• Publications
  • Influence
Trainable frontend for robust and far-field keyword spotting
TLDR
This work introduces a novel frontend called per-channel energy normalization (PCEN), which uses an automatic gain control based dynamic compression to replace the widely used static compression in speech recognition.
Rudin-Osher-Fatemi Total Variation Denoising using Split Bregman
TLDR
This work focuses here on the split Bregman algorithm of Goldstein and Osher for TV-regularized denoising, a technique that was originally developed for AWGN image denoizing and has since been applied to a multitude of other imaging problems.
Automatic Color Enhancement (ACE) and its Fast Implementation
TLDR
Two fast approximations of automatic Color Enhancement “ACE” are described, using a polynomial approximation of the slope function to decomposes the main computation into convolutions, reducing the cost to O(N 2 logN).
Chan-Vese Segmentation
TLDR
The level set formulation of the Chan-Vese model and its numerical solution using a semi-implicit gradient descent is described, which allows the segmentation to handle topological changes more easily than explicit snake methods.
Total Variation Inpainting using Split Bregman
TLDR
Inpainting is used to restore regions of an image that are corrupted by noise or where the data is missing, and to solve disocclusion, to estimate the scene behind an obscuring foreground object.
A Survey of Gaussian Convolution Algorithms
TLDR
This survey discusses approximate Gaussian convolution based on nite impulse response lters, DFT and DCT based convolution, box lter, and several recursive lters and pays particular attention to boundary handling.
A Variational Model for the Restoration of MR Images Corrupted by Blur and Rician Noise
TLDR
A variational model to restore images degraded by blur and Rician noise using total variation regularization with a fidelity term involving the Rician probability distribution is proposed.
Total Variation Deconvolution using Split Bregman
TLDR
TV-regularized deconvolution with Gaussian noise and its ecient solution using the split Bregman algorithm of Goldstein and Osher is discussed and a straightforward extension for Laplace or Poisson noise is shown and empirical estimates for the optimal value of the regularization parameter are developed.
Contour Stencils: Total Variation along Curves for Adaptive Image Interpolation
TLDR
This work introduces contour stencils, a new method for estimating the image contours based on total variation along curves, which has linear complexity in the number of pixels and can be computed in one or a small number of passes through the image.
Contour stencils for edge-adaptive image interpolation
TLDR
A simple method for detecting the local orientation of image contours is developed and used to design an edge-adaptive image interpolation strategy, which is computationally efficient, operates robustly over a variety of image features, and performs competitively in a comparison against existing methods.
...
1
2
3
4
5
...