Research Outputs

Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2

Browse

Search Results

Now showing 1 - 10 of 14
  • Placeholder
    Publication
    3D face recognition
    (Institute of Electrical and Electronics Engineers (IEEE), 2006) DutaĒ§aci, H.; Sankur, B.; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907
    In 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 yĆ¼z taramalarında uygulanan Ƨeşitli ƶzelliklerin yĆ¼z tanıma performanslarını karşılaştırıyoruz. Karşılaştırdığımız ƶzellikler, DFT veya DCT tabanlı ƶzellikler, ICA tabanlı ƶzellikler ve NNMF tabanlı ƶzelliklerdir. Ɩznitelik Ƨıkarma tekniklerini kayıtlı yĆ¼zlerin Ć¼Ć§ farklı temsiline uyguluyoruz: 3B nokta bulutları, 2B derinlik gƶrĆ¼ntĆ¼leri ve 3B voksel temsilleri. Ayrıca, 2D derinlik gƶrĆ¼ntĆ¼leri ve bunların fĆ¼zyon şemaları Ć¼zerindeki blok tabanlı DFT veya DCT tabanlı yerel ƶzellikleri de dikkate alıyoruz. 3D-RMA veri seti Ć¼zerinde farklı temsil tĆ¼rleri ve ƶzellik vektƶrleri kombinasyonları kullanılarak deneyler yapılmıştır.
  • Placeholder
    Publication
    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, YĆ¼cel; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; 215195; 107907
    This 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, Ƨok kameralı video kullanarak zamanla değişen gerƧek nesnelerin 3B yeniden yapılandırılmasını ve modellenmesini ele almaktadır. Ƈalışma iki aşamadan oluşmaktadır. Ä°lk aşamada, nesnenin ilk şekli, bir yĆ¼zey deformasyon modeli kullanılarak silĆ¼etlerinden kurtarılır. Aynı deformasyon modeli, ikinci aşamada, yĆ¼zey evrimi yoluyla zamanla değişen siluet bilgisi yoluyla geri kazanılan ilk şekli izlemek iƧin de kullanılır. YĆ¼zey deformasyonu/evrimi modeli, sabit bağlantıya sahip uzamsal ve zamansal olarak pĆ¼rĆ¼zsĆ¼z bir yĆ¼zey ağ temsili oluşturmamıza izin verir. Bu, sonunda, altta yatan hareketin anlamını koruyan ve işlemesi, gƶrselleştirmesi, depolaması ve iletmesi Ƨok daha verimli olan genel bir uzay-zaman temsiline yol aƧar.
  • Placeholder
    Publication
    A new computational framework for 3D shape descriptors
    (Institute of Electrical and Electronics Engineers (IEEE), 2006) AkgĆ¼l, C.B.; Sankur B., Schmitt F.; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907
    In this work, we propose a computational framework for histogram-based 3D shape descriptors. Our method is based on evaluating the density of a shape function defined over the surface of 3D model using Gaussian modeling. The proposed approach has a better shape description ability compared to other competitor histogram-based approaches. We illustrate this assertion in a content-based 3D model retrieval application. / Bu Ƨalışmada, histogram tabanlı 3B şekil tanımlayıcıları iƧin hesaplamalı bir ƧerƧeve ƶneriyoruz. Metodumuz, Gauss modellemesi kullanılarak 3B modelin yĆ¼zeyi Ć¼zerinde tanımlanan bir şekil fonksiyonunun yoğunluğunun değerlendirilmesine dayanmaktadır. Ɩnerilen yaklaşım, diğer rakip histogram tabanlı yaklaşımlara kıyasla daha iyi bir şekil tanımlama yeteneğine sahiptir. Bu iddiayı iƧerik tabanlı bir 3B model alma uygulamasında gƶsteriyoruz.
  • Thumbnail Image
    PublicationOpen Access
    Augmented tabletop role-playing game with movement-based gameplay and arm-worn devices
    (Association for Computing Machinery (ACM), 2017) Department of Computer Engineering; Buruk, Oğuz Turan; Ɩzcan, Oğuzhan; Ɩzbeyli, Ä°smet Melih; Faculty Member; Department of Computer Engineering; KU ArƧelik Research Center for Creative Industries (KUAR) / KU ArƧelik Yaratıcı EndĆ¼striler Uygulama ve Araştırma Merkezi (KUAR); College of Engineering; N/A; 12532; N/A
    Augmenting table-top role-playing games (TTRPG) is a trending subject in game research. Different objects and interaction modalities such as surface displays, tangible devices or interactive rooms are used for the augmentation of TTRPG. Still, usage of wearable devices and movement-based gameplay in such games is a rather underexplored area although they have a potential for enhancing the player experience according to the previous studies. To delve into this area, we developed a new interactive environment comprised of arm-worn devices and an augmented die. These devices, together with a new role-playing game system, facilitate movement-based gameplay which encourage players to enact their characters with their bodies. In this paper, we explained the specifications of this gaming environment and our demonstration setting.
  • Placeholder
    Publication
    Boosting classifiers for music genre classification
    (Institute of Electrical and Electronics Engineers (IEEE), 2006) N/A; Department of Computer Engineering; Bağcı, Ulaş; Erzin, Engin; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 34503
    This paper investigates discriminative boosting of classifiers to improve the automatic music genre classification performance. Two classifier structures, boosting of the Gaussian mixture model based classifiers and classifiers that are using the inter-genre similarity information, are proposed. The first classifier structure presents a novel extension to the maximum-likelihood based training of the Gaussian mixtures to integrate GMM classifier into boosting architecture. In the second classifier structure, the boosting idea is modified to better model the intergenre similarity information over the mis-classified feature population. Once the inter-genre similarities are modeled, elimination of the inter-genre similarities reduces the inter-genre confusion and improves the identification rates. A hierarchical auto-clustering classifier scheme is integrated into the inter-genre similarity modeling. Experimental results with promising classification improvements are provided. / Ɩz: Bu makale, otomatik mĆ¼zik tĆ¼rĆ¼ sınıflandırma performansını iyileştirmek iƧin sınıflandırıcıların ayrımcı gĆ¼Ć§lendirmesini araştırmaktadır. Gauss karışım modeli tabanlı sınıflandırıcıların ve tĆ¼rler arası benzerlik bilgisini kullanan sınıflandırıcıların gĆ¼Ć§lendirilmesi olmak Ć¼zere iki sınıflandırıcı yapısı ƶnerilmiştir. Ä°lk sınıflandırıcı yapısı, GMM sınıflandırıcısını gĆ¼Ć§lendirme mimarisine entegre etmek iƧin Gauss karışımlarının maksimum olabilirliğe dayalı eğitimine yeni bir uzantı sunar. Ä°kinci sınıflandırıcı yapısında, tĆ¼rler arası benzerlik bilgisini yanlış sınıflandırılmış ƶzellik popĆ¼lasyonu Ć¼zerinde daha iyi modellemek iƧin artırma fikri değiştirilir. TĆ¼rler arası benzerlikler modellendikten sonra, tĆ¼rler arası benzerliklerin ortadan kaldırılması tĆ¼rler arası karışıklığı azaltır ve tanımlama oranlarını artırır. Hiyerarşik bir otomatik kĆ¼meleme sınıflandırıcı şeması, tĆ¼rler arası benzerlik modellemesine entegre edilmiştir. Umut verici sınıflandırma iyileştirmeleri ile deneysel sonuƧlar sağlanmıştır.
  • Placeholder
    Publication
    Comparative lip motion analysis for speaker identification
    (Institute of Electrical and Electronics Engineers (IEEE), 2005) Department of Computer Engineering; Department of Computer Engineering; Department of Electrical and Electronics Engineering; N/A; Yemez, YĆ¼cel; Erzin, Engin; Tekalp, Ahmet Murat; ƇetingĆ¼l, Hasan Ertan; Faculty Member; Faculty Member; Faculty Member; Master Student; Department of Computer Engineering; Department of Electrical and Electronics Engineering; College of Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; 107907; 34503; 26207; N/A
    The aim of this work is to determine the best lip analysis system, thus the most accurate lip motion features for audio-visual open-set speaker identification problem. Based on different analysis points on the lip region, two alternatives for initial lip motion representation is considered. In the first alternative, the feature vector is composed of the 2D-DCT coefficients of the motion vectors estimated within the rectangular mouth region whereas in the second, outer lip boundaries are tracked over the video frames and only the motion vectors around the lip contour are taken into account along with the shape of the lip boundary. Another comparison has been performed between optical flow and block-matching motion estimation methods to find the best model for lip movement. The dimension of the obtained lip feature vector is then reduced by a two-stage discrimination method selecting the most discriminative lip features. An HMM-based identification system has been used for performance comparison of these motion representations. It is observed that the lower-dimensional feature vector computed by block-matching within a rectangular grid in the lip region maximizes the identification performance. /Bu Ƨalışmanın amacı, gƶrsel-işitsel aƧık set konuşmacı tanıma problemi iƧin en iyi dudak analiz sistemini, dolayısıyla en doğru dudak hareketi ƶzelliklerini belirlemektir. Dudak bƶlgesindeki farklı analiz noktalarına dayalı olarak, başlangıƧ dudak hareketi gƶsterimi iƧin iki alternatif gƶz ƶnĆ¼nde bulundurulur. Birinci alternatifte ƶznitelik vektƶrĆ¼ dikdƶrtgen ağız bƶlgesi iƧinde tahmin edilen hareket vektƶrlerinin 2D-DCT katsayılarından oluşurken, ikinci alternatifte dış dudak sınırları video kareleri Ć¼zerinden izlenir ve sadece dudak konturu etrafındaki hareket vektƶrleri izlenir. dudak sınırının şekli ile birlikte dikkate alınır. Dudak hareketi iƧin en iyi modeli bulmak iƧin optik akış ve blok eşleştirme hareket tahmin yƶntemleri arasında başka bir karşılaştırma yapılmıştır. Elde edilen dudak ƶzelliği vektƶrĆ¼nĆ¼n boyutu daha sonra en ayırt edici dudak ƶzelliklerini seƧen iki aşamalı bir ayrım yƶntemiyle azaltılır. Bu hareket gƶsterimlerinin performans karşılaştırması iƧin HMM tabanlı bir tanımlama sistemi kullanılmıştır. Dudak bƶlgesinde dikdƶrtgen bir grid iƧerisinde blok eşleştirme ile hesaplanan alt boyutlu ƶzellik vektƶrĆ¼nĆ¼n tanımlama performansını maksimuma Ƨıkardığı gƶrĆ¼lmektedir.
  • Placeholder
    Publication
    Feature-level and descriptor-level information fusion for density-based 3D shape descriptors
    (IEEE, 2007) AkgĆ¼l C.B.; Sankur B.; Schmitt F.; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of Engineering; 107907
    We address the 3D object retrieval problem using density-based shape descriptors. We explore first and second order local surface features and their multivariate combinations in the density estimation framework. We also experiment with descriptor level information fusion. The results, obtained using two different databases, Princeton Shape Benchmark and Sculpteur, show that, boosted with both feature level and descriptor level information fusion, the density-based shape description framework enables effective and efficient 3D object retrieval.
  • Thumbnail Image
    PublicationOpen Access
    GestAnalytics: experiment and analysis tool for gesture-elicitation studies
    (Association for Computing Machinery (ACM), 2017) Department of Computer Engineering; Buruk, Oğuz Turan; Ɩzcan, Oğuzhan; Faculty Member; Department of Computer Engineering; KU ArƧelik Research Center for Creative Industries (KUAR) / KU ArƧelik Yaratıcı EndĆ¼striler Uygulama ve Araştırma Merkezi (KUAR); College of Engineering; N/A; 12532
    Gesture-elicitation studies are common and important studies for understanding user preferences. In these studies, researchers aim at extracting gestures which are desirable by users for different kinds of interfaces. During this process, researchers have to manually analyze many videos which is a tiring and a time consuming process. Although current tools for video analysis provide annotation opportunity and features like automatic gesture analysis, researchers still need to (1) divide videos into meaningful pieces, (2) manually examine each piece, (3) match collected user data with these, (4) code each video and (5) verify their coding. These processes are burdensome and current tools do not aim to make this process easier and faster. To fill this gap, we developed ā€œGestAnalyticsā€ with features of simultaneous video monitoring, video tagging and filtering. Our internal pilot tests show that GestAnalytics can be a beneficial tool for researchers who practice video analysis for gestural interfaces.
  • Placeholder
    Publication
    Inter genre similarity modeling for automatic music genre classification
    (Institute of Electrical and Electronics Engineers (IEEE), 2006) N/A; Department of Computer Engineering; Bağcı, Ulaş; Erzin, Engin; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 34503
    Two important problems of the automatic music genre classification are feature extraction and classifier design. This paper investigates inter-genre similarity modeling (IGS) to improve the automatic music genre classification performance. Intergenre similarity information is extracted over the mis-classified feature population. Once the inter-genre similarity is modeled, elimination of the inter-genre similarity reduces the inter-genre confusion and improves the identification rates. Inter-genre similarity modeling is further improved with iterative IGS modeling and score modeling for IGS elimination. Experimental results with promising classification improvements are provided. / Ɩz: Otomatik mĆ¼zik tĆ¼rĆ¼ sınıflandırmasının iki ƶnemli sorunu, ƶzellik Ƨıkarımı ve sınıflandırıcı tasarımıdır. Bu makale, otomatik mĆ¼zik tĆ¼rĆ¼ sınıflandırma performansını iyileştirmek iƧin tĆ¼rler arası benzerlik modellemesini (IGS) araştırmaktadır. TĆ¼rler arası benzerlik bilgisi, yanlış sınıflandırılmış ƶzellik popĆ¼lasyonu Ć¼zerinden Ƨıkarılır. TĆ¼rler arası benzerlik modellendikten sonra, tĆ¼rler arası benzerliğin ortadan kaldırılması, tĆ¼rler arası karışıklığı azaltmakta ve tanımlama oranlarını iyileştirmektedir. TĆ¼rler arası benzerlik modellemesi, yinelemeli IGS modellemesi ve IGS'nin ortadan kaldırılması iƧin puan modellemesi ile daha da geliştirildi. Umut verici sınıflandırma iyileştirmeleri ile deneysel sonuƧlar sağlanmıştır.
  • Placeholder
    Publication
    Learning morphological disambiguation rules for Turkish
    (Association for Computational Linguistics (ACL), 2006) Department of Computer Engineering; Department of Computer Engineering; TĆ¼re, Ferhan; YĆ¼ret, Deniz; Undergraduate Student; Faculty Member; Department of Computer Engineering; College of Engineering; College of Engineering; N/A; 179996
    In this paper, we present a rule based model for morphological disambiguation of Turkish. The rules are generated by a novel decision list learning algorithm using supervised training. Morphological ambiguity (e.g. lives = live+s or life+s) is a challenging problem for agglutinative languages like Turkish where close to half of the words in running text are morphologically ambiguous. Furthermore, it is possible for a word to take an unlimited number of suffixes, therefore the number of possible morphological tags is unlimited. We attempted to cope with these problems by training a separate model for each of the 126 morphological features recognized by the morphological analyzer. The resulting decision lists independently vote on each of the potential parses of a word and the final parse is selected based on our confidence on these votes. The accuracy of our model (96%) is slightly above the best previously reported results which use statistical models. For comparison, when we train a single decision list on full tags instead of using separate models on each feature we get 91% accuracy.