Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 17 of 17 for “"Artificial vision"”.

  1. Large-scale Trends in Vision Systems: Novel Methods for Identifiability

    While the analogy between artificial neural networks (ANNs) and the brain have been well validated in past work, one question without a clear answer is—what causes an ANN to be more or less brain-like? A better understanding of this may lead to the discovery and implementation of more performant …

    mit Repository record for Large-scale Trends in Vision Systems: Novel Methods for Identifiability (opens in a new tab)

  2. Reconeixement d'accions mitjançant visió artificial per teleassistència

    … This work explores the possibility of using artificial vision to monitor actions of everyday life through the imaging method of the history of the movement (MHI) and the classification of these images using neural networks and support vector machine. The results obtained are insufficient to …

    catalunya Repository record for Reconeixement d'accions mitjançant visió artificial per teleassistència (opens in a new tab)

  3. Learning from minimally labeled data with accelerated convolutional neural networks

    <p>The main objective of an Artificial Vision Algorithm is to design a mapping function that takes an image as an input and correctly classifies it into one of the user-determined categories. There are several important properties to be satisfied by the mapping function for visual understanding. …

    purdue-thes Repository record for Learning from minimally labeled data with accelerated convolutional neural networks (opens in a new tab)

  4. Neuro-electronic technology in medicine and beyond

    … and is compared with recent developments in artificial vision. The final sections consider a future for non-medicinal applications of neuro-electronic technology. Social attitudes towards use for both medicinal and non-medicinal purposes are discussed, and the viability of use in the latter …

    lancaster Repository record for Neuro-electronic technology in medicine and beyond (opens in a new tab)

  5. An Intelligent Soft-Computing Texture Classification System

    … a general approach that shows a way towards real artificial vision.<br/><br/>Finding ways to enable computerised systems to visually recognise its surroundings is of increasing importance for the industry and society at large. To reach this goal not only objects but less well describable texture …

    southwales Repository record for An Intelligent Soft-Computing Texture Classification System (opens in a new tab)

  6. Increasing Functional Task Performance in Adults with Low Vision

    … functional task performance of adults with low vision utilizing tactile vision substitution systems, specifically tongue display units (TDUs). TDUs are a novel assistive device that functions to provide artificial vision to those with low vision. TDUs pixelate images captured on a camera the …

    dominican Repository record for Increasing Functional Task Performance in Adults with Low Vision (opens in a new tab)

  7. A Model Of Visual Recognition Implemented Using Neural Networks

    … is an important property of biological vision. It is highly desirable that artificial vision systems also have this ability. This thesis documents research into the use of artificial neural networks to implement a prototype model of visual object recognition. The prototype model, …

    edithcowan Repository record for A Model Of Visual Recognition Implemented Using Neural Networks (opens in a new tab)

  8. Computational Modelling of Functionally-Identified Retinal Ganglion Cells using a Multi-Objective Optimisation Approach

    … it is desirable to reconstruct a useful sense of artificial vision by selectively activating different neuron populations in a planned sequence and spatial pattern. However, current retinal neuroprostheses have limited ability in targeting different retinal neuron types. Improvements in the field …

    unsw Repository record for Computational Modelling of Functionally-Identified Retinal Ganglion Cells using a Multi-Objective Optimisation Approach (opens in a new tab)

  9. Evaluating ventral visual stream contributions to human visual robustness with deep learning approaches

    … mechanisms that confer robustness in human vision and whether they can be adequately captured by DCNNs. This thesis leverages deep convolutional neural networks (DCNNs) to investigate the role of VVS in achieving visual robustness, with a particular focus on how neural representational …

    uiuc Repository record for Evaluating ventral visual stream contributions to human visual robustness with deep learning approaches (opens in a new tab)

  10. A study in human attention to guide computational action recognition

    Computer vision researchers have a lot to learn from the human visual system. We, as humans, are usually unaware of how enormously difficult it is to watch a scene and summarize its most important events in words. We only begin to appreciate this truth when we attempt to build a system that …

    mit Repository record for A study in human attention to guide computational action recognition (opens in a new tab)

  11. Recognition, reorganisation, reconstruction and reinteraction for scene understanding

    … for humans. However, for computer systems using artificial vision, it is not. Thus, researchers from philosophy to neuroscience, from mathematics to computer science, have devoted ample time to understand the underlying principles for developing a vision system which would be able to see as well …

    oxford-brookes Repository record for Recognition, reorganisation, reconstruction and reinteraction for scene understanding (opens in a new tab)

  12. An invariance-based account of feedforward categorization in a realistic model of the ventral visual pathway

    … scenes, the current top-performing computer vision models owe a debt to visual neuroscience. The hierarchical architecture of convolutional networks, and related models such as HMAX, mimics that of the ventral stream of visual cortex. In essence, they apply the model of Hubel and Wiesel …

    mit Repository record for An invariance-based account of feedforward categorization in a realistic model of the ventral visual pathway (opens in a new tab)

  13. Desenvolvimento de metodologias para determinação do bem-estar e massa corporal de frangos de corte por meio de análise digital de imagens

    … bem-estar animal. A vantagem do sistema de visão artificial em relação ao sistema visual humano é a possibilidade de efetuar medições exatas, baseadas na contagem de pixels. Além disso, não influencia o comportamento dos animais, anula o efeito da subjetividade e evita o cansaço físico do …

    brazil-ufv Repository record for Desenvolvimento de metodologias para determinação do bem-estar e massa corporal de frangos de corte por meio de análise digital de imagens (opens in a new tab)

  14. Encriptación de imágenes portadoras de textos esteganografiados usando sistemas caóticos, visión artificial y codificación ADN

    … a color gracias a técnicas propias de la visión artificial, generando posteriormente una criptoimagen la cual se construye aplicando sistemas caóticos y codificación ADN

    udistrital Repository record for Encriptación de imágenes portadoras de textos esteganografiados usando sistemas caóticos, visión artificial y codificación ADN (opens in a new tab)