Browsing by Keywords "Object recognition"

Now showing items 1-20 of 41

    • Automated detection of objects using multiple hierarchical segmentations 

      Akçay H. Gökhan; Aksoy, Selim (IEEE, 2007-07)
      We introduce an unsupervised method that combines both spectral and structural information for automatic object detection. First, a segmentation hierarchy is constructed by combining structural information extracted by ...

    • Automatic detection of geospatial objects using multiple hierarchical segmentations 

      Akçay, H. G.; Aksoy, S. (Institute of Electrical and Electronics Engineers, 2008-07)
      The object-based analysis of remotely sensed imagery provides valuable spatial and structural information that is complementary to pixel-based spectral information in classification. In this paper, we present novel methods ...

    • Color vision in humans and computers 

      Boyacı, Hüseyin; Akarun L. (IEEE, 2008)
      Humans and many other species rely on color for object recognition. What are the biological underpinnings of color vision and how can we computationally model human color perception? In this study we briefly summarize ...

    • Computationally efficient wavelet affine invariant functions for 2D object recognition 

      Bala, E.; Çetin, A. Enis (IEEE, 2003)
      In this paper, an affine invariant function is presented for object recognition from wavelet coefficients of the object boundary. In previous works, undecimated wavelet transform was used for affine invariant functions. ...

    • Computationally efficient wavelet affine invariant functions for shape recognition 

      Bala, E.; Çetin, A. Enis (IEEE, 2004)
      An affine invariant function for object recognition is constructed from wavelet coefficients of the object boundary. In previous works, undecimated dyadic wavelet transform was used to construct affine invariant functions. ...

    • Connectivity-guided adaptive lifting transform for image like compression of meshes 

      Köse, Kıvanç; Çetin, A. Enis; Güdükbay, Uğur; Onural, Levent (IEEE, 2007-05)
      We propose a new connectivity-guided adaptive wavelet transform based mesh compression framework. The 3D mesh is first transformed to 2D images on a regular grid structure by performing orthogonal projections onto the image ...

    • Çarpıcıdan bağımsız ortak fark matrisi kullanarak video ve görüntü işleme 

      Çetin, A. Enis; Duman, Kaan; Tuna, Hakan; Eryıldırım, Abdulkadir (IEEE, 2009-04)
      Bu bildiride gerçel sayılar üzerinde yarı grup kuran yeni bir iletmen tanımlayarak elde edilen bir bölge betimleyicisi ile hareketli obje takibi, yüz sezimi, plaka bulma, bölge betimleme için kullanılabilecek hızlı bir ...

    • The effect of task on cue usefulness for visual scene classification 

      Karaca, Meltem (Bilkent University, 2017-05)
      Detecting objects in the environment is one of the most fundamental functions of the visual system. Humans are highly effective at this, and past studies have shown that we can process things like whether or not an animal ...

    • Effects of surface reflectance and 3D shape on perceived rotation axis 

      Doerschner, K.; Yilmaz, O.; Kucukoglu, G.; Fleming, R. W. (Association for Research in Vision and Ophthalmology, 2013)
      Surface specularity distorts the optic flow generated by a moving object in a way that provides important cues for identifying surface material properties (Doerschner, Fleming et al., 2011). Here we show that specular flow ...

    • Estimation of depth fields suitable for video compression based on 3-D structure and motion of objects 

      Alatan, A. A.; Onural, L. (Institute of Electrical and Electronics Engineers, 1998-06)
      Intensity prediction along motion trajectories removes temporal redundancy considerably in video compression algorithms. In three-dimensional (3-D) object-based video coding, both 3-D motion and depth values are required ...

    • Eye tracking using markov models 

      Bağcı, A. M.; Ansari, R.; Khokhar, A.; Çetin, A. Enis (IEEE, 2004)
      We propose an eye detection and tracking method based on color and geometrical features of the human face using a monocular camera. In this method a decision is made on whether the eyes are closed or not and, using a Markov ...

    • Fine-grained object recognition and zero-shot learning in multispectral imagery 

      Sümbül, Gencer; Aksoy, Selim; Cinbiş, R. G. (IEEE, 2018)
      We present a method for fine-grained object recognition problem, that aims to recognize the type of an object among a large number of sub-categories, and zero-shot learning scenario on multispectral images. In order to ...

    • Fine-grained object recognition and zero-shot learning in remote sensing imagery 

      Sümbül, Gencer; Cinbis, R. G.; Selim Aksoy (Institute of Electrical and Electronics Engineers, 2018)
      Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional ...

    • Flame detection in video using hidden Markov models 

      Töreyin, B. Uğur; Dedeoğlu, Yiğithan; Çetin, A. Enis (IEEE, 2005)
      This paper proposes a novel method to detect flames in video by processing the data generated by an ordinary camera monitoring a scene. In addition to ordinary motion and color clues, flame flicker process is also detected ...

    • Fractional fourier transform pre-processing for neural networks and its application to object recognition 

      Barshan, Billur; Ayrulu, Birsel (Elsevier, 2002-01)
      This study investigates fractional Fourier transform pre-processing of input signals to neural networks. The fractional Fourier transform is a generalization of the ordinary Fourier transform with an order parameter a. ...

    • Haber videolarında nesne tanıma ve otomatik etiketleme 

      Baştan, Muhammet; Duygulu, Pınar (IEEE, 2006-04)
      We propose a new approach to object recognition problem motivated by the availability of large annotated image and video collections. Similar to translation from one language to another, this approach considers the object ...

    • İmge işleme yoluyla çubuk kod yersenimi 

      Öktem, R.; Çetin, A. Enis (IEEE, 2005-05)
      Bu özette imge işleme kullanılarak çubuk kod bölgesi çıkarımı ele alınmıştır. Çubuk kodlar birbirine paralel açık-koyu doğrulardan oluştuklarından, ikili bir ayrıt haritasında da belirli bir oryantasyonda birbirine bağlı ...

    • Man-made object classification in SAR images using 2-D cepstrum 

      Eryildirim, A.; Çetin, A. Enis (IEEE, 2009-05)
      In this paper, a novel descriptive feature parameter extraction method from Synthetic Aperture Radar (SAR) images is proposed. The new method is based on the two-dimensional (2-D) real cepstrum. This novel 2-D cepstrum ...

    • Mining web images for concept learning 

      Golge, Eren (Bilkent University, 2014-08)
      We attack the problem of learning concepts automatically from noisy Web image search results. The idea is based on discovering common characteristics shared among category images by posing two novel methods that are able ...

    • Modeling interaction of fluid, fabric, and rigid objects for computer graphics 

      Bayraktar, Serkan; Güdükbay, Uğur; Özgüç, Bülent (IEEE, 2006)
      Simulating every day phenomena such as fluid, rigid objects, or cloth and their interaction has been a challenge for the computer graphics community for decades. In this article techniques to model such interactions are ...