Fast Bilateral Filtering Research Articles

Radial basis function network for fast bilateral filtering

The bilateral filter perhaps is the most fundamental smoothing tool in image processing. However, low-computational efficiency limits its applications. To the best of authors' knowledge, all existing fast bilateral filtering algorithms are handcrafted by talented authors. However, it is a painstaking and effortless work to design an acceleration algorithm. In this Letter, the authors propose a radial basis function network to automatically produce the fast bilateral filtering algorithm. This is done by establishing the one–one connection between the radial basis function network and the fast bilateral filtering algorithm. Experiments demonstrate that their method is able to produce state-of-the-art results.

A Reconfigurable and Scalable FPGA Architecture for Bilateral Filtering

Bilateral filter is an edge-preserving smoother that has applications in image processing, computer vision, and computational photography. In the past, fieldprogrammable gate array (FPGA) implementations of the filter have been proposed that can achieve high throughput using parallelization and pipelining. An inherent limitation with direct implementations is that their complexity scales as O(ω <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) with the filter width ω. In this paper, we propose an FPGA implementation of a fast bilateral filter that requires just O(1) operations for any arbitrary ω. The attractive feature of the FPGA implementation is that it is both scalable and reconfigurable. To the best of our knowledge, this is the first scalable FPGA implementation of the bilateral filter. As an application, we use the FPGA implementation for image denoising.

Hyperspectral image classification based on joint sparsity model with low-dimensional spectral–spatial features

We propose a hyperspectral image (HSI) classification method combining low-dimensional spectral–spatial features with joint sparsity model (JSM). First, for the high-dimensional data sets, we introduced image fusion for feature reduction. Then fast bilateral filtering is adopted to exploit spatial features, which will be combined with the original spectral features for classification. Based on the low-dimensional spectral–spatial features, we utilize JSM to serve as a classifier. Considering the strong relationship between the neighboring pixels in HSI, this model can achieve a promising performance by exploiting regional spectral–spatial information. Overall accuracies (with 10% and 2% training samples) of the proposed method are 97.84% and 97.52% for the Indian Pines image and University of Pavia image. Experimental results on different HSI data sets show that the proposed method shows outstanding performance in terms of classification accuracy and computational efficiency.

Global Color Sparseness and a Local Statistics Prior for Fast Bilateral Filtering.

The property of smoothing while preserving edges makes the bilateral filter a very popular image processing tool. However, its non-linear nature results in a computationally costly operation. Various works propose fast approximations to the bilateral filter. However, the majority does not generalize to vector input as is the case with color images. We propose a fast approximation to the bilateral filter for color images. The filter is based on two ideas. First, the number of colors, which occur in a single natural image, is limited. We exploit this color sparseness to rewrite the initial non-linear bilateral filter as a number of linear filter operations. Second, we impose a statistical prior to the image values that are locally present within the filter window. We show that this statistical prior leads to a closed-form solution of the bilateral filter. Finally, we combine both ideas into a single fast and accurate bilateral filter for color images. Experimental results show that our bilateral filter based on the local prior yields an extremely fast bilateral filter approximation, but with limited accuracy, which has potential application in real-time video filtering. Our bilateral filter, which combines color sparseness and local statistics, yields a fast and accurate bilateral filter approximation and obtains the state-of-the-art results.

Wavelet and fast bilateral filter based de-speckling method for medical ultrasound images

Speckle noise is an undesirable part of the ultrasound imaging process, since it can degrade the quality of ultrasound images and restrict the development of automatic diagnostic techniques for ultrasound images. Aiming at the problem of speckle noise, an improved de-speckling method for medical ultrasound images is proposed, which is based on the wavelet transformation and fast bilateral filter. According to the statistical properties of medical ultrasound image in the wavelet domain, an improved wavelet threshold function based on the universal wavelet threshold function is considered. The wavelet coefficients of noise-free signal and speckle noise are modeled as generalized Laplace distribution and Gaussian distribution, respectively. The Bayesian maximum a posteriori estimation is applied to obtain a new wavelet shrinkage algorithm. High-pass component speckle noise in the wavelet domain of ultrasound images is suppressed by the new shrinkage algorithm. Additionally, the coefficients of the low frequency signal in the wavelet domain are filtered by the fast bilateral filter, since the low-pass component of ultrasound images also contains some speckle noise. Compared with other de-speckling methods, experiments show that the proposed method has improved de-speckling performance for medical ultrasound images. It not only has better reduction performance than other methods but also can preserve image details such as the edge of lesions.

A fast bilateral filter with application to artefact reduction

Elastography in medical ultrasound is an imaging technique that displays information about tissue stiffness. However, elastography suffers from artefact noise that may come from two dominant sources: decorrelation error and amplitude modulation error. In order to reduce artefact and improve the quality of ultrasonic elastography, a fast bilateral filter is proposed in this study based on local histogram. The presented filter is derived from a conventional bilateral filter, and a local histogram is introduced to speed up the filter. The proposed algorithm can reduce artefact noise and, at the same time, maintain the tissue structure. Both simulation and phantom testing show that the proposed method can improve the quality of ultrasonic elastography in terms of tissue elastographic signal-to-noise ratio and elastographic contrast-to-noise ratio values.

An Improved Method Based on Fast Bilateral Filter for High Dynamic Image Rendering

This paper presents an improved high dynamic range image tone mapping method based on fast bilateral filtering. The algorithm first applied a bilateral filtering to the luminance channel of the image, the image is decomposed into an HDR base layer and an LDR detail layer. Then the HDR base layer is blurred with bilateral filtering again, get the details portion of the base layer, at the same time the dynamic range of the global base layer is compressed. Finally, the detail component and the compressed HDR base layer are recombined and the result is tone-mapped image for displaying. For color image, the color restoration converts luminance value into RGB color. Experimental results show that the proposed technique performed better than the conventional bilateral filtering, preserving more details and enhancing local contrast, giving decent visual effect and avoiding additional artifacts.

Histogram-Based Fast Adaptive Bilateral Filter for Ultrasound Speckle Reduction

Tissue structure including lesions in ultrasound images is important in clinical diagnosis. The way to suppress noise effectively and to preserve the structure is vital for diagnosis and also for image postprocessing. In order to reduce speckle and improve the quality of ultrasound images, this paper presents a fast adaptive bilateral filter (FABF) based on local histogram. The presented filter is derived from a conventional bilateral filter and is adaptively adjusted by speckle detection based on histogram matching. The criterion of speckle region is defined from a similarity value obtained from local histogram matching between the processing window and a reference speckle area. The presented filter can effectively reduce the speckle noise and, at the same time, maintain the tissue structure. In phantom and in vivo data, the proposed method can improve the quality of an ultrasound image in terms of tissue SNR and CNR values.

Characteristic matching-based adaptive fast bilateral filter for ultrasound speckle reduction

Ultrasound images show a granular pattern of noise known as speckle which diminishes their quality and results in difficulties in diagnosis. This paper presents an adaptive fast bilateral filter (AFBF) to reduce the speckle noise. The presented filter is derived from a conventional bilateral filter and is adaptively adjusted by the detection of speckle statistics. The criterion of speckle region is defined from a similarity value obtained from local characteristic matching between the processing window and a reference speckle area. The presented filter can reduce the speckle noise and, at the same time, maintain the tissue structure. Ultrasound phantom testing and in vivo imaging show that the proposed method can improve the quality of an ultrasound image in terms of tissue SNR, CNR and FOM values.

Automated Segmentation of Intraretinal Cystoid Fluid in Optical Coherence Tomography

Cystoid macular edema (CME) is observed in a variety of ocular disorders and is strongly associated with vision loss. Optical coherence tomography (OCT) provides excellent visualization of cystoid fluid, and can assist clinicians in monitoring the progression of CME. Quantitative tools for assessing CME may lead to better metrics for choosing treatment protocols. To address this need, this paper presents a fully automated retinal cyst segmentation technique for OCT image stacks acquired from a commercial scanner. The proposed method includes a computationally fast bilateral filter for speckle denoising while maintaining CME boundaries. The proposed technique was evaluated in images from 16 patients with vitreoretinal disease and three controls. The average sensitivity and specificity for the classification of cystoid regions in CME patients were found to be 91% and 96%, respectively, and the retinal volume occupied by cystoid fluid obtained by the algorithm was found to be accurate within a mean and median volume fraction of 1.9% and 0.8%, respectively.

A Low‐Memory, Straightforward and Fast Bilateral Filter Through Subsampling in Spatial Domain

AbstractIn this work we present a new algorithm for accelerating the colour bilateral filter based on a subsampling strategy working in the spatial domain. The base idea is to use a suitable subset of samples of the entire kernel in order to obtain a good estimation of the exact filter values. The main advantages of the proposed approach are that it has an excellent trade‐off between visual quality and speed‐up, a very low memory overhead is required and it is straightforward to implement on the GPU allowing real‐time filtering. We show different applications of the proposed filter, in particular efficient cross‐bilateral filtering, real‐time edge‐aware image editing and fast video denoising. We compare our method against the state of the art in terms of image quality, time performance and memory usage.

Fast bilateral filter for HDR imaging

Bilateral filtering is a method often used in image processing applications. It is specifically useful for HDR algorithms. A novel approach to a fast and close approximation of bilateral filtering is presented. The method is designed especially with a focus on HDR image conversion into a normal color space processing. This paper presents the methods itself, describes the sources of acceleration and discusses the results of the method.

Fast Bilateral Filter With Arbitrary Range and Domain Kernels

In this paper, we present a fast implementation of the bilateral filter with arbitrary range and domain kernels. It is based on the histogram-based fast bilateral filter approximation that uses uniform box as the domain kernel. Instead of using a single box kernel, multiple box kernels are used and optimally combined to approximate an arbitrary domain kernel. The method achieves better approximation of the bilateral filter compared to the single box kernel version with little increase in computational complexity. We also derive the optimal kernel size when a single box kernel is used.

A Fast Approximation to the Bilateral Filter for ITK

This document describes an implementation of an alternative bilateral filtering algorithm in ITK. This class implements the fast bilateral filter algorithm in ITK by taking the input image and organizing it into the required data structure as an ITK Image with dimension one greater than the original image. The DiscreteGaussianImageFilter is then used to blur the higher dimensional image. The discrete Gaussian image filter was chosen because the kernel width used should usually be small due to the down-sampling involved when using this technique. As described in the ITK documentation, this class should outperform the recursive Gaussian algorithm due to the small kernel size DiscreteGaussianImageFilter.After the Gaussian blur has been completed the data will be interpolated and written to the output image.By incorporating this class into the ITK framework, this more efficient algorithm will be made available to all ITK users.

High dynamic range image tone mapping and retexturing using fast trilateral filtering

Using fast trilateral filtering we present a novel tone mapping and retexturing method for high dynamic range (HDR) images. Our new trilateral filtering-based tone mapping is about seven to ten times faster than that in [3]. Firstly, a novel tone mapping algorithm for HDR images is presented. It is based on fast bilateral filtering and two newly developed filters: the quasi-Cauchy function kernel filter and the fourth degree Taylor polynomial kernel filter. Secondly, a new gradient-based image retexturing method is introduced, which consists of three steps: 1) converting HDR images into low dynamic range (LDR) images using our fast trilateral filtering-based tone mapping method; 2) recovering the gradient luminance maps for the region to be retextured; 3) reconstructing the final retextured image by solving the Poisson equation. The proposed approach is suitable for HDR image tone mapping and retexturing, and experimental results have demonstrated the satisfactory performance of our method.

Fast bilateral filter for edge-preserving smoothing

Edge-preserving lowpass filters are a valuable tool in several image processing tasks, including noise reduction and dynamic range compression. A high-quality algorithm is the bilateral filter, but its computational cost is very high. A fast but approximate implementation was introduced by Durand and Dorsey. Introduced are two modifications in this technique which allow further acceleration and a significant increase in quality.