Now showing items 1-5 of 5

    • Icon

      Extracción de características en imágenes de rayos X de cuadros  [Master's Thesis]

      Velasco Montero, Delia (2016)
      El análisis de imágenes de placas de rayos X capturadas de pinturas de cuadros permite la caracterización del tipo de tela usada por el pintor. Este trabajo se enfoca en la extracción de características relevantes que ...
    • Icon

      On the Correlation of CNN Performance and Hardware Metrics for Visual Inference on a Low-Cost CPU-based Platform  [Presentation]

      Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (Institute of Electrical and Electronics Engineers, 2019)
      While providing the same functionality, the various Deep Learning software frameworks available these days do not provide similar performance when running the same network model on a particular hardware platform. On the ...
    • Icon

      On-The-Fly Deployment of Deep Neural Networks on Heterogeneous Hardware in a Low-Cost Smart Camera  [Presentation]

      Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (Association for Computing Machinery, 2018)
      This demo showcases a low-cost smart camera where different hardware configurations can be selected to perform image recognition on deep neural networks. Both the hardware configuration and the network model can be changed ...
    • Icon

      Optimum Selection of DNN Model and Framework for Edge Inference  [Article]

      Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (IEEE, 2018)
      This paper describes a methodology to select the optimum combination of deep neuralnetwork and software framework for visual inference on embedded systems. As a first step, benchmarkingis required. In particular, we have ...
    • Icon

      Performance Analysis of Real-Time DNN Inference on Raspberry Pi  [Article]

      Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (SPIE, 2018)
      Deep Neural Networks (DNNs) have emerged as the reference processing architecture for the implementation of multiple computer vision tasks. They achieve much higher accuracy than traditional algorithms based on shallow ...