Mostrar el registro sencillo del documento

dc.rights.licenseAtribución-NoComercial 4.0 Internacional
dc.contributor.advisorPrieto Ortiz, Flavio Augusto
dc.contributor.advisorPolanía Cabrera, Luisa Fernanda
dc.contributor.authorBastidas Rodríguez, Maria Ximena
dc.date.accessioned2020-06-24T16:44:50Z
dc.date.available2020-06-24T16:44:50Z
dc.date.issued2020-06-21
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/77683
dc.description.abstractNowadays, many classification problems are approached with deep learning architectures, and the results are outstanding compared to the ones obtained with traditional computer vision approaches. However, when it comes to texture, deep learning analysis has not had the same success as for other tasks. The texture is an inherent characteristic of objects, and it is the main descriptor for many applications in the computer vision field, however due to its stochastic appearance, it is difficult to obtain a mathematical model for it. According to the state of the art, deep learning techniques have some limitations when it comes to learning textural features; and, to classify texture using deep neural networks, it is essential to integrate them with handcrafted features or develop an architecture that resembles these features. By solving this problem, it would be possible to contribute in different applications, such as fractographic analysis. To achieve the best performance in any industry, it is important that the companies have a failure analysis, able to show the flaws’ causes, offer applications and solutions and generate alternatives that allow the customers to obtain more efficient components and productions. The failure of an industrial element has consequences such as significant economic losses, and in some cases, even human losses. With this analysis it is possible to examine the background of the damaged piece in order to find how and why it fails, and to help prevent future failures, in order to implement safer conditions. The visual inspection is the basis for the generation of every fractographic process in failure analysis and it is the main tool for fracture classification. This process is usually done by non-expert personnel on the topic, and normally they do not have the knowledge or experience required for the job, which, without question, increases the possibilities of generating a wrong classification and negatives results in the whole process. This research focuses on the development of a visual computer system that implements a textural deep learning architecture. Several approaches were taken into account, including combining deep learning techniques with traditional handcrafted features, and the development of a new architecture based on the wavelet transform and the multiresolution analysis. The algorithm was test on textural benchmark datasets and on the classification of mechanical fractures with particular texture and marks on surfaces of crystalline materials.
dc.description.abstractActualmente, diferentes problemas computacionales utilizan arquitecturas de aprendizaje profundo como enfoque principal. Obteniendo resultados sobresalientes comparados con los obtenidos por métodos tradicionales de visión por computador. Sin embargo, cuando se trata de texturas, los análisis de textura no han tenido el mismo éxito que para otras tareas. La textura es una característica inherente de los objetos y es el descriptor principal para diferentes aplicaciones en el campo de la visión por computador. Debido a su apariencia estocástica difícilmente se puede obtener un modelo matemático para describirla. De acuerdo con el estado-del-arte, las técnicas de aprendizaje profundo presentan limitaciones cuando se trata de aprender características de textura. Para clasificarlas, se hace esencial combinarlas con características tradicionales o desarrollar arquitecturas de aprendizaje profundo que reseemblen estas características. Al solucionar este problema es posible contribuir a diferentes aplicaciones como el análisis fractográfico. Para obtener el mejor desempeño en cualquier tipo de industria es importante obtener análisis fractográfico, el cual permite determinar las causas de los diferentes fallos y generar las alternativas para obtener componentes más eficientes. La falla de un elemento mecánico tiene consecuencias importantes tal como pérdidas económicas y en algunos casos incluso pérdidas humanas. Con estos análisis es posible examinar la historia de las piezas dañadas con el fin de entender porqué y cómo se dio el fallo en primer lugar y la forma de prevenirla. De esta forma implementar condiciones más seguras. La inspección visual es la base para la generación de todo proceso fractográfico en el análisis de falla y constituye la herramienta principal para la clasificación de fracturas. El proceso, usualmente, es realizado por personal no-experto en el tema, que normalmente, no cuenta con el conocimiento o experiencia necesarios requeridos para el trabajo, lo que sin duda incrementa las posibilidades de generar una clasificación errónea y, por lo tanto, obtener resultados negativos en todo el proceso. Esta investigación se centra en el desarrollo de un sistema visual de visión por computado que implementa una arquitectura de aprendizaje profundo enfocada en el análisis de textura. Diferentes enfoques fueron tomados en cuenta, incluyendo la combinación de técnicas de aprendizaje profundo con características tradicionales y el desarrollo de una nueva arquitectura basada en la transformada wavelet y el análisis multiresolución. El algorítmo fue probado en bases de datos de referencia en textura y en la clasificación de fracturas mecánicas en materiales cristalinos, las cuales presentan texturas y marcas características dependiendo del tipo de fallo generado sobre la pieza.
dc.description.sponsorshipFundación CEIBA
dc.format.extent96
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.rightsDerechos reservados - Universidad Nacional de Colombia
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.titleA textural deep neural network architecture for mechanical failure analysis
dc.typeOtro
dc.rights.spaAcceso abierto
dc.type.driverinfo:eu-repo/semantics/other
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dc.publisher.programBogotá - Ingeniería - Doctorado en Ingeniería - Ingeniería Eléctrica
dc.contributor.researchgroupGrupo de Automática de la Universidad Nacional GAUNAL
dc.description.degreelevelDoctorado
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotá
dc.relation.referencesIntroduction to Support Vector Machines. , p. on–line: http://docs.opencv.org/doc/tutorials/ml/introduction to svm/introduction to svm.html
dc.relation.referencesComputer Vision. En: Department of Computer Science and Engineering, University of Washington (2000), p. on–line: https://courses.cs.washington.edu/courses/cse576/book.
dc.relation.referencesComputer Vision. En: Department of Computer Science and Engineering, University of Washington (2000), p. on–line: https://courses.cs.washington.edu/courses/cse576/book.
dc.relation.referencesMaterial Failures – The Role of Fractography in Determining the cause. (2017)
dc.relation.referencesAndrearczyk, V. ; Whelan, Paul F.: Deep Learning for Biomedical Texture Image Analysis. En: Proceedings of the 18th Irish Machine Vision and Image Processing conference (2016)
dc.relation.referencesAndrearczyk, V. ; Whelan, Paul F.: Using Filter Banks in Convolutional Neural Networks for Texture Classification. En: Pattern Recognition Letters, Vol. 84 (2016), p. 63–69
dc.relation.referencesAnselm, Martin K.: Manager, Analytical & Failure Analysis Services, Universal Instruments. En: On-line: https://www.smta.org/. (2018)
dc.relation.referencesAntreas Antoniou, Harrison E.: Data Augmentation Generative Adversarial Networks. En: arXiv:1711.04340 (2017)
dc.relation.referencesArdakani, Ali A. ; Gharbali, Akbar ; Mohammadi, Afshin: Classification of Benign and Malignant Thyroid Nodules Using Wavelet Texture Analysis of Sonograms. En: Journal of Ultrasound in Medicin (2015)
dc.relation.referencesArivazhagan, S. ; Ganesan, L.: Texture segmentation using wavelet transform. En: Pattern Recognition Letters 24 (2003)
dc.relation.referencesBackes, A.R. ; Bruno, O.M.: Plant Leaf Identification Using Multi-scale Fractal Dimension. En: ICIAP (2009), p. 143–150
dc.relation.referencesBastidas-Rodriguez, M.X. ; Prieto-Ortiz, F.A. ; Espejo, Edgar: Fractographic classification in metallic materials by using computer vision. En: Engineering Failure Analysis 59 (2016), p. 237–252
dc.relation.referencesBasu, S. ; Mukhopadhyay, S. ; Karki, M. ; DiBiano, R. ; Ganguly, S. ; Nemani, R. ; Gayaka, S.: Deep neural networks for texture classification - A theoretical analysis. En: Neural Networks 97 (2018), p. 173 – 182
dc.relation.referencesBecker, W.T.: Fracture Appearance and Mechanisms of Deformation and Fracture. En: University of Tennessee, Emeritus; S. Lampman, ASM International (2010)
dc.relation.referencesBruna, Joan ; Mallat, Stephane: Invariant Scattering Convolution Networks. En: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 35 (2013), Nr. 8
dc.relation.referencesCamargo, O.M. ; Arista, B.V ; Camargo, J.M: Digital Processing of Fractographic Images for Welded Joints on Microalloy Steel API5L-X52 Aged. En: IEEE Latin America, Transactions (2013), p. Vol. 11, NO 1
dc.relation.referencesCaputo, B. ; Hayman, E. ; Mallikarjuna, P.: Class-specific material categorisation. En: IEEE International Conference on Computer Vision (2005), p. 1597–1604
dc.relation.referencesChakraborty, S. [u. a.]: Interpretability of deep learning models: A survey of results. En: IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation, 2017, p. 1–6
dc.relation.referencesChang, T. ; Kuo, C. . J.: Texture analysis and classification with tree-structured wavelet transform. En: IEEE Transactions on Image Processing 2 (1993), Nr. 4, p. 429–441
dc.relation.referencesCimpoi, M. ; Maji, S. ; Kokkinos, I. ; Vedaldi, A.: Deep filter banks for texture recognition, description, and segmentation. En: International Journal of Computer Vision 118 (2016), Nr. 1, p. 65–94
dc.relation.referencesClaypoole, R. L. ; Davis, G. M. ; Sweldens, W. ; Baraniuk, R. G.: Nonlinear wavelet transforms for image coding via lift
dc.relation.referencesCotter, F. ; Kingsbury, N.: Deep Learning in the Wavelet Domain. En: arXiv preprint arXiv:1811.06115 (2018)
dc.relation.referencesCross, George R. ; Jain, Anil K.: Markov Random Field Texture Models. En: IEEE Transactions on pattern analysis and machine intelligence (1983)
dc.relation.referencesDaubechies, I. ; Sweldens, W.: Factoring wavelet transforms into lifting steps. En: The Journal of Fourier Analysis and Applications 4 (1998), Nr. 3, p. 247–269
dc.relation.referencesDeepa Sankar, Tessamma T.: Fractal Features based on Differential Box Counting Method for the Categorization of Digital Mammograms. En: Internationa Journal of Computer Information Systems and Industrial Management Applications (2010)
dc.relation.referencesDeng, J. ; Dong, W. ; Socher, R. ; Li, L. ; Li, Kai ; Fei-Fei, Li: ImageNet: A large-scale hierarchical image database. En: IEEE Conference on Computer Vision and Pattern Recognition (2009), p. 248–255
dc.relation.referencesDharmagunawardhana, Chathurika ; Mahmoodia, Sasan ; Bennettb, Michael ; Niranjan, Mahesan: Rotation invariant texture descriptors based on Gaussian Markov random fields for classification. En: Pattern Recognition Letters 69 (2016), p. 15–21
dc.relation.referencesDong, Y. ; Su, H. ; Zhu, J. ; Zhang, B.: Improving interpretability of deep neural networks with semantic information. En: IEEE Conference on Computer Vision and Pattern Recognition, 2017, p. 4306–4314
dc.relation.referencesD.Pham, Tuan: The Kolmogorov-Sinai entropy in the setting of fuzzy sets for image texture analysis and classification. En: Pattern Recognition 53 (2016), p. 229–237
dc.relation.referencesElfadel, Ibrahim M. ; Picard, Rosalind W.: Gibbs Random Fields, Cooccurrences, and Texture Modeling. En: IEEE Transactions on Pattern Analysis and Machine Intelligence (1994)
dc.relation.referencesElsken, T. ; Metzen, J. ; Hutter, F.: Simple and Efficient Architecture Search for CNNs. (2017)
dc.relation.referencesE.Salari ; Z.Ling: Texture segmentation using hierarchical wavelet decomposition. En: Pattern Recognition 28 (1995), Nr. 12
dc.relation.referencesEspejo, E.: Fallas por Fractura y Fractograf´ıa. En: Notas de clase curso An´alisis de Falla Universidad Nacional de Colombia - Sede Bogot´a (2013)
dc.relation.referencesFan, Guoliang ; Xia, Xiang-Gen: Wavelet-based texture analysis and synthesis using hidden Markov models. En: IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 50 (2003), Nr. 1, p. 106–120
dc.relation.referencesFawcett, Tom: An Introduction to ROC Analysis. En: Pattern Recognition Letters 27 (2006)
dc.relation.referencesFawzi, Alhussein ; Samulowitzy, Horst ; Turagay, Deepak ; Frossard, Pascal: Adaptive Data Augmentation for Image Classification. En: Image Processing (ICIP), 2016 IEEE International Conference (2016)
dc.relation.referencesFeng, Shuo ; Zhou, Huiyu ; Dong, Hongbiao: Using deep neural network with small dataset to predict material defects. En: Materials & Design 162 (2019), p. 300–310
dc.relation.referencesFujieda, S. ; Takayama, K. ; Hachisuka, T: Wavelet Convolutional Neural Networks. En: arXiv:1805.08620 (2018)
dc.relation.referencesGalloway, Mary M.: Texture Analysis Using Gray Level Run Lengths. En: Computer Graphics and Image Processing (1975), p. 172–179
dc.relation.referencesGeirhos, Robert ; Rubisch, Patricia ; Michaelis, Claudio ; Bethge, Matthias ; Wichmann, Felix A. ; Brendel, Wieland: ImageNet-Trained CNNS are biased towards texture; increasing shape bias improves accuracy and robustness. En: ICLR (2019)
dc.relation.referencesGholipour, M. ; Noubari, H. A.: Hardware implementation of lifting based wavelet transform. En: International Conference on Signal Processing Systems Vol. 1, 2010, p. V1–215–V1–219
dc.relation.referencesGoodfellow, Ian ; Bengio, Yoshua ; Courville, Aaron: Deep Learning. MIT Press, 2016. – http://www.deeplearningbook.org
dc.relation.referencesGoodfellow, Ian J. ; Pouget-Abadie, Jean ; Mirza, Mehdi ; Xu, Bing ; Warde- Farley, David ; Ozair, Sherjil ; Courville, Aaron ; Bengio, Yoshua: Generative Adversarial Networks. En: arXiv:1406.2661 (2014)
dc.relation.referencesHadida, Abdenour ; Ylioinas, Juha ; Bengherabi, Messaoud ; Ghahramani, Mohammad ; Taleb-Ahmed, Abdelmalik: Gender and texture classification: A comparative analysis using 13 variants of local binary patterns. En: Pattern Recognition Letters 68 (2015), p. 231–238
dc.relation.referencesHafemann, Luiz G. ; Oliveira, Luiz S. ; Cavalin, Paulo: Forest Species Recognition using Deep Convolutional Neural Networks. En: 22nd International Conference on Pattern Recognition (2014)
dc.relation.referencesHafemann, Luiz G. ; Oliveira, Luiz S. ; Cavalin, Paulo R. ; Sabourin, Robert: Transfer Learning between Texture Classification Tasks using Convolutional Neural Networks. En: 2015 International Joint Conference on Neural Networks (IJCNN) (2015)
dc.relation.referencesHaider, Ali: Accelerated Fatigue Reliability Analysis of Stiffened Sections Using Deep Learning. En: Graduate College of the Oklahoma State University (2018)
dc.relation.referencesHammouche, Kamal ; Losson, Olivier ; Macaire, Ludovic: Fuzzy aura matrices for texture classification. En: Pattern Recognition (2016), p. 212–228
dc.relation.referencesHauberg, Søren ; Freifeld, Ore ; Boesen Lindbo Larsen, Anders ; Fisher, III ; Hansen, Lars K.: Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation. En: Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (2016), p. 342–350
dc.relation.referencesHazra, Dipankar: Texture Recognition with combined GLCM, Wavelet and Rotated Wavelet Features. En: International Journal of Computer and Electrical Engineering 13 (2011), Nr. 1, p. 1793–8163
dc.relation.referencesHe, K. ; Zhang, X. ; Ren, S. ; Sun, J. Jian S.: Deep Residual Learning for Image Recognition. En: Conference on Computer Vision and Pattern Recognition (2016)
dc.relation.referencesHinton, G.E. ; Osindero, S. ; Teh, Y.: A fast learning algorithm for deep belief nets. En: Neural Computation (2006)
dc.relation.referencesHuang, G. ; Liu, Z. ; Van der Maaten, L.: Densely Connected Convolutional Networks. En: Conference on Computer Vision and Pattern Recognition (2018)
dc.relation.referencesI, Laws K.: Textured Image Segmentation. En: University of Southern California (1980)
dc.relation.referencesIdrissa, Mahamadou ; Acheroy, Marc: Texture classification using Gabor filters. En: Pattern Recognition Letters (2002), p. 1095–1102
dc.relation.referencesIpohorski, M.: Fractograf´ıa, Aplicaciones al An´alisis de Fallas. En: CNEA 490 (1988), p. Comisi´on Nacional de Energ´ıa At´omica, Argentina: Buenos Aires
dc.relation.referencesJacek, Komenda ; Barbara, Maroli ; Lars, H¨oglund: Recognition of patterns on fracture surfaces by automatic image analysis. En: Image Anal Stereol (2002)
dc.relation.referencesJim´enez Guerrero, Mar´ıa Del P.: Extracci´on de caracter´ısticas de textura basada en la Transformada Wavelet Discreta, Capitulo 5. En: Escuela Superior de Ingenieros, Universidad de Sevilla , p. http://bibing.us.es/proyectos/abreproy/11494/ fichero/PROYECTO\%252FCapitulo+5.pdf
dc.relation.referencesJun-Yan Zhu, Phillip Isola Alexei A. E.: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. En: ICCV (2017)
dc.relation.referencesKarrasNVIDIA, Tero ; Aila, Timo ; Laine, Samuli ; Lehtinen, Jaakko: Progressive Growing of GANs for Improved Quality, Stability, and Variation. En: ICLR (2018)
dc.relation.referencesKhokhlov, M. ; Fischer, A. ; Rittel, D.: Multi-Scale Stereo-Photogrammetry System for Fractographic Analysis Using Scanning Electron Microscopy. En: Experimental Mechanics (2012)
dc.relation.referencesKolednik, O. ; Scherer, S. ; Schwarzb¨ock, P. ; Werth, P.: Quantitative Fractography by Means of a New Digital Image Analysis System. En: Proc. of ECF13, Paper 1U.60. Elsevier, Amsterdam (2000)
dc.relation.referencesKomai, Kenjiro ; Minoshima, Kohji ; Ishii, Shoich: Recognition of Different Fracture Surface Morphologies using Computer Image Processing Technique. En: SME Intentationat Jettma Series A (1993)
dc.relation.referencesKonovalenko, Ihor ; Maruschak, Pavlo ; Prentkovskis, Olegas ; Juneviˇcius, Raimundas: Automated Method for Fractographic Analysis of Shape and Size of Dimples on Fracture Surface of High-Strength Titanium Alloys. En: Materials 11 (2018)
dc.relation.referencesKrizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. En: Tech Report (2009)
dc.relation.referencesKrizhevsky, A. ; Sutskever, I. ; Hinton, G.E.: Imagenet classification with deep convolutional neural networks. En: Advances in Neural Information Processing Systems 25 (2012), p. 1097–1105
dc.relation.referencesKuna, M.: Finite Elements in Fracture Mechanics, Solid Mechanics and Its Applications. En: Springer Science+Business Media Dordrecht (2013)
dc.relation.referencesLabatut, Vincent ; Cherifi, Hocine: Accuracy Measures for the Comparison of Classifiers. En: Cornell University, arXiv:1207.3790 (2012)
dc.relation.referencesLaine, A. ; Fan, J.: Texture classification by wavelet packet signatures. En: IEEE Transactions on Pattern Analysis and Machine Intelligence 15 (1993), Nr. 11, p. 1186– 1191
dc.relation.referencesLauschmann, H. ; Nedbal, I.: Auto-Shape Analysis of Image Textures in Fractography. En: Czech Technical University, Faculty of Nuclear Sciences and Physical Engineering, Dept. of Materials, Rep´ublica Checa: Trojanova (2002)
dc.relation.referencesLeCun, Y.: Generalization and network design strategies. En: Connectionism in Perspective (1989)
dc.relation.referencesLi, Fei-Fei: Class notes: CS231n: Convolutional Neural Networks. En: Standford University, available on: http://cs231n.github.io/convolutional-networks/
dc.relation.referencesLi, Fei-Fei: Class notes: CS231n: Convolutional Neural Networks. En: Standford University, available on: http://cs231n.github.io/convolutional-networks/
dc.relation.referencesLin, Hsuan T.: Texture Classification using Fractal-based Features and Support Vector Machines. En: Department of Computer Science and Information Engineering, National Taiwan University , p. http://www.work.caltech.edu/~htlin/course/ doc/FractalFinal.pdf
dc.relation.referencesLin, M. ; Chen, Q. ; Yan, S: Network In Network. En: International Conference on Learning Representations (2014)
dc.relation.referencesLivens, S ; Scheunders, P ; van de Wouwer, G ; Dyc, D V.: Wavelet for texture analysis, an overview. En: 6th International Conference on Image Processing and Its Applications (1997)
dc.relation.referencesLu, H. ; Wang, H. ; Zhang, Q. ; Won, D. ; Yoon, S. W.: A Dual-Tree Complex Wavelet Transform Based Convolutional Neural Network for Human Thyroid Medical Image Segmentation. En: IEEE International Conference on Healthcare Informatics (2018), p. 191–198
dc.relation.referencesMaani, Rouzbeh ; Kalra, Sanjay ; Yang, Yee-Hong: Noise robust rotation invariant features for texture classification. En: Pattern Recognition, vol. 46 (2013), p. 2103– 2116
dc.relation.referencesMahto, Bishnu P.: Characterization of Ductile Iron Through Fractograpic Study. En: Master thesis, National Institute of Technology (2014)
dc.relation.referencesMallat, S.G.: A Theory for Multiresolution Signal Decomposition: The Wavelet Representation. En: IEEE Transactions on Pattern Analysis and Machine Intelligence 2 (1989), Nr. 7, p. 674–693
dc.relation.referencesMallat, St´ephane: Wavelet Tour of Signal Processing. En: Academic Press, 3rd edition (2009), p. Chapter 1: Sparse Representations
dc.relation.referencesMeurant, G.: Wavelets: a tutorial in theory and applications. Vol. 2. Academic press, 2012
dc.relation.referencesMoreno, C.J. ; Espejo, E.: A performance evaluation of three inference engines as expert systems for failure mode identification in shafts. En: Engineering Failure Analysis 53 (2015), p. 24–35
dc.relation.referencesOdena, Augustus ; Olah, Christopher ; Shlens, Jonathon: Conditional Image Synthesis with Auxiliary Classifier GANs. En: arXiv:1610.09585 (2017)
dc.relation.referencesO’Gara, Sarah ; McGuinness, Kevin: Comparing Data Augmentation Strategies for Deep Image Classification. En: IMVIP 2019: Irish Machine Vision Image Processing, Technological University Dublin, Dublin, Ireland (2019)
dc.relation.referencesOyallon, E. ; Belilovsky, E. ; Zagoruyko, S.: Scaling the scattering transform: Deep hybrid networks. En: International Conference on Computer Vision (2017)
dc.relation.referencesP. Shanmugavadivu, V. S.: Fractal Dimension Based Texture Analysis of Digital Images. En: Procedia Engineering (2012), p. 2981–2986
dc.relation.referencesPan, Sinno J. ; Fellow, Qiang Y.: A Survey on Transfer Learning. En: IEEE Transactions on Knowledge and Data Engineering (2010), p. 1345–1359
dc.relation.referencesPei, J. ; Wright, J. ; Smyth, A.: Mapping polynomial fitting into feedforward neural networks for modeling nonlinear dynamic systems and beyond. En: Science Direct, Computer methods in applied mechanics and engineering (2005)
dc.relation.referencesPham, Tuan A.: Optimization of Texture Extraction Algorithm. En: Computer Engineering, Department of Electrical Engineering, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University Techbology, Netherlands (2010)
dc.relation.referencesPierre, Soille: Morphological Texture Analysis: An Introduction. En: Morphology of Condensed Matter: Physics and Geometry of Spatially Complex Systems, Springer Berlin Heidelberg (2002), p. 215–237
dc.relation.referencesP.S. Hiremath, S. S.: Wavelet based co-occurrence histogram features for texture classification with an application to script identification in a document image. En: Pattern Recognition Letters 29 (2008), p. 1182–1189
dc.relation.referencesR. Haralick, K. S. ; Dinstein, I.: Textural features for image classification. (1973)
dc.relation.referencesRodr´ıguez, Maria Ximena B.: Clasificaci´on fractogr´afica en materiales cristalinos empleando visi´on por computador. En: Universidad Nacional de Colombia, Tesis de Maestr´ıa (2015)
dc.relation.referencesBastidas Rodríguez, Maria Ximena.: Clasificación fractográfica en materiales cristalinos empleando visión por computador. En: Universidad Nacional de Colombia, Tesis de Maestría (2015)
dc.relation.referencesRoss, A.S. ; Doshi-Velez, F.: Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients. En: AAAI Conference on Artificial Intelligence, 2018
dc.relation.referencesSalimans, Tim ; Goodfellow, Ian J. ; Zaremba, Wojciech ; Cheung, Vicki ; Radford, Alec ; Chen, Xi: Improved techniques for training GANs. En: NIPS (2016)
dc.relation.referencesSayadi, Mounir ; Sakrani, Samir ; Fnaiech, Farhat ; Cheriet, Mohamed: Graylevel Texture Characterization Based on a New Adaptive Nonlinear Auto-Regressive Filter. En: Ecole de technologie sup´erieure, Notre-Dame , Montreal, Quebec, Electronic Letters on Computer Vision and Image Analysis (2008)
dc.relation.referencesSayadi, Mounir ; Sakrani, Samir ; Fnaiech, Farhat ; Cheriet, Mohamed: Graylevel Texture Characterization Based on a New Adaptive Nonlinear Auto-Regressive Filter. En: Ecole de technologie sup´erieure, Notre-Dame , Montreal, Quebec, Electronic Letters on Computer Vision and Image Analysis (2008)
dc.relation.referencesSilva, J.M. ; Infante, V. ; de Freitas, M. ; Reis, L.: Microscopy analysis of damaged aeronautical components. En: Microscopy: Science, Technology, Applications and Education, A. M´endez-Vilas and J. D´ıaz (Eds.) (2010)
dc.relation.referencesSimonyan, K. ; Zisserman, A.: VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION. En: International Conference on Learning Representations (2015)
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.subject.proposalAprendizaje de máquina
dc.subject.proposalMachine learning
dc.subject.proposalcomputer vision
dc.subject.proposalvisión por computador
dc.subject.proposalDeep learning
dc.subject.proposalAprendizaje profundo
dc.subject.proposalTexture analysis
dc.subject.proposalAnálisis de textura
dc.subject.proposalAnálsis de falla
dc.subject.proposalfailure analysis
dc.type.coarhttp://purl.org/coar/resource_type/c_1843
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.contentText
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2


Archivos en el documento

Thumbnail

Este documento aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del documento

Atribución-NoComercial 4.0 InternacionalEsta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.Este documento ha sido depositado por parte de el(los) autor(es) bajo la siguiente constancia de depósito