Now showing items 1-19 of 19

    • IconA Real-Time, Event Driven Neuromorphic System for Goal-Directed Attentional Selection  [Article]

      Gallupi, Francesco; Brohan, Kevin; Davidson, Simón; Serrano Gotarredona, Teresa; Pérez Carrasco, José Antonio; Linares Barranco, Bernabé; Furber, Steve (Springer Verlag, 2012)
      Computation with spiking neurons takes advantage of the abstraction of action potentials into streams of stereotypical events, which encode information through their timing. This approach both reduces power consumption ...
    • IconAnálisis de la aplicación de algoritmos de K-means y Continuous Max-Flow a la segmentación de imágenes en color  [Final Degree Work]

      Pinto Sánchez-Matamoros, Luis Fernando (2015)
      En el campo del procesamiento de imagen se realizan cada año numerosos avances en relación a los algoritmos y técnicas para el tratamiento y segmentación de imágenes. En este trabajo se propondrá un uso conjunto de dos ...
    • IconClasificación de imágenes usando redes neuronales convolucionales en Python  [Final Degree Work]

      Artola Moreno, Álvaro (2019)
      En los último años se han generalizado en nuestro lenguaje y en numerosas acciones cotidianas que desarrollamos cuando accedemos a Internet o utilizamos dispositivos tecnológicos los conceptos de Inteligencia Artificial ...
    • IconClasificación de lesiones de piel basada en filtros de Gabor y color  [Presentation]

      Pérez Carrasco, José Antonio; Serrano Gotarredona, María del Carmen; Acha Piñero, Begoña (Sociedad española de ingeniería biomédica, 2009)
      Cuando se pretende diagnosticar un posible cáncer de piel, los médicos evalúan la lesión siguiendo diferentes reglas. Aunque la más famosa es la regla ABCD (Asimetría, Borde, Color, Diámetro), una técnica muy empleada ...
    • IconClustering learning for robotic vision  [Presentation]

      Culurciello, Eugenio; Bates, Jordan; Dundar, Aysegul; Pérez Carrasco, José Antonio; Farabet, Clément (2013)
      We present the clustering learning technique applied to multi-layer feedforward deep neural networks. We show that this unsupervised learning technique can compute network filters with only a few minutes and a much reduced ...
    • IconEfficient feedforward categorization of objects and human postures with address-event image sensors  [Article]

      Chen, Shoushun; Akselrod, Polina; Zhao, Bo; Pérez Carrasco, José Antonio; Linares Barranco, Bernabé; Culurciello, Eugenio (Institute of Electrical and Electronics Engineers, 2012)
      This paper proposes an algorithm for feedforward categorization of objects and, in particular, human postures in real-time video sequences from address-event temporal-difference image sensors. The system employs an innovative ...
    • IconFast vision through frameless event-based sensing and convolutional processing: Application to texture recognition  [Article]

      Pérez Carrasco, José Antonio; Acha Piñero, Begoña; Serrano Gotarredona, María del Carmen; Camuñas Mesa, Luis Alejandro; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé (Institute of Electrical and Electronics Engineers, 2010)
      Address-event representation (AER) is an emergent hardware technology which shows a high potential for providing in the near future a solid technological substrate for emulating brain-like processing structures. When used ...
    • IconMapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate-Coding and Coincidence Processing. Application to Feed-Forward ConvNets  [Article]

      Pérez Carrasco, José Antonio; Zhao, Bo; Serrano Gotarredona, María del Carmen; Acha, Begoña; Serrano Gotarredona, Teresa; Cheng, Shouchun; Linares Barranco, Bernabé (Institute of Electrical and Electronics Engineers (IEEE), 2013)
      Event-driven visual sensors have attracted interest from a number of different research communities. They provide visual information in quite a different way from conventional video systems consisting of sequences of ...
    • IconOn spike-timing-dependent-plasticity, memristive devices, and building a self-learning visual cortex  [Article]

      Zamarreño Ramos, Carlos; Camuñas Mesa, Luis Alejandro; Pérez Carrasco, José Antonio; Masquelier, T.; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé (Frontiers Media, 2011)
      In this paper we present a very exciting overlap between emergent nanotechnology and neuroscience, which has been discovered by neuromorphic engineers. Specifically, we are linking one type of memristor nanotechnology ...
    • IconProcesamiento de actividad cerebral en Pez Carpa Dorada mediante Matlab  [Final Degree Work]

      González Santalla, Francisco Javier (2019)
      Uno de los temas principales en neurociencia es el análisis de la conectividad funcional entre diferentes áreas del cerebro. Actualmente, las técnicas para registrar la actividad neuronal mediante VSDI (Imagen Tintada ...
    • IconProcesamiento mediante Matlab de imágenes de actividad cerebral en pez Carpa Dorada  [Final Degree Work]

      Sánchez-Cid Artillo, Ignacio (2018)
      En este Trabajo Fin de Grado se intenta aportar soluciones a los problemas con los que se encontraron los profesores del Departamento de Psicología Experimental de la Universidad de Sevilla. Estos problemas provienen de ...
    • IconProcesamiento mediante Matlab de imágenes de actividad cerebral en pez Carpa Dorada  [Final Degree Work]

      Sánchez-Cid Artillo, Ignacio (2018)
      En este Trabajo Fin de Grado se intenta aportar soluciones a los problemas con los que se encontraron los profesores del Departamento de Psicología Experimental de la Universidad de Sevilla. Estos problemas provienen de ...
    • IconRed neuronal convolucional rápida sin fotogramas para reconocimientos de dígitos  [Presentation]

      Pérez Carrasco, José Antonio; Serrano Gotarredona, María del Carmen; Acha Piñero, Begoña; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé (Unión Científica Internacional de Radio, 2011)
      In this paper a bio-inspired six-layer convolutional network (ConvNet) non-frame based for digit recognition is shown. The system has been trained with the backpropagation algorithm using 32x32 images from the MNIST ...
    • IconSegmentación de tejidos con contornos difusos en imágenes radiológicas  [Doctoral Thesis]

      Suárez Mejías, Cristina (2017-06-26)
      En la presente tesis se han desarrollado dos algoritmos innovadores para la segmentación de tumores retroperitoneales en imágenes radiológicas en 3D, ambos basados en la metodología de relajación convexa. Un algoritmo hace ...
    • IconSegmentation of bone structures in 3D CT images based on continuous max- ow optimization  [Presentation]

      Pérez Carrasco, José Antonio; Acha Piñero, Begoña; Serrano Gotarredona, María del Carmen (Society of Photo-optical Instrumentation Engineers (SPIE), 2015)
      In this paper an algorithm to carry out the automatic segmentation of bone structures in 3D CT images has been implemented. Automatic segmentation of bone structures is of special interest for radiologists and surgeons ...
    • IconSimulador de sistemas AER basados en eventos  [Presentation]

      Pérez Carrasco, José Antonio; Serrano Gotarredona, María del Carmen; Acha Piñero, Begoña; Serrano Gotarredona, Teresa; Linares Barranco, Bernabé (2008)
      Address-Event-Representation (AER) is a communications protocol for transferring (visual) information between chips, originally developed for bio-inspired vision and audition systems. Such systems may consist of a ...
    • IconSistema de reconocimiento de caracteres de alta velocidad basado en eventos  [Presentation]

      Pérez Carrasco, José Antonio; Acha Piñero, Begoña; Serrano Gotarredona, María del Carmen; Serrano Gotarredona, Teresa; Linares Barranco, Bernabé (2011)
      Spike-based processing technology is capable of very high speed throughput, as it does not rely on sensing and processing sequences of frames. Besides, it allows building complex and hierarchically structured cortical-like ...
    • IconSistema de reconocimiento de caracteres de alta velocidad basado en eventos  [Presentation]

      Pérez Carrasco, José Antonio; Acha Piñero, Begoña; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé (Unión Científica Internacional de Radio, 2011)
      Spike-based processing technology is capable of very high speed throughput, as it does not rely on sensing and processing sequences of frames. Besides, it allows building complex and hierarchically structured cortical-like ...
    • IconTowards Real-World Neurorobotics: Integrated Neuromorphic Visual Attention  [Article]

      Adams, Samantha V.; Rast, Alexander D.; Patterson, Cameron; Gallupi, Francesco; Brohan, Kevin; Pérez Carrasco, José Antonio; Wennekers, Thomas; Furber, Steve; Cangelosi, Angelo (Springer Verlag, 2014)
      Neuromorphic hardware and cognitive robots seem like an obvious fit, yet progress to date has been frustrated by a lack of tangible progress in achieving useful real-world behaviour. System limitations: the simple and ...