Gradient Domain Guided Image Filtering Research Articles

Display method for high dynamic range infrared image based on gradient domain guided image filter

Display method for high dynamic range infrared image based on gradient domain guided image filter

Speckle noise reduction in US images: Enhanced filtering with optimal filter coefficients

Ultrasound (US) imaging is one of the prominent techniques, which is widely used for its advantages such as affordability, non-radiation, and non-invasiveness. However, the visual evaluation in this imaging model was hampered by speckle noise. De-specking is therefore seen as the most important task. The preservation of every minute detail in the US images is the main challenge of de-speckling. This paper proposes a new de-speckling model that includes two major phases: the preprocessing stage and the noise reduction phase. Preprocessing is carried out by the anisotropic filtering process. In the noise reduction phase, two levels of decomposition take place. In the first level of decomposition, Discrete Waveform Transform (DWT) is used. The next level of decomposition (2-level) intakes the output from the first level, the sub-bands. The 2-level uses improved Weighted Guided Image Filtering (WGIF), and Gradient Domain Guided Image Filtering (GDGIF) for surpassing the noise. To make the process even more specific on efficient de-speckling, the concept of optimization is incorporated and eventually tunes the filter coefficients by considering Structural Similarity Index (SSIM) and Peak Signal to Noise Ratio (PSNR). This optimal tuning process is carried out by a new Shark Solution Integrated Coot Optimization Algorithm (SSI-COA). Finally, the noise-free image is produced through the inverse DWT. The efficiency of SSI-COA is evaluated over the conventional methods under various measures. The cost values using SSI-COA are less than (around 0.0518) when compared to other models. Moreover, a PSNR of 0.053275 is attained using SSI-COA for best-case scenarios.

Speckle Noise Reduction in Ultrasound Images

Abstract: Ultrasound Imaging is used to examine various organs in the Human Body. However, in the process of obtaining a Ultrasound Image, Speckle noise is generated due to backscattered echo signals. So, a noise reduction method is required. To improve the speckle noise reduction, we propose a novel algorithm using characteristics of speckle noise and filtering methods based on Speckle Reducing Anisotropic Diffusion (SRAD) filtering, Discrete Wavelet Transform (DWT), Weighted Guided Image Filtering (WGIF) and Gradient Domain Guided Image Filtering (GDGIF). The SRAD filter is exploited as a preprocessing filter because it can be directly applied to a medical US image containing speckle noise without a log-compression. The wavelet domain has the advantage of suppressing the additive noise. Therefore, a homomorphic transformation is utilized to convert the multiplicative noise into additive noise. After two-level DWT decomposition is applied, to suppress the residual noise of an SRAD filtered image, GDGIF and WGIF are exploited to reduce noise from seven high-frequency subband images and one low-frequency sub-band image, respectively. Finally, a noise-free image is attained through inverse DWT and an exponential transform

X-ray Image Enhancement Based on Adaptive Gradient Domain Guided Image Filtering

Due to the contrast of X-ray images being low, significant elements including organs, bones, and nodules are very difficult to identify, so contrast enhancement is necessary. In this paper, an X-ray image enhancement algorithm based on adaptive gradient domain guided image filtering is proposed. The amplification factor in the gradient domain guided image filtering needs to be set manually; it needs to constantly adjust the parameters to achieve the best enhancement effect, and this also increases the computational complexity. In order to solve this problem, an adaptive amplification factor is defined in this paper, and the proposed algorithm is applied to the X-ray image enhancement. Experimental results demonstrate that the proposed method is superior to state-of-the art algorithms in terms of detail enhancement and edge-preserving.

Artificial Intelligence Algorithm-Based Differential Diagnosis of Crohn's Disease and Ulcerative Colitis by CT Image.

The aim of this study was to investigate the effect of low-dose CT enterography (CTE) based on modified guided image filtering (GIF) algorithm in the differential diagnosis of ulcerative colitis (UC) and Crohn's disease (CD). Methods. One hundred and twenty patients with suspected diagnosis of IBD were studied. They were randomly divided into control group (routine CT examination) and observation group (low-dose CTE examination based on improved GIF algorithm), with 60 cases in each group. Comprehensive diagnosis was used as the standard to assess the diagnostic effect. Results. (1) The peak signal-to-noise ratio (PSNR) (26.02 dB) and structural similarity (SSIM) (0.8921) of the algorithm were higher than those of GIF (17.22 dB/0.8491), weighted guided image filtering (WGIF) (23.78 dB/0.8489), and gradient domain guided image filtering (GGIF) (23.77 dB/0.7567) (P < 0.05); (2) the diagnostic sensitivity (91.49%), specificity (92.31%), accuracy (91.67%), positive predictive value (97.73%), and negative predictive value (75%) of the observation group were higher than those of the control group (P < 0.05); the sensitivity and specificity of CTE in the diagnosis of UD and CD were 96.77% and 81.25% and 98.33% and 93.33%, respectively (P < 0.05); there were significant differences in symmetrical intestinal wall thickening and smooth serosal surface between UD and CD (P < 0.05). Conclusion. (1) The improved GIF algorithm has a more effective application value in the denoising processing of low-dose CT images and can better improve the image quality; (2) the accuracy of CTE in the diagnosis of IBD is high, and CTE is of great value in the differential diagnosis of UD and CD.

Efficient local stereo matching algorithm based on fast gradient domain guided image filtering

Guided image filtering (GIF) based cost aggregation or disparity refinement stereo matching algorithms are studied extensively owing to the edge-aware preserved smoothing property. However, GIF suffers from halo artifacts in sharp edges and shows high computational costs on high-resolution images. The performance of GIF in stereo matching would be limited by the above two defects. To solve these problems, a novel fast gradient domain guided image filtering (F-GDGIF) is proposed. To be specific, halo artifacts are effectively alleviated by incorporating an efficient multi-scale edge-aware weighting into GIF. With this multi-scale weighting, edges can be preserved much better. In addition, high computational costs are cut down by sub-sampling strategy, which decreases the computational complexity from O(N) to O(N/s2) (s: sub-sampling ratio) To verify the effectiveness of the algorithm, F-GDGIF is applied to cost aggregation and disparity refinement in stereo matching algorithms respectively. Experiments on the Middlebury evaluation benchmark demonstrate that F-GDGIF based stereo matching method can generate more accuracy disparity maps with low computational cost compared to other GIF based methods.

A Single Image Dehazing Technique Using the Dual Transmission Maps Strategy and Gradient-Domain Guided Image Filtering

In this paper, a single image dehazing technique using dual transmission maps strategy and gradient-domain guided image filtering is presented. A new strategy is adopted to compute the dual transmission maps using the dark channel and atmospheric light. Further, the transmission maps are refined to remove any remaining ill effects using the gradient-domain-guided filter. Finally, using the dark channel, atmospheric light, and refined transmission map, the haze-free image is obtained. The dual transmission maps strategy not only removes halo artifacts and reduces the saturation but also ensures the natural appearance in the recovered images. Furthermore, the proposed scheme is evaluated using a wide range of images and compared with state-of-the-art schemes. The comparison shows the superiority of the proposed technique in terms of recovering haze-free images.

Low-Light Image Brightening via Fusing Additional Virtual Images

Capturing high-quality images via mobile devices in low-light or backlighting conditions is very challenging. In this paper, a new, single image brightening algorithm is proposed to enhance an image captured in low-light conditions. Two virtual images with larger exposure times are generated to increase brightness and enhance fine details of the underexposed regions. In order to reduce the brightness change, the virtual images are generated via intensity mapping functions (IMFs) which are computed using available camera response functions (CRFs). To avoid possible color distortion in the virtual image due to one-to-many mapping, a least square minimization problem is formulated to determine brightening factors for all pixels in the underexposed regions. In addition, an edge-preserving smoothing technique is adopted to avoid noise in the underexposed regions from being amplified in the virtual images. The final brightened image is obtained by fusing the original image and two virtual images via a gradient domain guided image filtering (GGIF) based multiscale exposure fusion (MEF) with properly defined weights for all the images. Experimental results show that the relative brightness and color are preserved better by the proposed algorithm. The details in bright regions are also preserved well in the final image. The proposed algorithm is expected to be useful for computational photography on smart phones.

Despeckling Algorithm for Removing Speckle Noise from Ultrasound Images

Ultrasound (US) imaging can examine human bodies of various ages; however, in the process of obtaining a US image, speckle noise is generated. The speckle noise inhibits physicians from accurately examining lesions; thus, a speckle noise removal method is essential technology. To enhance speckle noise elimination, we propose a novel algorithm using the characteristics of speckle noise and filtering methods based on speckle reducing anisotropic diffusion (SRAD) filtering, discrete wavelet transform (DWT) using symmetry characteristics, weighted guided image filtering (WGIF), and gradient domain guided image filtering (GDGIF). The SRAD filter is exploited as a preprocessing filter because it can be directly applied to a medical US image containing speckle noise without a log-compression. The wavelet domain has the advantage of suppressing the additive noise. Therefore, a homomorphic transformation is utilized to convert the multiplicative noise into additive noise. After two-level DWT decomposition is applied, to suppress the residual noise of an SRAD filtered image, GDGIF and WGIF are exploited to reduce noise from seven high-frequency sub-band images and one low-frequency sub-band image, respectively. Finally, a noise-free image is attained through inverse DWT and an exponential transform. The proposed algorithm exhibits excellent speckle noise elimination and edge conservation as compared with conventional denoising methods.

Underwater image enhancement using an edge-preserving filtering Retinex algorithm

We develop a novel edge-preserving filtering retinex algorithm for single underwater image enhancement, in which gradient domain guided image filtering (GGF) priors of reflection and illumination are embedded into a retinex-based variational framework for promoting image structures and reducing artifacts or noise. We transform an underwater image enhancement issue into a two-phase objective function. We first employ a general retinex-based method to generate guidance reflection and illumination, and then we use GGF to fuse fine structures of guidance reflection and illumination into ideal reflection and illumination. Meanwhile, the l2 norm is efficiently imposed on GGF priors which measure gradient errors between latent and ideal estimations of reflection and illumination. Then we derive an efficient optimization scheme to address the proposed model, which is fast implemented on pixel-wise operations and requires no prior knowledge about imaging conditions. Final experiments demonstrate the effectiveness of the proposed method in structures promotion, artifacts or noise suppression, naturalness and color preservation. Compared with several leading methods, the proposed method yields better subjective results and objective assessments. Furthermore, the utility of our method is extended for enhancing sandstorm and low illumination images.

Improved color attenuation prior based image de-fogging technique

Single image de-fogging has been a confronting problem due to its ill-posed nature. In this paper, a de-fogging technique based upon color attenuation prior (CAP) has been proposed. CAP uses linear model and learning the parameters of this model with a supervised learning method for estimating the scene depth of a foggy image. This depth map is utilized for transmission map estimation. Transmission (t) is one of the important parameter of physical model based de-fogging techniques which describes the portion of the light coming from the scene point that is not scattered and reaches the camera. It is a map called transmission or transparency of the fog 0 < t(x) < 1, t(x) = 0 means completely foggy, t(x) = 1 means fog-free. The more accurately the transmission or depth is estimated, the better the defogging performance will be. In the proposed work, to quickly and accurately estimate the transmission map, a sub-sampling based local minimum operation and fast gradient domain guided image filtering (GDGF) is applied on CAP based initial depth map. The edge attentive restraints of GDGF make edges to be conserved better in the de-fogged images. The de-fogged images obtained by CAP technique suffer from dullness and higher illumination variations due to consideration of fog image degradation model in homogeneous environment and a constant value of atmospheric light. Such variations are removed in the proposed work by using Lambert’s law of illumination reflection, which helps to compensate non uniform illumination, causes simultaneous dynamic range modification, color consistency, and lightness rendition without producing the artifacts in a de-fogged image. To improve the processing speed, image sub-sampling mechanism is used in various steps of image de-fogging. The sub-sampling is used in such a way that the quality of the output at any step is not compromised as demonstrated through various quality parameters. Experimental results show that the proposed approach outperforms state-of-the-art fog removal techniques in terms of efficiency and the de-fogging effect.

Medical image fusion based on modified pulse coupled neural network model and kirsch operator

The medical image fusion process integrates the information of multiple source images into a single image. This fused image can provide more comprehensive information and is helpful in clinical diagnosis and treatment. In this paper, a new medical image fusion algorithm is proposed. Firstly, the original image is decomposed into a low-frequency sub-band and a series of high-frequency sub-bands by using nonsubsampled shearlet transform (NSST). For the low-frequency sub-band, kirsch operator is used to extract the directional feature maps from eight directions and novel sum-modified-Laplacian (NSML) method is used to calculate the significant information of each directional feature map, and then, combining a sigmod function and the significant information updated by gradient domain guided image filtering (GDGF), calculate the fusion weight coefficients of the directional feature maps. The fused feature map is obtained by summing the convolutions of the weight coefficients and the directional feature maps. The final fused low-frequency sub-band is obtained by the linear combination of the eight fused directional feature maps. The modified pulse coupled neural network (MPCNN) model is used to calculate the firing times of each high-frequency sub-band coefficient, and the fused high-frequency sub-bands are selected according to the firing times. Finally, the inverse NSST acts on the fused low-frequency sub-band and the fused high-frequency sub-bands to obtain the fused image. The experimental results show that the proposed medical image fusion algorithm expresses some advantages over the classical medical image fusion algorithms in objective and subjective evaluation.

Weighted aggregation for guided image filtering

As a local filter, the guided image filtering (GIF) suffers from halo artifacts. To address this issue, a novel weighted aggregating strategy is proposed in this paper. By introducing the weighted aggregation to GIF, the proposed method called WAGIF can achieve results with sharp edges and avoid/reduce halo artifacts. More specifically, compared to the weighted guided image filtering and the gradient domain guided image filtering, the proposed method can achieve both fine and coarse smoothing results in the flat areas while preserving edges. In addition, the complexity of the proposed approach is O(N) for an image with N pixels. It is demonstrated that the GIF with weighted aggregation performs well in the fields of computational photography and image processing, including single image detail enhancement, tone mapping of high-dynamic-range images, single image haze removal, etc.

Anisotropic Guided Filtering.

The guided filter and its subsequent derivatives have been widely employed in many image processing and computer vision applications primarily brought about by their low complexity and good edge-preservation properties. Despite this success, the different variants of the guided filter are unable to handle more aggressive filtering strengths leading to the manifestation of "detail halos". At the same time, these existing filters perform poorly when the input and guide images have structural inconsistencies. In this paper, we demonstrate that these limitations are due to the guided filter operating as a variable-strength locally-isotropic filter that, in effect, acts as a weak anisotropic filter on the image. Our analysis shows that this behaviour stems from the use of unweighted averaging in the final steps of guided filter variants including the adaptive guided filter (AGF), weighted guided image filter (WGIF), and gradient-domain guided image filter (GGIF). We propose a novel filter, the Anisotropic Guided Filter (AnisGF), that utilises weighted averaging to achieve maximum diffusion while preserving strong edges in the image. The proposed weights are optimised based on the local neighbourhood variances to achieve strong anisotropic filtering while preserving the low computational cost of the original guided filter. Synthetic tests show that the proposed method addresses the presence of detail halos and the handling of inconsistent structures found in previous variants of the guided filter. Furthermore, experiments in scale-aware filtering, detail enhancement, texture removal, and chroma upsampling demonstrate the improvements brought about by the technique.

A High-Throughput VLSI Architecture for Real-Time Full-HD Gradient Guided Image Filter

Guided image filtering has been applied widely in recent years as a solution to the ever-increasing demand of high-performance filtering, especially for real-time image/video processing. The lately proposed gradient domain guided image filter (GDGIF) is one of the typical works focusing on improving the quality of the filtering result of the original guided image filter (GIF), dealing with the halo-artifacts problem for edge-preserving smoothing. However, due to the involvement of global pixel values in the computation, high computation complexity, and additional complex operation, there is no existing VLSI design for the gradient guided filter. This paper presents a high-throughput VLSI architecture for real-time full-HD ( $1920\times 1080$ ) GDGIF. Four techniques are used in the newly proposed design to reduce the computation complexity and increase the processing throughput. First, a pre-processing stage is introduced to address the problem of global parameters required in the GDGIF. Second, multi-scale down-samplings are adopted for reducing circuit size and processing time. Then, a parallel structure operated at a higher frequency is used at the output stage to restore the full image size and to achieve high throughput at the same time. At last, approximated computation is introduced to eliminate speed bottleneck by simplifying the complex exponentiation operation. Based on the STM 65-nm CMOS technology, the implementation results show that the proposed architecture is able to support full-HD image filtering at a throughput above 75 frame/s, with a design area of 586314 $\mu \text{m}^{2}$ and a power consumption of 18.5 mW.

Pansharpening with a Gradient Domain GIF Based on NSST

In order to improve the fusion quality of multispectral (MS) and panchromatic (PAN) images, a pansharpening method with a gradient domain guided image filter (GIF) that is based on non-subsampled shearlet transform (NSST) is proposed. First, multi-scale decomposition of MS and PAN images is performed by NSST. Second, different fusion rules are designed for high- and low-frequency coefficients. A fusion rule that is based on morphological filter-based intensity modulation (MFIM) technology is proposed for the low-frequency coefficients, and the edge refinement is carried out based on a gradient domain GIF to obtain the fused low-frequency coefficients. For the high-frequency coefficients, a fusion rule based on an improved pulse coupled neural network (PCNN) is adopted. The gradient domain GIF optimizes the firing map of the PCNN model, and then the fusion decision map is calculated to guide the fusion of the high-frequency coefficients. Finally, the fused high- and low-frequency coefficients are reconstructed with inverse NSST to obtain the fusion image. The proposed method was tested using the WorldView-2 and QuickBird data sets; the subjective visual effects and objective evaluation demonstrate that the proposed method is superior to the state-of-the-art pansharpening methods, and it can efficiently improve the spatial quality and spectral maintenance.

Pan-GGF: A probabilistic method for pan-sharpening with gradient domain guided image filtering

Abstract In this paper, we develop a novel probabilistic pan-sharpening method with gradient domain guided image filtering (named Pan-GGF). We employ gradient domain guided image filtering (GGIF) to enforce effective spatial fusion of panchromatic and multispectral images, and the proposed scheme shows better spatial and spectral fusion than other fusion methods, such as projection substitution, detail injection and weighted combination models. A maximum a posterior (MAP) formulation is then presented with imposing l1 norm priors on the errors between panchromatic and multispectral images in both image and gradient domains, and the proposed objective function is addressed through an efficient optimization scheme that alternates between auxiliary variables approximation and high resolution multispectral images reconstruction. Numerous experiments are performed to demonstrate the satisfactory performance of the proposed method in spatial and spectral fusion, and the proposed method outperforms several classical and state-of-the-art pan-sharpening methods in both subjective results and objective assessments.

MRI reconstruction with an edge-preserving filtering prior

Abstract We develop a novel MRI reconstruction algorithm with an edge-preserving filtering prior. In the proposed algorithm, a gradient domain guided image filtering (GGF) is embedded into a commonly-used MRI reconstruction method, which can promote image structures and suppress artifacts or noise. And the l1 norm is accurately imposed on the GGF prior which measures the error between guidance and ideal images in gradient domain. We first turn the MRI reconstruction problem into a two-phase objective function, and then we derive an efficient optimization scheme to address the proposed model by iteratively alternating GGF and l1 norm approximations, and guidance and ideal images reconstructions. We finally provide numerous experiments to validate the effectiveness of the proposed method in both noise-free and noisy MRI reconstructions, and the proposed method outperforms several leading reconstruction approaches in both subjective results and objective assessments. In addition, our method can be effective in computed tomography (CT) image reconstruction.

Effective Guided Image Filtering for Contrast Enhancement

Although the guided image filtering (GIF) has an excellent edge-preserving property, it is prone to suffer from the halo artifacts near the edges. Weighted GIF and gradient-domain GIF try to address the problem by incorporating an edge-aware weighting into GIF. However, they are very sensitive to the regularization parameter and the halo artifacts will become serious as the regularization parameter increases. Moreover, noise in the background is often amplified because of the fixed amplification factor for the detail layer. In this letter, an effective GIF is proposed for better contrast enhancement. First, the average of local variances for all pixels is incorporated into the cost function of GIF for preserving the edges accurately in the base layer. Second, the amplification factor for the detail layer is calculated in a content-adaptive way for suppressing the noise while boosting the fine details. Experimental results show that the proposed filter is more robust to the regularization parameter and can produce visually pleasing output images. Compared to GIF and its related filters, halo artifacts and noise are reduced or attenuated by the proposed filter significantly.

Multiscale infrared and visible image fusion using gradient domain guided image filtering

For better surveillance with infrared and visible imaging, a novel hybrid multiscale decomposition fusion method using gradient domain guided image filtering (HMSD-GDGF) is proposed in this study. In this method, hybrid multiscale decomposition with guided image filtering and gradient domain guided image filtering of source images are first applied before the weight maps of each scale are obtained using a saliency detection technology and filtering means with three different fusion rules at different scales. The three types of fusion rules are for small-scale detail level, large-scale detail level, and base level. Finally, the target becomes more salient and can be more easily detected in the fusion result, with the detail information of the scene being fully displayed. After analyzing the experimental comparisons with state-of-the-art fusion methods, the HMSD-GDGF method has obvious advantages in fidelity of salient information (including structural similarity, brightness, and contrast), preservation of edge features, and human visual perception. Therefore, visual effects can be improved by using the proposed HMSD-GDGF method.