Browsing by Author "Zoubir, Abdelhak M."

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Classification of underwater objects based on Zernike and pseudo Zernike moments and Fourier descriptors
    (2010) Arpón Díaz-Aldagalán, Javier; Río Bocio, Carlos del; Fandos, Raquel; Zoubir, Abdelhak M.; Escuela Técnica Superior de Ingenieros Industriales y de Telecomunicación; Telekomunikazio eta Industria Ingeniarien Goi Mailako Eskola Teknikoa; Technische Universität Darmstadt (Alemania); Ingeniería Eléctrica y Electrónica; Ingeniaritza Elektrikoa eta Elektronikoa
    In this work the process of classification of underwater objects in sonar images is treated. The necessary steps, which are based on image processing and computer vision, are first the segmentation, then feature extraction and finally classification. Three different kinds of descriptors are tested in this work: the Zernike Polynomials (ZP), the pseudo Zernike Polynomials (PZP) and the Fourier Descriptors (FD). Several sets of these coefficients are tested with a Mahalanobis classifier. A set of coefficients are proposed that give us succesful results for each feature descriptor and there are compared to choose the most reliable.
  • Thumbnail Image
    PublicationOpen Access
    A segmentation algorithm for measuring blood glucose in hand-held devices
    (2013) Aramendía Vidaurreta, Verónica; Malanda Trigueros, Armando; Demitri, Nevine; Zoubir, Abdelhak M.; Escuela Técnica Superior de Ingenieros Industriales y de Telecomunicación; Telekomunikazio eta Industria Ingeniarien Goi Mailako Eskola Teknikoa; Technishche Universität Darmstadt (Alemania); Ingeniería Eléctrica y Electrónica; Ingeniaritza Elektrikoa eta Elektronikoa
    This thesis deals with the estimation of blood glucose values from biomedical images. This estimation is related to the chemical reaction between glucose and a chemical reactant. The main goal is to segment the blood sample area from several sets of test measurements. An algorithm based on histograms thresholding and its combination with watershed segmentation is proposed and applied to these images. Furthermore, the kernel density estimator is used, as an alternative to the histogram, to estimate the probability density function of the images. After the identification of the optimal thresholding methods, a general procedure is proposed. This procedure includes image preprocessing, blood sample detection, histogram thresholding, binary masks comparison and a relative remission estimation. Then, using a convergence criterion the convergence value of the chemical reaction is found. Finally, the results are evaluated with respect to both accuracy and computation time