Scribd Logo
Upload

Welcome to Scribd!

  • 9 views

    Implementation of Fast and Accurate Bilateral Filtering Using Gauss Polynomial Decomposition On Matlab

    Uploaded by

    Surbhit Sinha
    This document summarizes an implementation of the bilateral filter using Gauss polynomial decomposition on MATLAB. It describes the bilateral filter, which replaces pixel values with a weighted average of nearby pixels, with weights based on spatial distance and intensity difference. It then explains how the Gaussian range kernel can be approximated using polynomials, allowing the filter to be implemented as a series of Gaussian filters. The algorithm was tested by adding Gaussian noise to an image and filtering with different sigma values, showing improved runtime and quality compared to other bilateral filtering techniques.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd

    Implementation of Fast and Accurate Bilateral Filtering Using Gauss Polynomial Decomposition On Matlab

    Uploaded by

    Surbhit Sinha
    9 views10 pages
    This document summarizes an implementation of the bilateral filter using Gauss polynomial decomposition on MATLAB. It describes the bilateral filter, which replaces pixel values with a weighted average of nearby pixels, with weights based on spatial distance and intensity difference. It then explains how the Gaussian range kernel can be approximated using polynomials, allowing the filter to be implemented as a series of Gaussian filters. The algorithm was tested by adding Gaussian noise to an image and filtering with different sigma values, showing improved runtime and quality compared to other bilateral filtering techniques.

    Original Description:

    very good ppt for microwave applications

    Original Title

    PPT

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document summarizes an implementation of the bilateral filter using Gauss polynomial decomposition on MATLAB. It describes the bilateral filter, which replaces pixel values with a weighted average of nearby pixels, with weights based on spatial distance and intensity difference. It then explains how the Gaussian range kernel can be approximated using polynomials, allowing the filter to be implemented as a series of Gaussian filters. The algorithm was tested by adding Gaussian noise to an image and filtering with different sigma values, showing improved runtime and quality compared to other bilateral filtering techniques.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    9 views10 pages

    Implementation of Fast and Accurate Bilateral Filtering Using Gauss Polynomial Decomposition On Matlab

    Uploaded by

    Surbhit Sinha
    This document summarizes an implementation of the bilateral filter using Gauss polynomial decomposition on MATLAB. It describes the bilateral filter, which replaces pixel values with a weighted average of nearby pixels, with weights based on spatial distance and intensity difference. It then explains how the Gaussian range kernel can be approximated using polynomials, allowing the filter to be implemented as a series of Gaussian filters. The algorithm was tested by adding Gaussian noise to an image and filtering with different sigma values, showing improved runtime and quality compared to other bilateral filtering techniques.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    You are on page 1of 10

    Implementation of Fast and accurate

    Bilateral filtering using Gauss


    Polynomial Decomposition on
    MATLAB
    Submitted ByBharadwaj Saripalli (BT12ECE012)
    Honey Gupta (BT12ECE023)
    Ajay Kanetkar (BT12ECE026)
    Surbhit Sinha (BT12ECE080)

    BILATERAL FILTER:

    A non-linear, edge-preserving and noise-reducing smoothing filter for


    images

    Intensity value at each pixel is replaced by a weighted average of intensity


    values from nearby pixels

    Weight can be based on a Gaussian distribution


    Preserves sharp edges by systematically looping through each pixel and
    adjusting weights to the adjacent pixels

    Decomposition into
    Large-scale and Small-scale Layers

    input

    smoothed
    (structure, large scale)

    edge-preserving: Bilateral Filter

    residual
    (texture, small scale)

    Weighted Average of Pixels


    Depends on spatial distance
    and intensity difference

    Pixels across edges have almost influence


    p

    range

    space

    Wp = Normalization term

    GAUSSIAN BILATERAL FILTERING


    Consider a discrete image { f(i) : i I }, where I is some finite rectangular domain
    of Z. The Gaussian bilateral filtering of this image is given by

    where both the spatial and range kernels are Gaussian,

    GAUSS POLYNOMIAL DECOMPOSITION


    Idea is to approximate the range kernel using appropriate polynomials
    and trigonometric functions. By using these approximations in place of
    the Gaussian kernel, the Gaussian function can be approximated using a
    series of Gaussian filtering.
    Consider the translation of the range kernel ( )

    Performing Taylor Series expansion on


    We get

    ALGORITHM
    The steps are shown in the figure:

    IMPLEMENTATION & ANALYSIS


    Gaussian noise of 5% was added to the
    image and results were obtained for
    different values of s.

    CONCLUSION
    The algorithm presented in the paper named Fast and Accurate
    Bilateral Filtering Using Gauss Polynomial Decomposition by Kunal
    N. Chaudhury is studied and implemented using MATLAB on an
    Intel Core i3-3110M CPU @2.40GHz machine with 4 GB memory,
    and results obtained show that the run-time and PSNR are better in
    comparison to the present available bilateral filtering techniques
    and can be used for real time filtering with ease.

    THANK YOU

    You might also like