Now showing items 1-20 of 52

    • 3D imaging techniques for characterising microcracks in cement-based materials 

      Mac, Monika Jolanta; Yio, Marcus H.N.; Desbois, Guillaume; Casanova Hormaechea, Ignasi; Wong, Hong S.; Buenfeld, Nick R. (2021-02)
      Article
      Open Access
      Concrete inherently contains pores and microcracks that can adversely impact its mechanical properties and long-term durability. However, characterising microcracks is difficult due to their complex, multiscale and ...
    • A quaternion deterministic monogenic CNN layer for contrast invariance 

      Moya Sánchez, Eduardo Ulises; Xambó Descamps, Sebastián; Salazar Colores, Sebastián; Sánchez-Pérez, Abraham; Cortés García, Claudio Ulises (Springer, 2021)
      Part of book or chapter of book
      Open Access
      Deep learning (DL) is attracting considerable interest as it currently achieves remarkable performance in many branches of science and technology. However, current DL cannot guarantee capabilities of the mammalian visual ...
    • A trainable monogenic ConvNet layer robust in front of large contrast changes in image classification 

      Moya Sánchez, Eduardo Ulises; Xambó Descamps, Sebastián; Sánchez-Pérez, Abraham; Salazar Colores, Sebastián; Cortés García, Claudio Ulises (Institute of Electrical and Electronics Engineers (IEEE), 2021-12-20)
      Article
      Open Access
      Convolutional Neural Networks (ConvNets) at present achieve remarkable performance in image classification tasks. However, current ConvNets cannot guarantee the capabilities of the mammalian visual systems such as invariance ...
    • An approach for physiological motion compensation in robotic-assisted cardiac surgery 

      Avilés Rivero, Angélica Ivone; Sobrevilla Frisón, Pilar; Casals Gelpi, Alicia (2014-11-14)
      Article
      Open Access
      The lack of physiological motion compensation is a major problem in robotic-assisted cardiac surgery. Since the heart is beating while the surgeon carried out the procedure, dexterity of the surgeon’s and precision are ...
    • An approximation of the K-function for the study of binary images 

      Ayala Gallego, Guillermo; Simó Vidal, Amelia (Institut d'estadística de Catalunya, 1993)
      Article
      Open Access
      Jensen et al. (1990) gave an exact expression for the K-function in non-overlapping Boolean models. The present study proposes and evaluates an approximate expression for the K-function in overlapping isotropic Boolean ...
    • Anàlisi digital d'imatges de formes eritrocitàries anòmales 

      Pladevall Viladecans, Clara (Universitat Politècnica de Catalunya, 2017-06)
      Bachelor thesis
      Restricted access - author's decision
      Un total de 300.000 nens neixen cada any al món amb una hemoglobinopatia major, inclosa l’Hemoglobinopatia S (HbS), que constitueix una de les alteracions genètiques més freqüents en determinats països. Aquesta alteració ...
    • Application of geometric-morphometric, hypersdectral imaging and molecular makers to the study of depth-driven diferences in populations of decapods (crustacea) 

      Aguzzi, Jacopo; Costa, Corrado; Batista Company, Juan; Antonucci, Francesca; Pallottino, Federico; Menesatti, Paolo; Canali, Emiliano; Giorgi, Stefano; Angelini, Claudio; Ketmaier, Valerio (SARTI (Technological Development Centre of Remote Acquisition and Data processing Systems), 2010-04-26)
      Article
      Open Access
    • Applying deep learning for food image analysis 

      Asenjo Ponce de León, Marc (Universitat Politècnica de Catalunya, 2020-04)
      Master thesis
      Open Access
      With the increasing availability of data on the internet, deep learning techniques have been on the rise these past decade. Food images specifically are one of the most commonly shared types of image on social media. ...
    • Autoclaved cellulose fibre reinforced cement: effects of silica fume 

      Fernández Carrasco, Lucía; Claramunt Blanes, Josep; Ardanuy Raso, Mònica (2014-07-01)
      Article
      Restricted access - publisher's policy
      With the aim of developing vegetable-fibre cement composites free of portlandite and with short curing process, this study analyses the influence of the curing conditions and the addition of pozzolanic material on the ...
    • Automated image analysis for single-atom detection in catalytic materials by transmission electron microscopy 

      Mitchell, Sharon; Parés Pont, Ferran; Faust Akl, Dario; Collins, Sean; Kepaptsoglou, Demie; Ramasse, Quentin; Garcia Gasulla, Dario; Pérez Ramírez, Javier; López Alonso, Nuria (2022-03-25)
      Article
      Restricted access - publisher's policy
      Single-atom catalytic sites may have existed in all supported transition metal catalysts since their first application. Yet, interest in the design of single-atom heterogeneous catalysts (SACs) only really grew when advances ...
    • Automated location of active fire perimeters in aerial infrared imaging using unsupervised edge detectors 

      Valero Pérez, Mario Miguel; Rios, Oriol; Pastor Ferrer, Elsa; Planas Cuchi, Eulàlia (2018-04-23)
      Article
      Open Access
      A variety of remote sensing techniques have been applied to forest fires. However, there is at present no system capable of monitoring an active fire precisely in a totally automated manner. Spaceborne sensors show too ...
    • Automatic measurements of partial cover factors and yarn diameters in fabrics using image processing 

      Tapias Anton, Montserrat; Rallo Capdevila, Miguel; Escofet Soteras, Jaume (2011-01)
      Article
      Restricted access - publisher's policy
    • Building graph representations of deep vector embeddings 

      Garcia Gasulla, Dario; Vilalta Arias, Armand; Parés Pont, Ferran; Moreno Vázquez, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Association for Computational Linguistics, 2017)
      Conference lecture
      Open Access
      Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector ...
    • Cabled video-observatory monitoring of seasonal rhythms in a Mediterranean coastal fish community 

      Condal, Fernando; Aguzzi, Jacopo; Sardà Amills, Francesc; Nogueras Cervera, Marc; Cadena Muñoz, Francisco Javier; Manuel Lázaro, Antonio (2020-11-19)
      Research report
      Open Access
      The obtention of time series in the structure and biodiversity of marine populations is of great interest in spite of increasing anthropic perturbations of direct type (e.g. fishing or littering) or of more indirect nature ...
    • Caracterització de la hidrodinàmica litoral amb dades de vídeo d'UAV 

      Nievas Salguero, Oscar Samuel (Universitat Politècnica de Catalunya, 2022-10-24)
      Bachelor thesis
      Open Access
      This work aims to explore the potential of UAV-captured videos for the characterization of shoreline dynamics at time scales of seconds to minutes. A 2 min video recorded by a UAV at Playa de la Victoria in Cádiz, on a day ...
    • Color based image classification and description 

      Laencina Verdaguer, Sergi (Universitat Politècnica de Catalunya, 2009-10-20)
      Master thesis
      Open Access
    • Colour calibration for quantitative biological analysis: A novel automated multivariate approach. 

      Costa, Corrado; Pallottino, Federico; Angelini, Claudio; Proietti, Marco; Capoccioni, Fabrizio; Aguzzi, Jacopo; Antonucci, Francesca; Menessati, Paolo (SARTI (Technological Development Centre of Remote Acquisition and Data processing Systems), 2010-04-13)
      Article
      Open Access
      This work proposed a novel approach to practical use of digital photography for biological purposes.
    • Cultural event recognition with visual ConvNets and temporal models 

      Salvador Aguilera, Amaia; Manchon Vizuete, Daniel; Calafell, Andrea; Giró Nieto, Xavier; Zeppelzauer, Matthias (2015)
      Conference lecture
      Open Access
      This paper presents our contribution to the ChaLearn Challenge 2015 on Cultural Event Classification. The challenge in this task is to automatically classify images from 50 different cultural events. Our solution is based ...
    • Deep convolutional neural network architecture for effective Image analysis 

      Ros Martí, Marc (Universitat Politècnica de Catalunya, 2017)
      Master thesis
      Open Access
      Covenantee:   Kungliga Tekniska högskolan
      This master thesis presents the process of designing and implementing a CNN-based architecture for image recognition included in a larger project in the field of fashion recommendation with deep learning. Concretely, the ...
    • Diseño de un nuevo prototipo de medida de granulometría por análisis de imagen 

      Andrieu, Yann (Universitat Politècnica de Catalunya, 2013-06)
      Master thesis (pre-Bologna period)
      Open Access
      Las medidas de granulometría son un medio eficaz para controlar el buen funcionamiento del proceso de fabricación de los azúcares. Sin embargo, las técnicas de granulometría actuales, como la del tamizado, se aplican bien ...