Learn More
We present a novel algorithm for image fusion from irregularly sampled data. The method is based on the framework of normalized convolution (NC), in which the local signal is approximated through a projection onto a subspace. The use of polynomial basis functions in this paper makes NC equivalent to a local Taylor series expansion. Unlike the traditional(More)
  • G M P Van Kempen, L J Van Vliet, R P W Duin, J Van Katwijk, J J Gerbrands, M R Van Steen +3 others
  • 1998
In this paper, the properties of the mean and variance of three estimators of the ratio between two random variables x, y are discussed. Given n samples of x and y we can construct two different estimators. One is biased and the other is asymptotically unbiased. Using the noise characteristics (variance, covariance) a third, unbiased estimator can be(More)
An edge detection scheme is developed robust enough to perform well over a wide range of signal-to-noise ratios. It is based upon the detection of zero crossings in the output image of a nonlinear Laplace filter. Specific characterizations of the nonlinear Laplacian are its adaptive orientation to the direction of the gradient and its inherent masks which(More)
Fluorescence in situ hybridization allows the enumeration of chromosomal abnormalities in interphase cell nuclei. This process is called dot counting. To estimate the distribution of chromosomes per cell, a large number of cells have to be analyzed, especially when the frequency of aberrant cells is low. Automation of dot counting is required because manual(More)
We propose a new curvature estimator, which operates on the output of an orientation estimator. Robust orientation estimators have been available for a long time. Some properties of the estimator as well as potential problems and limitations are discussed. The theory is verified by some experiments and practical limitations are investigated. The method is(More)
  • Proefschrift Ter, Rector Magnificus, L J Van Vliet, K Schutte, A Gisolf, J Ir +8 others
  • 2006
The low-resolution images (64×64 pixels) on the front page were provided by TNO-FEL. The low-resolution images (1000×1000 pixels) on the back page were provided by i-Optics. i-Optics is considering to incorporate a super-resolution algorithm into its products. In this thesis we investigate the task of improving the resolution of under-sampled image(More)
One of the essential ways in which nonlinear image restoration algorithms differ from linear, convolution-type image restoration filters is their capability to restrict the restoration result to nonnegative intensities. The iterative constrained Tikhonov-Miller (ICTM) algorithm, for example, incorporates the nonnegativity constraint by clipping all negative(More)