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 12 of 12 for “"Image convolution"”.

  1. Two-dimensional image convolution by analog computation

    Vision computing has been a subject of tremendous research interest since the days of the original perceptron in the 1940's [McClelland 88]. The last decade or so has shown a great deal of progress in our understanding of, at least, the early stages of vision and of the underlying structures and …

    ttu Repository record for Two-dimensional image convolution by analog computation (opens in a new tab)

  2. On the Performance of Line Integral Convolution in a Distributed-Memory Parallel Setting

    Line integral convolution (LIC) is a powerful tool for visualizing vector fields by combining particle advection with image convolution. Practical usage of LIC is limited by its computational expense, requiring many calculations for every cell in the mesh. Fortunately, computation of LIC can be …

    oregon Repository record for On the Performance of Line Integral Convolution in a Distributed-Memory Parallel Setting (opens in a new tab)

  3. GPRM: a high performance programming framework for manycore processors

    … platforms: LU factorisation of Sparse Matrices, Image Convolution, and Linked List Processing. We focus on proposing solutions that best fit into the GPRM’s model of execution. GPRM outperforms OpenMP in all cases on the TILEPro64. On the Xeon Phi, our solution for the LU Factorisation results in …

    glasgow Download PDF for GPRM: a high performance programming framework for manycore processors (opens in a new tab)

  4. Improving objects recognition through fast Fourier transformation in neural network

    Image Processing is a branch of computer vision, which deals with understanding and extracting information from digital images. Deep convolutional neural network is a major technique used for image processing. However, the major problem is that it requires a lot of training time and computational …

    ttu Repository record for Improving objects recognition through fast Fourier transformation in neural network (opens in a new tab)

  5. Selection-based Convolution for Irregular Images and Graph Data

    … continues to be revolutionized by advances in Convolutional Neural Networks. These networks are well suited for the regular grid structure of image data. However, there are many irregular image types that do not fit within such a framework, such as multi-view images, spherical images, …

    byu Repository record for Selection-based Convolution for Irregular Images and Graph Data (opens in a new tab) Download PDF for Selection-based Convolution for Irregular Images and Graph Data (opens in a new tab)

  6. Performance analysis of pyramid mapping algorithms for the hypercube

    … scientific processors also make them efficient image processors. Two algorithms which have been developed for the efficient mapping of the pyramid onto the hypercube are discussed in this thesis. The algorithm proposed by Stout [4] requires a hypercube with a number of processing elements (PEs) …

    njit Repository record for Performance analysis of pyramid mapping algorithms for the hypercube (opens in a new tab)

  7. Figure-ground segmentation in gratings and plaids : a psychophysical and calcium imaging study in macaque monkey

    … contrast, color, spatial frequency, and other image properties. A large body of work has been dedicated to account for boundary detection and figure-ground segregation in experimental textures and natural images, yet it remains elusive how the well-known neural operation, divisive …

    texas Repository record for Figure-ground segmentation in gratings and plaids : a psychophysical and calcium imaging study in macaque monkey (opens in a new tab)

  8. Blind Image Deconvolution using Approximate Greatest Common Divisor and Approximate Polynomial Factorisation

    Images play a significant and important role in diverse areas of everyday modern life. Examples of the areas where the use of images is routine include medicine, forensic investigations, engineering applications and astronomical science. The procedures and methods that depend on image processing …

    whiterose Download PDF for Blind Image Deconvolution using Approximate Greatest Common Divisor and Approximate Polynomial Factorisation (opens in a new tab)

  9. High speed, high volume, optimal image subtraction for large volume astronomical data pipelines

    … to the computationally intensive method of image comparison known as Optimal Image Subtraction (OIS). Of particular interest is the Dirac delta function basis spatially-varying OIS, a technique particularly applicable to images with asymmetric and non-Gaussian point spread functions (PSFs). …

    jamescook Download PDF for High speed, high volume, optimal image subtraction for large volume astronomical data pipelines (opens in a new tab)

  10. Interpolace obrazů

    V práci je popsán základní princip, vlastnosti a využití interpolace 2D signálu (obrazu). Podrobněji jsou popsány jednotlivé metody interpolace. Teoretické poznatky interpolace jsou prakticky vyzkoušeny v prostředí Matlab na vybraných metodách interpolace zahrnujících i vlastní implementaci …

    brno-tech Repository record for Interpolace obrazů (opens in a new tab)