WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7150

Browse

Filters

2008 - 200912010 - 20132

Settings

Access Right: Closed AccessAuthor: search.filters.author.Gümüştekin, Şevket

Search Results

Now showing 1 - 3 of 3
  • Conference Object
    Detection of Urban Change Using Remote Sensing and Gis: Izmir Case
    (Taylor and Francis Ltd., 2008) Tarhan, Çiğdem; Arkon, Cemal; Çelik, M.; Gümüştekin, Şevket; Tecim, V.
    This study is an example of how land use changes could be detected via high resolution remotely sensed data. In order to perform "change detection" IKONOS satellite images, belonging to 2001 and 2004, have been used. An automated Graphical User Interface (GUI) has been created for detection of environment. Different image enhancement techniques and a fuzzy inference system have been combined in the GUI. The detection results are classified according to some basic levels such as 20-50% and 70%. Additionally, four different change detection algorithms have been applied which are pixel-based, object based, feature based. These algorithms have been examined according to change detection levels with different image enhancement techniques. At the end of the study, the results have been compared.
  • Conference Object
    Citation - WoS: 2
    Enhancing Stereo Matching Performance by Using Polarization Images
    (Institute of Electrical and Electronics Engineers Inc., 2013) Ozan, Şükrü; Gümüştekin, Şevket
    Finding depth information from a scene by using stereo imaging is a widely used and effective method. But surface reflection properties of subjects in the scene, possible change in relative camera and light source locations have a negative effect on stereo matching performance in scenes where the specular reflection is evident. In this study the situations where the specular reflections in the scenes disturbs stereo matching performance are highlighted and the solution of this problem by using polarization imaging methods is examined.
  • Conference Object
    A Bayesian Approach for Licence Plate Recognition Developed on a Realistic Simulation Environment
    (Institute of Electrical and Electronics Engineers Inc., 2013) Efeler, Mahmut Cenk; Altınkaya, Mustafa Aziz; Gümüştekin, Şevket
    Template matching is one of the most common methods for license plate recognition. This method discards prior probabilities of license plate codes. The posterior code class probabilities constructed by including the prior probability information are expected to improve the recognition performance. The probability information that needs to be included requires extensive training data, which is quite costly to obtain. In order to generate these training images a license plate image simulator is developed with a realistic noise model. Simulated license plate images are then used to test a Bayesian decision theory based recognition procedure. Test results indicate that, with the inclusion of prior information, significant recognition gain is obtained with respect to standard template matching method at high noise levels.