Yazar "Ozturk, Ali" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    A clinically feasible kinematic assessment method of upper extremity motor function impairment after stroke
    (Elsevier Sci Ltd, 2016) Ozturk, Ali; Tartar, Ahmet; Huseyinsinoglu, Burcu Ersoz; Ertas, Ahmet H.
    The development of feasible kinematic assessment methods of upper extremity motor function impairment after stroke is clinically extremely important in physiotherapy and rehabilitation engineering. Microsoft Kinect has a potential of a low-cost and compact solution for clinical based assessment of the upper limb motor function after stroke. However, the reliability of Microsoft Kinect in the upper limb motor function assessment has not been well established. Therefore, there is a hesitation in usage of Microsoft Kinect for clinical applications. It is expected that any measurement procedure has the capability to differentiate between pathological and normal performance. On the other hand, the identification of the kinematic metrics that best evaluate impairment of upper-extremity motor function is a key problem of any measurement protocol. Primary objective of our study is, by differentiating pathological performance from the healthy performance and identifying the kinematic metrics that best evaluate the impairment, to demonstrate the robustness/usability of Microsoft Kinect in kinematic analysis of motor performance of stroke patients. We compared the kinematic metrics of the forward reaching movement obtained data recorded from Microsoft Kinect between three stroke patients and two healthy subjects based on the Principal Component Analysis (PCA). In the study, we have defined a new inter-joint coordination index (IJCI) based on PCA to capture inter-joint coordination dynamic of reaching movement in addition to other metrics those have been previously defined and used in literature to quantify upper limb impairment. We observed that the IJCI has significant importance to detect impairment of upper-extremity motor function during a forward reaching task and to discriminate stroke patients from healthy controls. We hope that this paper will promote the acceptance of objective kinematic analysis into routine rehabilitation practices. (C) 2015 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Performance of Interpolated Histogram of Oriented Gradients on the Feature Calculation of SIFT
    (Univ Suceava, Fac Electrical Eng, 2022) Ozturk, Ali; Cayiroglu, Ibrahim
    Scale Invariant Feature Transform (SIFT) is the most dominant and robust object detection algorithm. It utilizes the Histogram of Oriented Gradients (HOG) method for feature computation. HOG is applied with trilinear interpolation to gain performance improvement. This paper examines the effect of interpolation on the performance of SIFT on both OXFORD and HPatches datasets. The various algorithms of interpolation for HOG, and the spatial binning process algorithm, are presented here. The performance is evaluated with Intersection Over Union, Correct Match Percentage, as well as the execution time of the algorithms. Moreover, we used the multiplication of the Intersection Over Union and Correct Match Percentage to take advantage of both metrics. It was observed that the interpolation did not significantly affect the performance of the SIFT.
  • Küçük Resim Yok
    Öğe
    A Real-Time Application of Singular Spectrum Analysis to Object Tracking with SIFT
    (Eos Assoc, 2022) Ozturk, Ali; Cayiroglu, Ibrahim
    This study combined SIFT and SSA to propose a novel algorithm for real-time object tracking. The proposed algorithm utilizes an intermediate fixed-size buffer and a modified SSA algorithm. Since the complete reconstruction step of the SSA algorithm was unnecessary, it was considerably simplified. In addition, the execution time of a Matlab implementation of the SSA algorithm was compared with a respective C++ implementation. Moreover, the performance of the two different matching algorithms in the detection, the FlannBasedMatcher and Brute-Force matcher algorithms of the OpenCV library, was compared.