optimize the isometry cost in two steps. in the first step, the base vertices are transformed into spectral domain based on geodesic affinity, where the isometry errors are minimized in polynomial time by complete bipartite graph matching. the resulting correspondence serves as a good initialization for the second step of optimization in which we explicitly minimize the isometry cost via an iterative greedy algorithm in the original 3D Euclidean space. We demonstrate the performance of our method on various isometric (or nearly isometric) pairs of shapes for some of which the ground-truth correspondence is available.Publication Metadata only 3D Shape recovery and tracking from multi-camera video sequences via surface deformation(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.