Suleyman Demirci

Learn More
—It is well known in B-scan ground penetrating radar (GPR) imagery that the underground scatterers generally exhibit defocused, hyperbolic characteristics. This is mainly due to the data collection scheme and the finite beam width of the main lobe of the GPR antenna. To invert this undesirable effect and obtain focused images, various migration or focusing(More)
—Millimeter-wave (MMW) imaging is a powerful tool for the detection of objects concealed under clothing. Several factors including different kinds of objects, variety of covering materials and their thickness, accurate imaging of near-field scattered data affect the success of detection. To practice with such considerations, this paper presents the(More)
In the classical B-Scan ground penetrating radar (GPR), the collected data represented in the image domain, depict undesired hyperbolic effects and have low resolution features. In this work, we present frequency-wavenumber based Synthetic Aperture Radar (SAR) focusing technique to solve this problem. The formulation of algorithm is given and applied to(More)
A novel spatial domain image enhancement algorithm, in which dynamic range of the scene illumination is compressed from the human visual perspective to improve the visual quality and visibility in digital images captured under degraded visual conditions, is proposed. The proposed algorithm employs an adaptive approach so that local image statics, namely the(More)
The spectral matching, statistical and kernel based methods are the most widely known classification algorithms for hyperspectral imaging. Spectral matching algorithms try to identify the similarity of the unknown spectral signature of test pixels with the expected signature. In this study, an efficient spectral similarity method employing Multi-Scale(More)
In this study, an efficient spectral similarity method referred to as Weighted Chebyshev Distance (WCD) method is introduced for supervised classification of hyperspectral imagery (HSI) and target detection applications. The WCD is based on a simple spectral similarity based decision rule using limited amount of reference data. The estimation of upper and(More)
  • 1