20 results on '"DELRIEUX, Claudio Augusto"'
Search Results
2. Assessment of Landsat-8 and Sentinel-2 Water Indices: A Case Study in the Southwest of the Buenos Aires Province (Argentina)
- Author
-
Santecchia, Guillermina Soledad, primary, Revollo Sarmiento, Gisela Noelia, additional, Genchi, Sibila Andrea, additional, Vitale, Alejandro José, additional, and Delrieux, Claudio Augusto, additional
- Published
- 2023
- Full Text
- View/download PDF
3. Dataset of Clinical Cases, Images, Image Labels and Captions from Open Access Case Reports from Pubmed Central
- Author
-
Nievas Offidani, Mauro Andres, primary and Delrieux, Claudio Augusto, additional
- Published
- 2023
- Full Text
- View/download PDF
4. Local texture descriptors for the assessment of differences in diffusion magnetic resonance imaging of the brain
- Author
-
Thomsen, Felix Sebastian Leo, Delrieux, Claudio Augusto, and de Luis-García, Rodrigo
- Published
- 2017
- Full Text
- View/download PDF
5. Algoritmos Avanzados de Adquisición y Procesamiento de Nubes de Puntos 3D para el Descubrimiento de Información en Mamíferos Marinos
- Author
-
Almonacid, Jonathan Samuel, primary, Delrieux, Claudio Augusto, primary, and Lewis, Mirtha Noemí, primary
- Published
- 2020
- Full Text
- View/download PDF
6. Generación de un DEM Usando PDI para la Extracción de Líneas de Agua en Imágenes Satelitales
- Author
-
Blanco Monroy, Katy Lorena, Revollo Sarmiento, Gisela Noelia, Revollo Sarmiento, Natalia Veronica, Delrieux, Claudio Augusto, and Perillo, Gerardo Miguel E.
- Subjects
IMAGE PROCESSING ,Zona Intermareal ,Procesamiento de imágenes ,Métodos de Interpolación ,Estuario de Bahía Blanca ,INTERPOLATION METHOD ,ZONA INTERMAREAL ,PROCESAMIENTO DE IMÁGENES ,lcsh:G1-922 ,MÉTODOS DE INTERPOLACIÓN ,BAHIA BLANCA ESTUARY ,Ciencias de la Tierra y relacionadas con el Medio Ambiente ,Ciencias de la Computación ,purl.org/becyt/ford/1 [https] ,INTERTIDAL ZONE ,purl.org/becyt/ford/1.5 [https] ,Ciencias de la Computación e Información ,ESTUARIO DE BAHÍA BLANCA ,Meteorología y Ciencias Atmosféricas ,lcsh:GB3-5030 ,lcsh:Physical geography ,lcsh:Geography (General) ,CIENCIAS NATURALES Y EXACTAS - Abstract
El método de extracción de la línea de agua es una de las herramientas más efectivas para el estudio de cambios en zonas de planicies de marea y líneas de costa. Entre otras aplicaciones, puede utilizarse para la elaboración de modelos digitales de elevación (DEM) de la zona sumergida si se cuenta con información suficiente y precisa. En este trabajo se presenta la aplicación de nuevos algoritmos de segmentación de líneas de agua para la construcción de un DEM de la zona intermareal interna del Estuario de Bahía Blanca. Se utilizaron imágenes Landsat-8 del año 2014, eligiéndose un conjunto representativo de imágenes en condiciones de marea suficientemente variadas. Se aplicaron estos nuevos algoritmos a cada imagen para segmentar la zona inundada. Posteriormente, se asoció cada línea de agua al dato disponible correspondiente a la altura de marea en la hora de toma de la imagen. Usando un sistema de información geográfico (SIG) se fusionaron las diferentes líneas de agua junto con sus alturas respectivas, y aplicando diferentes interpolaciones es posible generar el DEM. Con el fin de evaluar la precisión del modelo generado y validar los resultados, se cotejaron los valores obtenidos en sitios puntuales con datos batimétricos de gran precisión de una zona del Canal Principal del estuario, tomados durante una campaña realizada en 2014. Utilizando solo los puntos de la batimetría correspondientes a la zona intermareal para evaluar la precisión del DEM generado, se encontró una correlación con buen coeficiente de determinación entre las alturas estimadas por el DEM y la batimetría medida in situ . The waterline extraction method is an effective tool to study changes in tidal flats or shorelines. Among other applications, when adequate information is available, it can be taken advantage in the construction of Digital Elevation Models (DEMs) of the intertidal area. In this paper we present new waterline extraction algorithms, which are applied to generate a DEM of the internal intertidal zone in the Bahía Blanca Estuary. For this, waterlines from satellite images were extracted. We selected a set of Landsat-8 images generated in 2014 with representative tidal conditions. Initially, to identify the waterline, we developed and applied to each image a novel segmentation algorithm based on minimum distance to multiple prototypes, each pixel selected is representative either of water or land. With the segmented image, the contour of the waterline was extracted using a specific marching algorithm. Then, the tide height was associated to each waterline. The resulting geographic information, included in a GIS, was employed to generate the DEM using an interpolation method. To validate the accuracy of the model, we compared the height of the DEM at several point sites with bathymetric information gathered in an oceanographic cruise carried out in the same year. The results show a good correlation between the computed DEM and this in situ bathymetric information. Fil: Blanco Monroy, Katy Lorena. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto Argentino de Oceanografía. Universidad Nacional del Sur. Instituto Argentino de Oceanografía; Argentina Fil: Revollo Sarmiento, Gisela Noelia. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Investigaciones en Ingeniería Eléctrica ; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina Fil: Revollo Sarmiento, Natalia Veronica. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Investigaciones en Ingeniería Eléctrica ; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina Fil: Perillo, Gerardo Miguel E.. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto Argentino de Oceanografía. Universidad Nacional del Sur. Instituto Argentino de Oceanografía; Argentina. Universidad Nacional del Sur. Departamento de Geología; Argentina
- Published
- 2017
7. A new algorithm for estimating the rod volume fraction and the trabecular thickness from in vivo computed tomography
- Author
-
Thomsen, Felix Sebastian Leo, Peña, Jaime Andrés, Lu, Yongtao, Huber, Gerd, Morlock, Michael, Glüer, Claus Christian, and Delrieux, Claudio Augusto
- Subjects
Ingeniería de Sistemas y Comunicaciones ,FAILURE LOAD ,LOCAL FRACTAL DIMENSION ,TRABECULAR THICKNESS ,INGENIERÍAS Y TECNOLOGÍAS ,ROD VOLUME RATIO ,QCT ,Ingeniería Eléctrica, Ingeniería Electrónica e Ingeniería de la Información ,Ingeniería Médica - Abstract
Purpose: Existing microstructure parameters are able to predict vertebral in vitro failure load, but for noisy in vivo data more complex algorithms are needed for a robust assessment. Methods: A new algorithm is proposed for the microstructural analysis of trabecular bone under in vivo quantitative computed tomography (QCT). Five fractal parameters are computed: (1) the average local fractal dimension FD, (2) its standard deviation FD.SD, (3) the fractal rod volume ratio fRV/BV, (4) the average fractal trabecular thickness fTb.Th, and (5) its coefcient of variation fTb.Th.CV. The algorithm requires neither an explicit skeletonization of the trabecular bone, nor a well-defned transition between bone and marrow phases. Two experiments were conducted to compare the fractal with established microstructural parameters. In the frst, 20 volumes-of-interest of embedded vertebrae phantoms were scanned fve times under QCT and high-resolution (HR-)QCT and once under peripheral HRQCT (HRpQCT), to derive accuracy and precision. In the second experiment, correlations between in vitro HRQCT structural parameters were obtained from 76 human T11, T12, or L1 vertebrae. In vitro fracture data were available for a subset of 17 human T12 vertebrae so that linear regression models between failure load and microstructural HRQCT parameters could be analyzed. Results: The results showed correlations of fTb.Th and fRV/BV with their nonfractal pendants trabecular thickness (Tb.Th) and respective structure model index (SMI) while higher precision and accuracy was observed on the fractal measures. Linear models of bone mineral density with two and three fractal microstructural HRQCT parameters explained 86% and 90% (adjusted R2) of the failure load and signifcantly improved the linear models based only on BMD and established standard microstructural parameters (68%-77% adjusted R2). Conclusions: The application of fractal methods may grant further insight into the study of bone quality in vivo when image resolution and quality are less than optimal for current standard methods. Fil: Thomsen, Felix Sebastian Leo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina Fil: Peña, Jaime Andrés. University Hospital Schleswig‐Holstein; Alemania Fil: Lu, Yongtao. Universitat Hamburg; Alemania Fil: Huber, Gerd. Universitat Hamburg; Alemania Fil: Morlock, Michael. University Hospital Schleswig‐Holstein; Alemania Fil: Glüer, Claus Christian. University Hospital Schleswig‐Holstein; Alemania Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
- Published
- 2016
8. Realistic modeling of porous materials
- Author
-
Baravalle, Rodrigo Guillermo, Scandolo, Leonardo, Delrieux, Claudio Augusto, Garcia Bauza, Cristian Dario, and Eisemann, Elmar
- Subjects
DYNAMICAL SYSTEMS ,Ingeniería de Sistemas y Comunicaciones ,POROUS MATERIALS ,PHOTOREALISM ,INGENIERÍAS Y TECNOLOGÍAS ,Ingeniería Eléctrica, Ingeniería Electrónica e Ingeniería de la Información - Abstract
Photorealistic modeling and rendering of materials with complex internal mesostructure is a hard challenge in Computer Graphics. In particular, macroscopic porous materials consist of complex translucent substances that exhibit different details and light interaction at several different scales. State‐of‐the‐art techniques for modeling porous materials manage the material either as a surface and set up complex capture procedures or as a volume by employing different instances of procedural noise models for its representation. While the surface solution achieves several desired material properties, it still presents drawbacks in practical applications—high computational costs, complex capture procedures, and poor image variability, among others. Volumetric solutions are more flexible, but the final structure and appearance are difficult to control. To overcome these drawbacks, we propose an algorithm for the procedural generation of porous materials. The method is based on an artistic and physically inspired simulation of the growth of self‐avoiding bubbles inside a volume, by means of dynamical systems. The patterns induced by the bubbles can be easily and intuitively controlled. The bubbles adapt to any given shape and have convincing global and local fluid‐like patterns as seen in bread and sponges. Our method generates 3D textures that adequately represent porous materials, which can be used as input for creating realistic renderings of different porous objects. As a case study, we present the results of using these 3D textures as input to a direct volume renderer and show that they compare favorably with standard 3D texture synthesis methods. Fil: Baravalle, Rodrigo Guillermo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina Fil: Scandolo, Leonardo. Universidad Nacional de Rosario; Argentina. Delft University of Technology; Países Bajos Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina Fil: Garcia Bauza, Cristian Dario. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina Fil: Eisemann, Elmar. Delft University of Technology; Países Bajos
- Published
- 2016
9. Analyzing digital color descriptors in wheat
- Author
-
Salomón, Nelly, Missler, Verónica, Delrieux, Claudio Augusto, and Miranda, Rubén
- Subjects
ESPECTROFOTÓMETRO ,CIENCIAS AGRÍCOLAS ,IMAGEN DIGITAL ,Agricultura ,purl.org/becyt/ford/4.1 [https] ,COLOR ,INTERACCIÓN GENOTIPO AMBIENTE ,Agricultura, Silvicultura y Pesca ,purl.org/becyt/ford/4 [https] ,TRIGO - Abstract
El color es uno de los factores en la estimación de la calidad en muchos productos de la agricultura y alimentos. En la actualidad, la evaluación de color depende de juicios de expertos humanos. Éstos son subjetivos e inevitablemente afectados por las condiciones físicas, psicofisiológicas y por elementos ambientales. Para proporcionar objetividad y coherencia a la medición y a la expresión cuantitativa del color se requiere contar con instrumental adecuado. Sería de gran utilidad contar con herramientas que permitan un acercamiento a la vez práctico y preciso al tema de la evaluación cromá- tica de productos para consumo humano. En este trabajo se propone una metodología orientada hacia dicho propósito y al análisis de la influencia ambiental en este carácter en dos estaciones de crecimiento consecutivas en el cultivo de trigo. Se emplearon 18 cultivares, los cuales se muestrearon en dos momentos del ciclo del cultivo. Como primer examen se usó un espectrofotómetro y una cámara digital para el análisis de color en el estado fenológico de macollaje. Se encontró correlación entre ambas metodologías, lo cual haría más práctico el trabajo del mejorador al momento de la toma de datos. Se continuó el estudio de la Interacción Genotipo Ambiente (IGA) solo con cámara digital. El estado fenológico de macollaje no evidenció una marcada IGA. Por el contrario, en el estado de madurez fisiológica se encontró una apreciable IGA. Color is one of the factors used in quality estimation in many agricultural and food products. Currently, the evaluation of color depends on judgments made by human experts. These are subjective and inevitably affected by physical, physiological and environmental conditions. Suitable instrumental is required to provide objectivity and coherence to color measurements and quantitative expressions. It would be very useful to have tools that allow both practical and precise approaches to chromatic evaluation of products for human consumption. This work suggests a methodology which might contribute to solve that constraint and the analysis of environmental influences on this character in two consecutive wheat growing seasons. This research used 18 cultivars, which were sampled in two crop growth stages. On the first part of this study, a spectrophotometer and a digital camera were used for the analysis of color at the phenological state of tillering. Data analysis showed a correlation between both study methodologies, which would make more practical the work of breeders during data collection. The second part of the study of the genotype-environment interaction (GEI) continued using only a digital camera. The phenological state of tillering did not evidence a marked GEI. On the other hand, an appreciable GEI was found at physiological ripeness. Fil: Salomón, Nelly. Universidad Nacional del Sur. Departamento de Agronomía; Argentina Fil: Missler, Verónica. Universidad Nacional del Sur. Departamento de Agronomía; Argentina Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina Fil: Miranda, Rubén. Asociación de Cooperativas Argentinas; Argentina
- Published
- 2015
10. A new algorithm for estimating the rod volume fraction and the trabecular thickness from in vivo computed tomography
- Author
-
Thomsen, Felix Sebastian Leo, primary, Peña, Jaime Andrés, additional, Lu, Yongtao, additional, Huber, Gerd, additional, Morlock, Michael, additional, Glüer, Claus‐Christian, additional, and Delrieux, Claudio Augusto, additional
- Published
- 2016
- Full Text
- View/download PDF
11. Local texture descriptors for the assessment of differences in diffusion magnetic resonance imaging of the brain
- Author
-
Thomsen, Felix Sebastian Leo, primary, Delrieux, Claudio Augusto, additional, and de Luis-García, Rodrigo, additional
- Published
- 2016
- Full Text
- View/download PDF
12. Visual Analysis of Spatio-Temporal Data Applications in Weather Forecasting
- Author
-
Diehl, Alexandra, Pelorosso, L., Delrieux, Claudio Augusto, Saulo, Andrea Celeste, Ruiz, Juan Jose, Gröller, M. E., and Bruckner, S.
- Subjects
Ciencias de la Computación e Información ,Picture/image generation ,Viewing algorithms ,CIENCIAS NATURALES Y EXACTAS ,Ciencias de la Computación - Abstract
Weather conditions affect multiple aspects of human life such as economy, safety, security, and social activities. For this reason, weather forecast plays a major role in society. Currently weather forecasts are based on Numerical Weather Prediction (NWP) models that generate a representation of the atmospheric flow. Interactive visualization of geo-spatial data has been widely used in order to facilitate the analysis of NWP models. This paper presents a visualization system for the analysis of spatio-temporal patterns in short-term weather forecasts. For this purpose, we provide an interactive visualization interface that guides users from simple visual overviews to more advanced visualization techniques. Our solution presents multiple views that include a timeline with geo-referenced maps, an integrated webmap view, a forecast operation tool, a curve-pattern selector, spatial filters, and a linked meteogram. Two key contributions of this work are the timeline with geo-referenced maps and the curve-pattern selector. The latter provides novel functionality that allows users to specify and search for meaningful patterns in the data. The visual interface of our solution allows users to detect both possible weather trends and errors in the weather forecast model. We illustrate the usage of our solution with a series of case studies that were designed and validated in collaboration with domain experts. Fil: Diehl, Alexandra. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina Fil: Pelorosso, L.. Universidad de Buenos Aires; Argentina Fil: Delrieux, Claudio Augusto. Universidad Nacional del Sur; Argentina Fil: Saulo, Andrea Celeste. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinacion Administrativa Ciudad Universitaria. Centro de Investigaciones del Mar y la Atmósfera; Argentina Fil: Ruiz, Juan Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinacion Administrativa Ciudad Universitaria. Centro de Investigaciones del Mar y la Atmósfera; Argentina Fil: Gröller, M. E.. Vienna University of Technology; Austria Fil: Bruckner, S.. University Of Bergen; Noruega
- Published
- 2015
13. Modeling Video Activity with Dynamic Phrases and Its Application to Action Recognition in Tennis Videos
- Author
-
Vainstein, Jonathan Javier, Manera, José Francisco, Negri, Pablo Augusto, Delrieux, Claudio Augusto, and Maguitman, Ana Gabriela
- Subjects
Motion description ,Optical flow ,Ciencias de la Computación e Información ,Support vector ma- chines ,Conditional random fields ,Action recognition ,CIENCIAS NATURALES Y EXACTAS ,Ciencias de la Computación - Abstract
We present a novel approach to action recognition in tennis shot sequences. The underlying model considers the per-frame motion to be regarded as a word (within an alphabet of possible motions), and the sequence of frames as a phrase whose meaning is determined by the words given in a specific order. This feature extraction mechanism allows a semantic treatment of the classification stage using Conditional Random Fields. The system was applied on the RGB videos of the THETIS dataset, achieving an accuracy of over 86% in recognizing 12 different tennis shots among several takes produced by 55 different amateur and professional players. Fil: Vainstein, Jonathan Javier. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Bahía Blanca. Instituto de Investigación En Ingeniería Eléctrica; Argentina. Universidad Nacional del Sur. Departamento de Ingenieria Electrica y de Computadoras; Argentina. Universidad Nacional del Sur. Departamento de Cs.e Ing.de la Computacion; Argentina Fil: Manera, José Francisco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Bahía Blanca. Instituto de Investigación En Ingeniería Eléctrica; Argentina. Universidad Nacional del Sur. Departamento de Ingenieria Electrica y de Computadoras; Argentina. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computacion; Argentina Fil: Negri, Pablo Augusto. Universidad Argentina de la Empresa; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Bahía Blanca. Instituto de Investigación En Ingeniería Eléctrica; Argentina. Universidad Nacional del Sur. Departamento de Ingenieria Electrica y de Computadoras; Argentina. Universidad Nacional del Sur. Departamento de Cs.e Ing.de la Computacion; Argentina Fil: Maguitman, Ana Gabriela. Universidad Nacional del Sur. Departamento de Cs.e Ing.de la Computacion; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
- Published
- 2014
14. Modelado para la Renderización Foto-Realista de Pan
- Author
-
Baravalle, Rodrigo Guillermo, Scandolo, Leonardo, Delrieux, Claudio Augusto, and Garcia Bauza, Cristian Dario
- Subjects
Pan ,purl.org/becyt/ford/1 [https] ,Tiempo Real ,Ciencias de la Computación e Información ,purl.org/becyt/ford/1.2 [https] ,Direct Volume Rendering ,CIENCIAS NATURALES Y EXACTAS ,Ciencias de la Computación - Abstract
El modelado foto-realístico de materiales con una estructura interna compleja presenta varios desafíos en Computación Gráfica. Específicamente, la miga del pan es un material translúcido cuya estructura es porosa, mostrando detalles en distintas escalas. Si se pretende obtener resultados fotorealistas, deben modelizarse fenómenos tales como sombras internas, oclusión, transmitancia y absorción. La solución típica en estos casos es la aplicación directa de la ecuación del rendering, es decir, utilizar iluminación global (ray tracing, path tracing). Sin embargo, estos métodos presentan un costo computacional elevado y necesitan una malla 3D detallada del material. El estado del arte en renderización de materiales porosos utiliza un complejo procedimiento de captura donde la luz que es reflejada por el material es obtenida en distintos ángulos. Esa información es utilizada para reconstruir un modelo computacional del material. Si bien utilizando esta técnica es posible modelar alguna de las propiedades lumínicas deseadas, los costos computacionales asociados, el procedimiento de captura requerido y la baja variabilidad de la imagen resultante han provocado una dificultosa aplicación práctica del método. En este trabajo proponemos el estudio e implementación en GPU de un modelo basado en direct volume rendering sobre un campo escalar representando la estructura de la miga de pan sin utilizar estructuras intermedias. Las imágenes obtenidas muestran resultados promisorios en tiempo real. La miga es representada a través de un campo escalar 3D, el cual es computado en dos pasos. El primero utiliza una generación a través de sistemas de partículas, y el segundo aplica sistemas dinámicos para evolucionar las partículas, emulando el proceso de leudado y cocción del pan. Fil: Baravalle, Rodrigo Guillermo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina Fil: Scandolo, Leonardo. Universidad Nacional de Rosario. Facultad de Ciencias Exactas Ingeniería y Agrimensura. Escuela de Ciencias Exactas y Naturales. Departamento de Ciencias de la Computación; Argentina Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Investigaciones en Ingeniería Eléctrica "Alfredo Desages". Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras. Instituto de Investigaciones en Ingeniería Eléctrica "Alfredo Desages"; Argentina Fil: Garcia Bauza, Cristian Dario. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
- Published
- 2014
15. Bread crumb classification using fractal and multifractal features
- Author
-
Baravalle, Rodrigo Guillermo, Delrieux, Claudio Augusto, and Gómez, Juan Carlos
- Subjects
purl.org/becyt/ford/1 [https] ,Ciencias de la Computación e Información ,Support Vector Machines ,Bread Crumb ,purl.org/becyt/ford/1.2 [https] ,Multifractal ,Fractal ,Classification ,CIENCIAS NATURALES Y EXACTAS ,Ciencias de la Computación - Abstract
Adequate image descriptors are fundamental in image classification and object recognition. Main requirements for image features are robustness and low dimensionality which would lead to low classification errors in a variety of situations and with a reasonable computational cost. In this context, the identification of materials poses a significant challenge, since typical (geometric and/or differential) feature extraction methods are not robust enough. Texture features based on Fourier or wavelet transforms, on the other hand, do withstand geometric and illumination variations, but tend to require a high amount of descriptors to perform adequately. Recently, the theory of fractal sets has shown to provide local image features that are both robust and low-dimensional. In this work we apply fractal and multifractal feature extraction techniques for bread crumb classification based on colour scans of slices of different bread types. Preliminary results show that fractal based classification is able to distinguish different bread crumbs with very high accuracy. Fil: Baravalle, Rodrigo Guillermo. Universidad Nacional de Rosario. Facultad de Ciencias Exactas, Ingeniería y Agrimensura; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y Sistemas; Argentina Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Bahía Blanca. Instituto de Investigación en Ingeniería Eléctrica; Argentina. Universidad Nacional del Sur. Departamento de Ingenieria Electrica y de Computadoras; Argentina Fil: Gómez, Juan Carlos. Universidad Nacional de Rosario. Facultad de Ciencias Exactas, Ingeniería y Agrimensura; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y Sistemas; Argentina
- Published
- 2012
16. Superresolución: Reconstrucción de datos en 1D
- Author
-
Hernández, Sebastián Alejandro, primary and Delrieux, Claudio Augusto, additional
- Published
- 2014
- Full Text
- View/download PDF
17. Análise multivariada da forma de mandíbulas e dentes como ferramenta para identificação de espécies de tubarões na costa pernambucana
- Author
-
GUERRA, Glauce da Silva, DUARTE NETO, Paulo José, LESSA, Rosangela Paula Teixeira, CUNHA FILHO, Moacyr, ALBUQUERQUE, Cristiane Rocha, SILVA, Antonio Samuel Alves da, and DELRIEUX, Claudio Augusto
- Subjects
Rhizoprionodon porosus ,Carcharhinus leucas ,Tubarão ,Identificação das espécies ,Análise de imagens ,Análise multivariada ,Galeocerdo cuvier ,Carcharhinus limbatus ,Arcada dentária ,Morfometria ,PROBABILIDADE E ESTATISTICA [CIENCIAS EXATAS E DA TERRA] - Abstract
Submitted by (lucia.rodrigues@ufrpe.br) on 2022-12-05T12:40:41Z No. of bitstreams: 1 Glauce da Silva Guerra.pdf: 1795068 bytes, checksum: 3a5afed1e817d2e7c15e661645bea8f1 (MD5) Made available in DSpace on 2022-12-05T12:40:41Z (GMT). No. of bitstreams: 1 Glauce da Silva Guerra.pdf: 1795068 bytes, checksum: 3a5afed1e817d2e7c15e661645bea8f1 (MD5) Previous issue date: 2020-02-21 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES Sharks have low resilience and require a very high energy demand due to their swimming activities, so they are always looking for food and although humans are not included in their diet, incidents end up happening. Due to these occurrences in Pernambucano’s coast, there was a need to identify the species, given a large number of reported cases without species identification in this region. Thus, this study aimed to identify, among the related species, differences and similarities of their dental arches, using both 2D and 3D templates and images. To do so, dental arches of several shark species were obtained from the acquisition of the head of specimens landed by the artisanal fleet of Pernambuco and, soon after, were taken to the laboratory to make clay templates. Subsequently, these molds and images (2D-3D) were used to study separately the contour of the curvature of the upper and lower mandibles, as well as the interdental distance marked on the templates and obtained directly from the dental arches. From the photos made with a camera, it was possible, not only identifying which species resemble and which differ but also observe where there is a greater variation between species. In summary, we see that Carcharhinus limbatus are similar in shape, width, and distance from end to end. The Galeocerdo curvier mandible curvature contour differs from all others. A pattern of proximity between the flat-headed shark (Carcharhinus leucas) and the tiger shark (Galeocerdo cuvier) has been revealed. Understanding the pattern of the arcade and bite form of shark species is an initial and vital step in the study of human incidents since through these results it will be possible to identify the main species involved in the incidents and then to start thinking about sustainable management proposals for the communities involved. Os tubarões apresentam baixa resiliência e exigem uma demanda muito grande de energia devido as suas atividades natatórias, consequentemente estão sempre em busca de alimento e, embora humanos não estejam incluídos em sua alimentação, incidentes acabam acontecendo. Devido a essas ocorrências na Costa Pernambucana houve a necessidade de identificar as espécies, tendo em vista o grande número de casos relatados sem identificação destas nesta região. Sendo assim, este estudo objetivou identificar, entre as espécies neste relacionadas, diferenças e similaridades de suas arcadas, por meio de moldes e imagens tanto em 2D quanto em 3D. Para isso, arcadas de diversas espécies de tubarões foram obtidas a partir da aquisição da cabeça de exemplares desembarcados pela frota artesanal de Pernambuco e, logo em seguida, foram levadas a laboratório para realização de moldes de argila. Em seguida, os referidos moldes e imagens (2D-3D) foram utilizadas para estudar, individualmente, o contorno da curvatura das mandíbulas superiores e inferiores, bem como a distância interdental marcada nos moldes e obtidas diretamente das arcadas. A partir das fotos feitas com câmera fotográfica, foi possível, além de identificar quais espécies se assemelham e quais se diferenciam, observar onde há maior variação entre as espécies. Em síntese, vemos que o Carcharhinus limbatus e Rhizoprionodon porosus apresentam semelhança de forma, de largura e de distância ponta a ponta. O contorno da curvatura da mandíbula do Galeocerdo cuvier difere de todas as outras. Foi revelado um padrão de proximidade entre o tubarão cabeça-chata (Carcharhinus leucas) e o tubarão-tigre (Galeocerdo cuvier). A compreensão do padrão da forma das arcadas e mordeduras das espécies de tubarões é um passo inicial e vital no estudo dos incidentes com humanos, pois através desses resultados será possível identificar quais as principais espécies que estão envolvidas nos incidentes e, a partir daí, começar a pensar em propostas de manejo sustentável para as comunidades envolvidas.
- Published
- 2020
18. Tomografia computadorizada aplicada a otólitos em 3D
- Author
-
VASCONCELOS FILHO, Jonas Eloi de, DUARTE NETO, Paulo José, DELRIEUX, Claudio Augusto, FERREIRA, Beatrice Padovani, ANTONINO, Antonio Celso Dantas, STOSIC, Borko, and LIMA, João Paulo Silva do Monte
- Subjects
Tomografia computadorizada ,Otólitos sagittae ,Estoque pesqueiro ,Imagem 3D ,PROBABILIDADE E ESTATISTICA [CIENCIAS EXATAS E DA TERRA] - Abstract
Submitted by Mario BC (mario@bc.ufrpe.br) on 2019-07-31T13:29:07Z No. of bitstreams: 1 Jonas Eloi de Vasconcelos Filho.pdf: 4779575 bytes, checksum: 478011721d09675217cc0fd9954cca75 (MD5) Made available in DSpace on 2019-07-31T13:29:07Z (GMT). No. of bitstreams: 1 Jonas Eloi de Vasconcelos Filho.pdf: 4779575 bytes, checksum: 478011721d09675217cc0fd9954cca75 (MD5) Previous issue date: 2019-02-26 Conselho Nacional de Pesquisa e Desenvolvimento Científico e Tecnológico - CNPq Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES Otoliths are called "black box" because they are sources of biological information that can be applied to the evaluation and management of fish stocks. And, one of the ways to study them is from analysis of images. However, 2D images have already been extensively explored, despite losing information because otoliths are a 3D object. Thus, the present study aimed to apply computed tomography to analyze otoliths sagittae. From 15 configurations of the tomographic parameters, it was concluded that average voltages (70 and 80 kV) with aluminum filters with 0.5 mm thickness are optimal for the acquisition of tomographic images of otoliths. These images were then explored internally and externally, with applications in growth ring counts, ontogeny, species comparisons, and, in the future, layered segmentation using the density difference. In addition, internal cavities were found in individuals of the genus Thunnus. The curvature of the surface of the otoliths was also analyzed in order to test the capacity of discrimination between species, ontogenetic variation and as a tool of segmentation of sulcus acusticus. It was found that the Mean and RMS curvature attributes can be used as a unique signature by species, besides discerning peaks and valleys in the relief of otoliths. And, from this, relate its complexity to the metabolism of individuals, as a reflection of age. In addition, with 3D segmentation, it will be possible to describe not only the area of the sulcus, but also its depth and volume. Therefore, this thesis will serve as a basis for future studies of 3D image analysis of otoliths and some applications. Otólitos são chamados de "black box"devido serem fontes de informações biológicas que podem ser aplicadas a avaliação e manejo de estoques pesqueiros. E, uma das maneiras de estudá-los é a partir de análises de imagens. Entretanto, as imagens em 2D já foram exaustivamente exploradas, apesar de perderem informações devido os otólitos serem um objeto em 3D. Assim, o presente estudo objetivou em aplicar tomografia computadorizada para analisar otólitos sagittae. A partir de 15 configurações dos parâmetros tomográficos, concluiu-se que voltagens médias (70 e 80 kV) com filtro de alumínio com 0,5 mm de espessura são ótimos para a aquisição de imagens tomográficas de otólitos. Em seguida, estas imagens foram exploradas internamente e externamente, com aplicações em contagens de anéis de crescimento, ontogenia, comparação entre espécies e, futuramente, segmentação em camadas usando a diferença de densidades. Ademais, verificou-se a presença de cavidades internas nos indivíduos do gênero Thunnus. Também foi analisada a curvatura da superfície dos otólitos, afim de testar a capacidade de discriminação entre espécies, variação ontogenética e como ferramenta de segmentação do sulcus acusticus. Constatou-se que os atributos de curvatura Mean e RMS podem serem usados como assinatura única por espécie, além de discernir picos e vales no relevo dos otólitos. E, a partir disto, relacionar sua complexidade com o metabolismo dos indivíduos, como reflexo da idade. Além disso, com a segmentação em 3D será possível descrever não só a área do sulcus, mas também sua profundidade e volume. Portanto, esta tese servirá como base para estudos futuros de análise de imagens em 3D de otólitos e algumas aplicação.
- Published
- 2019
19. Deep Landmarking: Reconocimiento automático de estructuras anatómicas por medio de morfometría geométrica
- Author
-
Cintas, Celia and Delrieux, Claudio Augusto
- Subjects
purl.org/becyt/ford/1 [https] ,Morfometría geométrica ,Image processing ,Ciencias de la Computación e Información ,Conv nets ,Deep learning ,purl.org/becyt/ford/1.2 [https] ,CIENCIAS NATURALES Y EXACTAS ,Ciencias de la Computación - Abstract
La adquisición de información fenotípica es un aspecto clave en diversos contextos, incluyendo análisis biométricos, estudios bioantropológicos, investigaciones biomédicas, y ciencia forense por citar algunos.Para ello se requiere la identificación automática de estructuras anatómicas de interés biométrico, como por ejemplo huellas dactilares, patrones en el iris, o rasgos faciales.Estas estructuras son utilizadas masivamente, pero poseen la desventaja de requerir intrusión para adquirir la información a ser analizada.En esta tesis presentamos un nuevo método, basado en la Morfometría Geométrica, para la detección y extacción automática de datos anatómicos característicos (features) en la forma de hitos (landmarks) en 2D o 3D.Para ello se entrenó una red neuronal con conjuntos de datos obtenidos en forma supervisada por medio de expertos antropólogos y biólogos. El sistema resultante posee la capacidad de realizar landmarking en forma automática en imágenes y video sin preparación previa, obteniéndose parámetros de calidad equivalente o superiores a los adquiridos por expertos humanos.Estos resultados abren la posibilidad de generar en forma automática y confiable vectores de atributos basados en propiedades fenotípicas.Se exploran algunas aplicaciones en diversos contextos incluyendo biometría, videojuegos, interfases naturales y otras aplicaciones. Accurate gathering of phenotypic information is a key aspect in several subject matters, including biometric identification, biomedical analysis, bioanthropology studies, forensics, and many other. Automatic identification of anatomical structures of biometric interest, such as fingerprints, iris patterns, or facial traits, are extensively used in applications like access control, anthropological research, and surveillance, all having in common the drawback of requiring intrusive means for acquiring the required information. In this thesis we present a new method, based on two well established methodologies, Geometric Morphometrics and Deep Learning algorithms, for automatic phenotype detection and feature extraction in the form of 2D and 3D landmarks. A convolutional neural network was trained with a set of manually landmarked examples. The trained network is able to provide morphometric landmarks on images automatically, with a performance that matches human assisted landmarking. The ability to perform in the open (i.e., in images or video taken with no specific acquisition preparation). The feasibility of using landmarks as feature vectors for different classifications tasks is explored in a novel spectrum of biometrics, video games, and natural user interfaces applications. Fil: Cintas, Celia. Universidad Nacional del Sur; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina. Autor
- Published
- 2017
20. Dataset of clinical cases, images, image labels and captions from open access case reports from PubMed Central (1990-2023).
- Author
-
Nievas Offidani MA and Delrieux CA
- Abstract
This paper details the acquisition, structure and preprocessing of the MultiCaRe Dataset, a multimodal case report dataset which contains data from 75,382 open access PubMed Central articles spanning the period from 1990 to 2023. The dataset includes 96,428 clinical cases, 135,596 images, and their corresponding labels and captions. Data extraction was performed using different APIs and packages such as Biopython, requests, Beautifulsoup, BioC API for PMC and EuropePMC RESTful API. Image labels were created based on the contents of their corresponding captions, by using Spark NLP for Healthcare and manual annotations. Images were preprocessed with OpenCV in order to remove borders and split figures containing multiple images, data were analyzed and described, and a subset was randomly selected for quality assessment. The dataset's structure allows for seamless integration of different types of data, making it a valuable resource for training or fine-tuning medical language, computer vision or multi-modal models., (© 2023 The Author(s).)
- Published
- 2023
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.