Efficient and Accurate Gaussian Image Filtering Using Running Sums

07/25/2011
by   Elhanan Elboher, et al.
0

This paper presents a simple and efficient method to convolve an image with a Gaussian kernel. The computation is performed in a constant number of operations per pixel using running sums along the image rows and columns. We investigate the error function used for kernel approximation and its relation to the properties of the input signal. Based on natural image statistics we propose a quadratic form kernel error function so that the output image l2 error is minimized. We apply the proposed approach to approximate the Gaussian kernel by linear combination of constant functions. This results in very efficient Gaussian filtering method. Our experiments show that the proposed technique is faster than state of the art methods while preserving a similar accuracy.

READ FULL TEXT
research
03/26/2016

Fast and Provably Accurate Bilateral Filtering

The bilateral filter is a non-linear filter that uses a range filter alo...
research
05/01/2015

Fast and Accurate Bilateral Filtering using Gauss-Polynomial Decomposition

The bilateral filter is a versatile non-linear filter that has found div...
research
07/22/2011

Constant-time filtering using shiftable kernels

It was recently demonstrated in [5] that the non-linear bilateral filter...
research
01/18/2019

Fast High-Dimensional Kernel Filtering

The bilateral and nonlocal means filters are instances of kernel-based f...
research
05/24/2019

Multi-Kernel Correntropy for Robust Learning

As a novel similarity measure that is defined as the expectation of a ke...
research
08/01/2016

Kernel Risk-Sensitive Loss: Definition, Properties and Application to Robust Adaptive Filtering

Nonlinear similarity measures defined in kernel space, such as correntro...
research
11/21/2019

Asymmetric Correntropy for Robust Adaptive Filtering

In recent years, correntropy has been seccessfully applied to robust ada...

Please sign up or login with your details

Forgot password? Click here to reset