Modified Double Bilateral Filter for Sharpness Enhancement and Noise Removal

Sable, Archana H.; Jondhale, Kalpana C.

doi:10.1109/ace.2010.76

Cited by 15 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images may be corrupted by noise during acquisition due to numerous reasons such as the camera hardware, examiner error (e.g., focusing), and illuminations issues [ 18 ]. Traditional filtering and noise reduction methods such as Gaussian low-pass filtering use weighted average of pixel values in the neighborhood and consider the spatial variation to be slow [ 19 ].…”

Section: Methodsmentioning

confidence: 99%

A Method for Visualization of Fine Retinal Vascular Pulsation Using Nonmydriatic Fundus Camera Synchronized with Electrocardiogram

et al. 2013

View full text Add to dashboard Cite

Pulsatile changes in retinal vascular geometry over the cardiac cycle have clinical implication for diagnosis of ocular and systemic vascular diseases. In this study, we report a Vesselness Mapping of Retinal Image Sequence (VMRS) methodology to visualize the vessel pulsation and quantify the pulsatile motions in the cardiac cycle. Retinal images were recorded in an image sequence corresponding to 8 segments of the cardiac cycle using a nonmydriatic fundus camera (Canon CR45, Canon Inc., Japan) modified with ECG-synchronization. Individual cross-sectional vessel diameters were measured separately and the significance of the variations was tested statistically by repeated measures analysis of variance (ANOVA). The graders observed an improved quality of vessel pulsation on a wide region around the optic disk using the VMRS. Individual cross- sectional vessel diameter measurement after visualization of pulsatile motions resulted in the detection of more significant diameter change for both arterioles (3.3 μm, P = 0.001) and venules (6.6 μm, P < 0.001) compared to individual measurement without visualization of the pulsatile motions (all P values > 0.05), showing an increase of 2.1 μm and 4.7 μm for arterioles and venules, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

A Method for Visualization of Fine Retinal Vascular Pulsation Using Nonmydriatic Fundus Camera Synchronized with Electrocardiogram

et al. 2013

View full text Add to dashboard Cite

show abstract

“…The parameters σ 1 and σ 2 control the influence of the weights on the final filter output. Since its introduction, various modifications of the BF, aiming mainly at increasing its ability to preserve image details, have been introduced [17,39,40,56,57]. However, although effective in the case of Gaussian noise, the bilateral filter cannot remove the impulses, which are treated as tiny details.…”

Section: Proposed Filtering Designmentioning

confidence: 99%

Robust local similarity filter for the reduction of mixed Gaussian and impulsive noise in color digital images

Smołka

Kusnik

2015

SIViP

View full text Add to dashboard Cite

In this paper, a novel technique designed for the suppression of mixed Gaussian and impulsive noise in color images is proposed. The new denoising scheme is based on a weighted averaging of pixels contained in a filtering block. The main novelty of the proposed solution lies in the new definition of the similarity between the samples of the processing block and a small window centered at the block's central pixel. Instead of direct comparison of pixels, a measure based on the similarity between a given pixel and the samples from the neighborhood of the central pixel is utilized. This measure is defined as the sum of distances in a given color space, between a pixel of the block and a certain number of most similar samples from the filtering window. The main advantage of the proposed scheme is that the new similarity measure is not influenced by the outliers injected into the image by the impulsive noise and the averaging process ensures the effectiveness of the new filter in the reduction of Gaussian noise. The experimental results prove that the novel filtering design is capable of suppressing mixed noise of high intensity and is competitive with respect to the stateof-the-art noise filtering methods.

show abstract

“…Therefore, a Modified Double Bilateral Filter (MDBF) [7] was proposed in 2010 to remove impulse noise from images. This adds black and white pixels in the image.…”

Section: Modified Double Bilateral Filtermentioning

confidence: 99%