Browsing by Author "Yari Ramos, Yessenia Deysi"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Multispectral images segmentation using fuzzy probabilistic local cluster for unsupervised clustering
    (Institute of Electrical and Electronics Engineers Inc., 2018) Mantilla, Luis; Yari Ramos, Yessenia Deysi
    In Pattern Recognition there are many algorithms it try to solve the problem of grouping objects of the same type, this is called clustering, however the task of dividing these lies not only in the objective function, but also the methodology used to calculate the similarity between objects. Because multispectral images contain information that has low statistical separation and a large amount of data it is necessary to enter local information. In this paper, the use of the Gaussian dispersion equation is proposed in order to calculate the contribution of each sample to the sample analyzed. The results show that the integration of local weights within the clustering model decreases the entropy of each group generated. © 2017 IEEE.
  • No Thumbnail Available
    Item
    Multispectral images segmentation using new fuzzy cluster centroid modified
    (Institute of Electrical and Electronics Engineers Inc., 2017) Mantilla, Luis; Yari Ramos, Yessenia Deysi
    The presence of outliers, noise, corrupt pieces of data and great quantity of samples in a multispectral image, makes the segmentation analysis work tedious. The fuzzy clustering approach, specially, is susceptible to inhomogeneity of characteristics. Furthermore, many algorithms such us FCM, PFCM, FCC, FWCM and modification aim to solve these problems by integrating spacial information. This process is carried through the analysis of the sample's neighborhood. This paper proposes the integration of the sample presence probability into a 'term' like form inside the existent model NFCC. This algorithm presents the basic steps for fuzzy clustering. With a middle variant that integrates the measure between each sample to all the centroids, this replaces the existent term by a new term. This new term integrates the spatial relationship between each sample of the multispectral image into a fitting term. The method is applied to multispectral images. Overall accuracy indicates that the term integrated to NFCC model decrease the overall cluster overlapping. © 2017 IEEE.
  • No Thumbnail Available
    Item
    Tunki project: Wetland remote sensing using satellite images and high performance computing
    (Latin American and Caribbean Consortium of Engineering Institutions, 2018) Mamani Aliaga, Alvaro; Yari Ramos, Yessenia Deysi; Apaza Veliz, Ronald; Aco Cardenas , Pablo Yanyachi
    Wetlands are important for the world due to the benefits they offer to humanity. However, there are studies showing their decrease in number in several regions. A form of monitoring of the wetlands is necessary to evaluate their reduction, appearance and / or disappearance. The Tunki project is a project to detect wetlands in a given region using satellite images and high-performance computing. The present work, exposes its architecture and its case study: the wetlands in the Chili river basin of the Arequipa-Peru region. The results show the wetlands detected and the mosaics generated using the satellite images and HPC. © 2018 Latin American and Caribbean Consortium of Engineering Institutions. All rights reserved.