???item.export.label??? ???item.export.type.endnote??? ???item.export.type.bibtex???

Please use this identifier to cite or link to this item: https://tede.ufrrj.br/jspui/handle/jspui/1306
Full metadata record
DC FieldValueLanguage
dc.creatorCampos, Alan Santos-
dc.creator.Latteshttp://lattes.cnpq.br/2600343834625437por
dc.contributor.advisor1Gregório, Ronaldo Malheiros-
dc.contributor.advisor-co1Cruz, Marcelo Dib-
dc.contributor.referee1Gregório, Ronaldo Malheiros-
dc.contributor.referee2Vera-Tudela, Carlos Andres Reyna-
dc.contributor.referee3Quiroz, Erik Alex Papa-
dc.date.accessioned2022-07-01T19:23:58Z-
dc.date.issued2022-03-29-
dc.identifier.citationCAMPOS, Alan Santos. Um estudo comparativo sobre a influência dos k-centróides no processo de segmentação de imagens em DTI-RM. 2022. 54 f. Dissertação (Mestrado em Modelagem Matemática e Computacional) - Instituto de Ciências Exatas, Universidade Federal Rural do Rio de Janeiro, Seropédica, 2022.por
dc.identifier.urihttps://tede.ufrrj.br/jspui/handle/jspui/1306-
dc.description.resumoA difusão tensorial de imagens por ressonância magnética (DTI-RM) é uma técnica não invasiva e eficaz na detecção de tumores ou anomalias em seres vivos. Em DTI-RM, podemos utilizar algoritmos de aprendizado de máquina, como por exemplo o K -Means, em processos como a segmentação de imagens. O algoritmo K -Means, originalmente utiliza centróides defi-nidos sob uma perspectiva euclidiana. Seu objetivo é a identificação de elementos semelhantes para agrupá-los em classes pertencentes a uma mesma região da imagem. Por outro lado, a existência e unicidade de segmentos geodésicos minimizantes, assim como expressões fecha-das para o cálculo de distâncias entre dois pontos arbitrários em alguns espaços riemannianos, como é o caso da variedade das matrizes simétricas definidas positivas, viabilizam a boa defini-ção de centróides sob uma perspectiva não-euclidiana. Assim sendo, as imagens em DTI-RM, cujos pixels, no caso bidimensional, ou voxels, no caso tridimensional, são respectivamente re-presentados por matrizes simétricas definidas positivas de ordem 2 e 3, e podem ser tratadas também sob uma perspectiva não-euclidiana, que utiliza a geometria natural desta variedade. Neste trabalho, desenvolvemos um estudo comparativo sobre a influência de alguns centróides, definidos tanto sob uma perspectiva euclidiana quanto riemanniana, no processo de segmenta-ção de imagens por meio do algoritmo K -Means.por
dc.description.abstractDiffusion tensor magnetic resonance imaging (DT-MRI) is a non-invasive and effective technique for detecting tumors or anomalies in living tissues. In DT-RMI, machine learning algorithms such as K -Means can be used in processes like image segmentation. The K -Means algorithm originally uses centers of mass defined under a Euclidean setting. The objective is to identify similar elements to group them in classes belonging to the same region of the image. On the other hand, the existence and uniqueness of minimizing geodesic segments, as well as closed expressions for computing distances between two arbitrary points in some Riemannian spaces, as it happens in the manifold of symmetric positive definite matrices, enable the well-posedness of centers of mass under a non-Euclidean setting. Therefore, images in DT-RMI, whose pixels, in the two-dimensional case, or voxels, in the three-dimensional one, are respectively represented by symmetric positive definite matrices of order 2 and 3, can be treated as well from a non-Euclidean setting, which uses the natural geometry of this manifold. In this work, we developed a comparative study on the influence of some centers of mass, defined both from a Euclidean and Riemannian setting, in the image segmentation process using the K -Means algorithm..eng
dc.description.provenanceSubmitted by Jorge Silva (jorgelmsilva@ufrrj.br) on 2022-07-01T19:23:58Z No. of bitstreams: 1 2022 - Alan Santos Campos.pdfeng
dc.description.provenanceMade available in DSpace on 2022-07-01T19:23:58Z (GMT). No. of bitstreams: 1 2022 - Alan Santos Campos.pdfeng
dc.description.sponsorshipCAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superiorpor
dc.formatapplication/pdf*
dc.thumbnail.urlhttps://tede.ufrrj.br/retrieve/69832/2022%20-%20Alan%20Santos%20Campos.pdf.jpg*
dc.languageporpor
dc.publisherUniversidade Federal Rural do Rio de Janeiropor
dc.publisher.departmentInstituto de Ciências Exataspor
dc.publisher.countryBrasilpor
dc.publisher.initialsUFRRJpor
dc.publisher.programPrograma de Pós-Graduação em Modelagem Matemática e Computacionalpor
dc.relation.references[1] AFSARI, B. Means and averaging on Riemannian manifolds, Ph.D. thesis. university of Maryland, university of Maryland, College Park., 2009. [2] AFSARI, B. Riemannian l p center of mass: existence, uniqueness, and convexity. Proceedings of the American Mathematical Society 139, 2 (2011), 655–673. [3] AGGARWAL, C. C., ET AL. Data mining: the textbook, vol. 1. Springer, 2015. [4] ALBUQUERQUE, M., CANER, E., MELLO, A., AND ALBUQUERQUE, M. Análise de imagens e visão computacional. Centro Brasileiro de Pesquisas Físicas. Rio de Janeiro (2012). [5] BHATIA, R. Positive definite matrices. Princeton university press, 2009. [6] BLACKLEDGE, J. M. Digital image processing: mathematical and computational methods. Elsevier, 2005. [7] BRAMER, M. Introduction to data mining. In Principles of Data Mining. Springer, 2013, pp. 311–327. [8] BREDIES, K., HOLLER, M., STORATH, M., AND WEINMANN, A. Total generalized variation for manifold-valued data. SIAM Journal on Imaging Sciences 11, 3 (2018), 1785–1848. [9] BURDEN, R. L., FAIRES, J. D., AND BURDEN, A. M. Numerical analysis. Cengage learning, 2015. [10] BURGER, W., AND BURGE, M. J. Digital image processing: an algorithmic introduction using Java. Springer, 2016. [11] CASEIRO, R., HENRIQUES, J. F., AND BATISTA, J. Foreground segmentation via background modeling on riemannian manifolds. In 2010 20th International Conference on Pattern Recognition (2010), IEEE, pp. 3570–3574. [12] CHEN, J., PAPPAS, T. N., MOJSILOVIC, A., AND ROGOWITZ, B. E. Adaptive perceptual color-texture image segmentation. IEEE Transactions on Image Processing 14, 10 (2005), 1524–1536. [13] COSTA, J. A. F., AND DE SOUZA, J. G. Image segmentation through clustering based on natural computing techniques. Image Segmentation (2011). [14] DA SILVA ALVES, C. D., OLIVEIRA, P. R., AND GREGÓRIO, R. M. l® riemannian weighted centers of mass applied to compose an image filter to diffusion tensor imaging. Applied Mathematics and Computation 390 (2021), 125603. [15] DAI, F., SUGISAKA, M., AND ZHANG, B. A survey of image segmentation by the classical method and resonance algorithm. In Image Segmentation. IntechOpen, 2011, pp. 1–14. [16] DIAS, L. O., BOM, C. R., ALVES, B. C., DE ALBUQUERQUE, M. P., DE ALBUQUERQUE, M. P., FARIA, E. L., AND CORREIA, M. D. Estimativa de permeabilidade absoluta com processamento de imagens utilizando distribuiç ao de tamanho de graos. Notas Técnicas 7, 3 (2017). [17] DO CARMO, M. P. Geometria Riemanniana. Instituto de Matemática Pura e Aplicada, 2008. [18] ESTIGONI, E. H., ET AL. Sistema para análise de postura baseado em processamento digital de imagens e reconstrução tridimensional. UFSC (2006). [19] GALLIER, J. H. Notes on the schur complement. University of Pennsylvania (2010). [20] GAN, G., MA, C., AND WU, J. Data clustering: theory, algorithms, and applications. SIAM, 2020. [21] GOH, A., AND VIDAL, R. Clustering and dimensionality reduction on riemannian manifolds. In 2008 IEEE Conference on computer vision and pattern recognition (2008), IEEE, pp. 1–7. [22] GONZALEZ, R. C., AND WOODS, R. E. Processamento de imagens digitais. Editora Blucher, 2000. [23] GRAÇA, R. F. P. S. O. Segmentação de imagens torácicas de Raio-X. PhD thesis, Universidade da Beira Interior, 2012. [24] GREGORIO, R. M., AND OLIVEIRA, P. R. Proximal point algorithm with schur decomposition on the cone of symmetric semidefinite positive matrices. J. Math. Anal. Appl. v. 355, n. 2, 469-479 (2009). [25] IZMAILOV, A., AND SOLODOV, M. Otimização, volume 1: condições de otimalidade, elementos de análise convexa e de dualidade. Impa, 2005. [26] IZMAILOV, A., AND SOLODOV, M. Otimização, volume 2: métodos computacionais. IMPA, 2007. [27] KAGANAMI, H. G., AND BEIJI, Z. Region-based segmentation versus edge detection. In 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing (2009), IEEE, pp. 1217–1221. [28] KHAN, S. Alpaydin ethem. introduction to machine learning (adaptive computation and machine learning series), 2004. [29] LENGLET, C., ROUSSON, M., AND DERICHE, R. Dti segmentation by statistical surface evolution. IEEE Transactions on Medical Imaging 25, 6 (2006), 685–700. [30] LENGLET, C., ROUSSON, M., DERICHE, R., FAUGERAS, O., LEHERICY, S., AND UGURBIL, K. A riemannian approach to diffusion tensor images segmentation. In Biennial International Conference on Information Processing in Medical Imaging (2005), Springer, pp. 591–602. [31] LIMA, E. L. Espaços métricos, vol. 4. Instituto de Matemática Pura e Aplicada, CNPq Rio de Janeiro, 1983. [32] LIU, D., XIONG, Y., PULLI, K., AND SHAPIRO, L. Estimating image segmentation difficulty. In International Workshop on Machine Learning and Data Mining in Pattern Recognition (2011), Springer, pp. 484–495. [33] LIU, T., LI, H., WONG, K., TAROKH, A., GUO, L., AND WONG, S. T. Brain tissue segmentation based on dti data. NeuroImage 38, 1 (2007), 114–123. [34] MORI, S. Introduction to diffusion tensor imaging. Elsevier, 2007. [35] NUNES, D. H. F. Um breve estudo sobre o algoritmo K-means. PhD thesis, Universidade de Coimbra, 2016. [36] PENNEC, X., FILLARD, P., AND AYACHE, N. A riemannian framework for tensor computing. Epidaure / Asclepios Project-team, INRIA Sophia-Antipolis 2004 Route des Lucioles BP 93, F-06902 Sophia Antipolis Cedex, France v. 149 (2005). [37] PHAM, D. L., XU, C., AND PRINCE, J. L. Current methods in medical image segmentation. Annual review of biomedical engineering 2, 1 (2000), 315–337. [38] REZATOFIGHI, H., TSOI, N., GWAK, J., SADEGHIAN, A., REID, I., AND SAVARESE, S. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2019), pp. 658–666. [39] RONCERO, V. G. Um Estudo de Segmentação de Imagens baseado em um método de Computação Evolucionária. PhD thesis, UFRJ, 2005. [40] SAKAI, T. Riemannian geometry, vol. 149. American Mathematical Soc., 1996. [41] SARPE, A.-I. Image segmentation with clustering k-means and watershed transform. In 2010 Second International Conferences on Advances in Multimedia (2010), IEEE, pp. 13–17. [42] SHEN, X., JU, S., CHO, S.-Y., AND LI, F. Mining user hidden semantics from image content for image retrieval. Journal of Visual Communication and Image Representation 19, 3 (2008), 145–164. [43] SILVA, L. Segmentação de imagens de profundidade por detecção de bordas. UFPR (2001). [44] SZELISKI, R. Computer vision: algorithms and applications. Springer Science & Business Media, 2010. [45] TUZEL, O., PORIKLI, F., AND MEER, P. Pedestrian detection via classification on riemannian manifolds. IEEE transactions on pattern analysis and machine intelligence 30, 10 (2008), 1713–1727. [46] UNIVERSITY, B. N. State key laboratory of cogitive neuroscience and learning enhanced sample. http:fcon_1000.projects.nitrc.org/indi/retro/BeijingEnhanced.html, 2021. [47] VAN HECKE, W., EMSELL, L., AND SUNAERT, S. Diffusion tensor imaging: a practical handbook. Springer, 2016. [48] WU, S.-T., VOLTOLINE, R., LOOS, W. S., RUBIANES SILVA, J. I., WATANABE, L. S., AMORIM, B. J., COAN, A. C., CENDES, F., AND YASUDA, C. L. Toward a multimodal diagnostic exploratory visualization of focal cortical dysplasia. IEEE Computer Graphics and Applications 38, 3 (2018), 73–89. [49] YOUSSIF, A., YOUSSRY, H., ET AL. Tissue segmentation techniques of brain mr images. In International Conference on Intelligent Computational Systems (2012), International Conference on Intelligent Computational Systems, pp. 1–5. [50] ZHANG, F., AND HANCOCK, E. R. New riemannian techniques for directional and tensorial image data. Pattern recognition 43, 4 (2010), 1590–1606.por
dc.rightsAcesso Abertopor
dc.subjectK-Means Algorithmeng
dc.subjectRiemannian Metricseng
dc.subjectImage Segmentationeng
dc.subjectAlgoritmo k-meanspor
dc.subjectMétrica Riemannianapor
dc.subjectSegmentação de Imagenspor
dc.subject.cnpqCiência da Computaçãopor
dc.titleUm estudo comparativo sobre a influência dos k-centróides no processo de segmentação de imagens em DTI-RMpor
dc.title.alternativeA comparative study on the influence of k-centroids on the image segmentation process in DT-MRIeng
dc.typeDissertaçãopor
Appears in Collections:Mestrado em Modelagem Matemática e Computacional

Files in This Item:
File Description SizeFormat 
2022 - Alan Santos Campos.pdf5.4 MBAdobe PDFThumbnail

Download/Open Preview


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.