Portuguese Chapter Conference

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2632931

Browse

Browsing Portuguese Chapter Conference by Subject "!"

Now showing 1 - 10 of 10
  • No Thumbnail Available
    Item
    BlenderCAVE: Easy VR Authoring for Multi-Screen Displays
    (The Eurographics Association, 2021) Gascón, Jorge; Bayona, José M.; Espadero, José M.; Otaduy, Miguel A.; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    BlenderCave is a framework for the fast creation of virtual reality applications for multi-screen display systems. It consists of a set of extensions to the open-source Blender Game Engine (BGE), leveraging the scene creation and real-time rendering capabilities of BGE, and augmenting them with easy-to-setup support for CAVE or Powerwall-type displays. The framework is implemented in a distributed manner, and it contains a virtual camera setup to control the display output, and a lightweight network communication protocol to manage events and synchronize the application state. We demonstrate that, with BlenderCAVE, 3D applications can easily be written in Blender and displayed on multi-screen displays.
  • No Thumbnail Available
    Item
    A Colour Rotation Based Detector for Bleeding Gastric Pathologies
    (The Eurographics Association, 2021) Coelho, P.; Cunha, A.; Costa, P.; Hadjileontiadis, L.; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    Colour is one the distinct features in computer vision systems and can be represented in several colour spaces. The most commonly used is the RGB colour space, since most high-quality cameras used in computer vision systems provide RGB signals, for example endoscopic capsule cameras. This work describes a computer vision algorithm intended to assist the physician in the diagnosis of endoscopic diseases, such as gastrointestinal bleeding, using a colour space rotation-based method. This algorithm modifies the images RGB representation channels in such way that the bleeding information can be effectively enhanced in a single channel. Tests in endoscopic images were performed and results have shown that the proposed colour-based rotation approach successfully increases the detection of bleeding regions in endoscopic images, corroborating the usefulness in physician diagnosis assistance.
  • No Thumbnail Available
    Item
    Courseware Reuse or Courseware to Reuse?
    (The Eurographics Association, 2023) Teixeira, José Carlos; Páris, César; Madeira, Joaquim; Lopes, J. Brisson; José Carlos Teixeira; Werner Hansmann; Michael B. McGrath
  • No Thumbnail Available
    Item
    Graph-Based Reflectance Segmentation
    (The Eurographics Association, 2021) Garces, Elena; Gutierrez, Diego; Lopez-Moreno, Jorge; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    Most of the unsupervised image segmentation algorithms use just RGB color information in order to establish the similarity criteria between pixels in the image. This leads in many cases to a wrong interpretation of the scene since these criteria do not consider the physical interactions which give raise to of those RGB values (illumination, geometry, albedo) nor our perception of the scene. In this paper, we propose a novel criterion for unsupervised image segmentation which not only relies on color features, but also takes into account an approximation of the materials reflectance. By using a perceptually uniform color space, we apply our criterion to one of the most relevant state of the art segmentation techniques, showing its suitability for segmenting images into small and coherent clusters of constant reflectance. Furthermore, due to the wide adoption of such algorithm, we provide for the first time in the literature an evaluation of this technique under several scenarios and different configurations of its parameters. Finally, in order to enhance both the accuracy of the segmentation and the inner coherence of the clusters, we apply a series of image processing filters to the input image (median, mean-shift, bilateral), analyzing their effects in the segmentation process. Our results can be transferred to any image segmentation algorithm.
  • No Thumbnail Available
    Item
    GraphJudge: A System for Assisted Assessment of Computer Graphics Assignments
    (The Eurographics Association, 2021) Rocha, Lindomar; Rodrigues, Rui; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    We describe a system for submission, automated validation and assisted evaluation of Computer Graphics' assignments. This type of assessments has a series of specific challenges associated to it, namely the analysis of graphical output and the variations between implementation in different development platforms and operating systems. When considering a large number of submitted programs (in the order of hundreds), preparing and evaluating the submissions quickly becomes a very time-consuming task. The goals of the system are therefore to allow submission and early validation for the students, and to ease the teachers' burden of compiling and executing, while automatically providing visual information of the submissions in an integrated and effective way.
  • No Thumbnail Available
    Item
    Interactive Visualizations of Automatic Debugging Reports
    (The Eurographics Association, 2021) Riboira, André; Rodrigues, Rui; Abreu, Rui; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    Automated debugging techniques, based on statistical analysis of historical test executions data, have recently received considerable attention due to their diagnostic capabilities. However, current automatic debugging tools suffer from a common shortcoming that may affect their adoption and correct use: the lack of effective visualizations of their output. This paper explores the use of interactive visualization techniques applied to automatic debugging results, and integrated in a common development environment (Eclipse), to improve the efficiency of the debugging process. The proposed tool – GZOLTAR– is an Eclipse plug-in that includes an automatic debugging algorithm and generates interactive visualizations of the resulting hierarchical data, with direct links to the IDE's source code editor.
  • No Thumbnail Available
    Item
    Investigating the Differences Between European Portuguese Sounds: An Approach Using Polygonal Mesh Comparison
    (The Eurographics Association, 2021) Martins, Paula; Silva, Samuel; Oliveira, Catarina; Ferreira, Carlos; Silva, Augusto; Teixeira, António; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    With the main purpose of studying the articulatory configuration of the European Portuguese (EP) sounds and to evaluate coarticulatory effects, a large 3D MRI database from several speakers and contexts have been acquired. Segmentation, visualization and interpretation of all the available data, essential to a detailed characterization of these sounds, are complex and time-consuming tasks. To perform the segmentation, a semi-automatic method was used. Meshes of the tongue were created from the segmented volumes and a polygonal mesh comparison tool (PolyMeCo) was used to compare: different sounds, the same sound produced in different contexts and syllabic positions, and productions from different speakers, providing a qualitative measure of these differences. To the best of our knowledge this is the first study in the literature using such an approach to analyze and compare tongue shape. Furthermore, these first results are very promising allowing a proper analysis and depiction of the main differences between EP sounds and further insight into their production.
  • No Thumbnail Available
    Item
    Left-Ventricle Global and Regional Functional Analysis from MDCT Images
    (The Eurographics Association, 2021) Silva, Samuel; Santos, Beatriz Sousa; Madeira, Joaquim; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    Left-ventricle functional analysis is of paramount importance for the assessment of coronary artery disease. Non-invasive coronary artery imaging using multiple-detector computed tomography (MDCT) provides a wealth of data concerning multiple cardiac phases. These have still to be explored in order to assess if further insight is possible regarding regional and functional analysis of the left ventricle leading to a more informed diagnosis and prognosis. Following on previous work regarding left-ventricle segmentation of all available cardiac phases in MDCT exams this article presents several parameters characterizing global and regional left ventricle function, computed for several cardiac phases and represented over time. Synchronized viewing of the different parameters is also supported.
  • No Thumbnail Available
    Item
    Mobile Computational Photography: Exposure Fusion on the Nokia N900
    (The Eurographics Association, 2021) Echevarria, Jose I.; Gutierrez, Diego; Silva, F. and Gutierrez, D. and Rodríguez, J. and Figueiredo, M.
    This paper explores the Nokia N900 platform as a versatile playground for mobile computational photography. We present the implementation of a simple yet practical application to acquire high quality tone mapped HDR images, and a relatively straightforward white balance selection. We have built everything from scratch: from the capture of the bracketed sequence of images with different exposures, to the final tone mapping algorithm. Completed in less than one week, showcasing the flexibility and productivity of the platform, our experiments have encouraged us to continue exploring all the possibilities this kind of devices offer.
  • No Thumbnail Available
    Item
    Modularity: The Key to Courseware Re-use
    (The Eurographics Association, 2023) Teixeira, José Carlos; José Carlos Teixeira; Werner Hansmann; Michael B. McGrath
    By courseware modularity we mean the possibility to build complete courses from many small course modules fitting together. ln contrast to puzzle pieces, course modules should be designed to fit into many different situations, allowing different courses to be produced. This goal introduces a lot of problems to be solved, like organisation (hierarchical) of the material, formats' compatibility, clear separation between contents, structure and presentation, ...