Maestría en Ingeniería Electrónica

Permanent URI for this collection

https://vitela.javerianacali.edu.co/handle/11522/583

Browse

Browsing Maestría en Ingeniería Electrónica by Subject "Twitter"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Perceptual Quality Assessment of Pan-sharpened Images
    (Pontificia Universidad Javeriana, 2018) Agudelo Medina, Oscar Andrés; Benítez Restrepo, Hernán Darío
    Pan-sharpening (PS) is an approach to fuse the spatial details of a high-resolution panchromatic (PAN) image and the spectral information of a low- resolution multispectral (MS) image. PS is a preliminary step for enhancing images for remote sensing tasks, such as change detection, object recognition, visual image analysis, and scene interpretation. Given the need for selecting pan-sharpening techniques that provide better spatial and spectral quality of pan-sharpened images, it is highly desirable to be able to automatically and accurately predict pan-sharpened image quality, as would be perceived and reported by human beings and evaluating at the same time spectral distortions as color changes in the PS image. In this research we propose a new image quality assessment (IQA) measure that uses the statistics of natural images, commonly referred to as natural scene statistics (NSS) to extract statistical regularities from PS images. NSS are measurably modified by the presence of distortions, we take advantage of this behavior to characterize some relevant distortions presented in PS images. We analyze six PS methods in the presence of two common distortions, blur, and white noise, on PAN images. Furthermore, we conducted a human study on the subjective quality of pristine and degraded PS images and created a completely blind fused image quality analyzer. In this test, 33 subjects evaluated 420 images in five sessions. In addition, we propose an opinion aware fused image quality analyzer, whose relative predictions with respect to other models match better to human perceptual evaluations than state-of-the-art reduced and full resolution quality metrics. An implementation of the results of subjective study and the proposed fused image quality measures can be found at https://github.com/oscaragudelom/Pansharpening-IQA.
  • No Thumbnail Available
    Item
    Towards an Algorithmic Selection of Spreaders in Twitter
    (Pontificia Universidad Javeriana, 2018) Duque Marín, Arturo; Rocha, Camilo
    This research empirically studies mechanisms and criteria for selecting spreaders in Twitter. Spreaders are users capable of disseminating information to large portions of the network, whether they are considered in uentials or not. This work is an initial approximation in which the Twitter social network is represented as a network and the selection mechanisms exploit its structural properties to nd suitable spreaders. Because the selection depends on di erent mechanisms (e.g. algorithmic, manual, and random selection), a comparison of the distinct features they generate, such as cost and coverage, is investigated. The cost of a spreader is assumed proportional to the coverage potential, that is, the larger the coverage potential, the greater the cost. The cost associated with the selection mechanism is the sum of the coverage potentials of all the selected initial spreaders. This work models, simulates and analyzes how di erent structural properties that characterize the nodes of a network shape information spreading in terms of the coverage and the cost of the initial spreaders. Extensive experimentation is carried out using data from the Twitter social network. These experiments illustrate how di erent selection mechanisms help shaping the dynamics of the spreading process, as well as the cost of the spreaders. Certain network metrics provide good insight for cost-e ective spreader selection, meaning that some metrics (node properties) lead to the identi cation of users with good capabilities to spread information. In general, this work identi es conditions under which an algorithmic selection mechanism o ers the best performance in terms of coverage and cost, and network metrics characterize the optimal initial spreaders in the network. The ndings can o er an alternative approach to select spreaders in commercial and advertising campaigns.