scispace - formally typeset
Search or ask a question
Topic

Bilateral filter

About: Bilateral filter is a research topic. Over the lifetime, 3500 publications have been published within this topic receiving 75582 citations.


Papers
More filters
Proceedings ArticleDOI
06 Mar 2008
TL;DR: In this paper, the authors proposed a locally adaptive method for low-dose CT using a weighted average in a local neighborhood, where the weights are determined according to both the spatial proximity and intensity similarity between the center pixel and the neighboring pixels.
Abstract: Optimal noise control is critical for dose reduction in CT. In this work, we investigated the use of a locally-adaptive method for noise reduction in low-dose CT. This method is based upon bilateral filtering, which smoothes the projection data using a weighted average in a local neighborhood, where the weights are determined according to both the spatial proximity and intensity similarity between the center pixel and the neighboring pixels. This filtering is locally adaptive and can preserve important edge information in the sinogram, thus without significantly sacrificing the spatial resolution. It is closely related to anisotropic diffusion, but is significantly faster. More importantly, a CT noise model can be readily incorporated in the filtering and denoising process. We have evaluated the noise-resolution properties of the bilateral filtering in a phantom study and a preliminary patient study with contrast-enhanced abdominal CT exams. The results demonstrated that bilateral filtering can achieve a better noise-resolution tradeoff than a series of commercial reconstruction kernels. This improvement on noise-resolution properties can be used for improving the image quality in low-dose CT and can also be translated to substantial dose reduction.

29 citations

Book ChapterDOI
08 Sep 2018
TL;DR: A novel method for MPI removal and depth refinement exploiting an ad-hoc deep learning architecture working on data from a multi-frequency ToF camera using a Convolutional Neural Network made of two sub-networks.
Abstract: The removal of Multi-Path Interference (MPI) is one of the major open challenges in depth estimation with Time-of-Flight (ToF) cameras. In this paper we propose a novel method for MPI removal and depth refinement exploiting an ad-hoc deep learning architecture working on data from a multi-frequency ToF camera. In order to estimate the MPI we use a Convolutional Neural Network (CNN) made of two sub-networks: a coarse network analyzing the global structure of the data at a lower resolution and a fine one exploiting the output of the coarse network in order to remove the MPI while preserving the small details. The critical issue of the lack of ToF data with ground truth is solved by training the CNN with synthetic information. Finally, the residual zero-mean error is removed with an adaptive bilateral filter guided from a noise model for the camera. Experimental results prove the effectiveness of the proposed approach on both synthetic and real data.

28 citations

Patent
10 Mar 1998
TL;DR: In this article, an intensity function describing a relationship between pixel distances from the edges and their corresponding intensity values is developed, which can be implemented in a look-up table or approximated with hardware.
Abstract: A computer graphics system renders an image on a display device using improved pre-filtering techniques that minimize aliasing artifacts in the image, particularly at the endpoints of lines. To anti-alias the image, a plurality of edges are placed near a line in the image. An edge function represents the edge. This edge function is multiplied by a scale factor to produce a distance function. This scale factor is the reciprocal of the Euclidean length of the line. The distance function is evaluated to determine the distance of selected pixels from each edge in units of pixels. These distances determine the intensity value for each selected pixel. Pixels on or beyond an edge, with respect to the line, are given a minimum intensity value; pixels inside all edges are given intensity values corresponding to their distances from the edge. An intensity function describing a relationship between pixel distances from the edges and their corresponding intensity values is developed. The intensity function can be implemented in a look-up table or approximated with hardware.

28 citations

Journal ArticleDOI
TL;DR: A 3D extension of the wavelet transform (WT)-based bilateral filtering for Rician noise removal using 3D WT to provide effective representation of the noisy coefficients demonstrated the ability of the proposed method for noise cancellation.
Abstract: Magnetic resonance (MR) images are normally corrupted by random noise which makes the automatic feature extraction and analysis of clinical data complicated. Therefore, denoising methods have traditionally been applied to improve MR image quality. In this study, we proposed a 3D extension of the wavelet transform (WT)-based bilateral filtering for Rician noise removal. Due to delineating capability of wavelet, 3D WT was employed to provide effective representation of the noisy coefficients. Bilateral filtering of the approximation coefficients in a modified neighborhood improved the denoising efficiency and effectively preserved the relevant edge features. Meanwhile, the detailed subbands were processed with an enhanced NeighShrink thresholding algorithm. Validation was performed on both simulated and real clinical data. Using the peak signal-to-noise ratio (PSNR) to quantify the amount of noise of the MR images, we have achieved an average PSNR enhancement of 1.32 times with simulated data. The quantitative and the qualitative measures used as the quality metrics demonstrated the ability of the proposed method for noise cancellation.

28 citations

Journal ArticleDOI
TL;DR: This work introduced in the scheme a new technique that mitigates ghosting, which relies on the employment of an edge-preserving spatial filter for the purpose of computing reliable spatial estimates.
Abstract: In scene-based nonuniformity correction (NUC) methods for infrared focal-plane array cameras, the problem of ghosting artifacts widely affects the sensitivity of the imaging system and visibly decreases the image quality. Ghosting artifacts can also degrade the performance of several applications, such as target detection and tracking. We carried out a detailed analysis of the problem using a well-established NUC technique: the least mean square Scribner's algorithm. In order to solve some drawbacks of the original Scribner's algorithm, we introduced in the scheme a new technique that mitigates ghosting. Such technique relies on the employment of an edge-preserving spatial filter for the purpose of computing reliable spatial estimates. We tested the effectiveness of the new technique applying the improved NUC method to an experimental IR sequence of frames acquired in the laboratory. Finally, the performance of the proposed method was discussed and compared to that yielded by a well-established deghosting technique.

28 citations


Network Information
Related Topics (5)
Image processing
229.9K papers, 3.5M citations
87% related
Image segmentation
79.6K papers, 1.8M citations
87% related
Feature (computer vision)
128.2K papers, 1.7M citations
86% related
Feature extraction
111.8K papers, 2.1M citations
86% related
Pixel
136.5K papers, 1.5M citations
84% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202321
202257
2021116
2020145
2019203
2018204