IMAGE_DENOISE_SPMD
SPMD Labs Cooperate to Make a Plot

IMAGE_DENOISE_SPMD is a MATLAB program which uses the SPMD (single program, multiple data) command so that multiple MATLAB workers or "labs" can cooperate in an image processing task.

An image can be read into MATLAB using the imread function in the Image Processing Toolbox. Many image processing operations can be broken up among cooperating processors. Using the spmd command, this is done most naturally by distributing the image, so that each worker gets a separate section. Once the processing is complete, the client copy of MATLAB can reassemble the image.

In the example considered here, a good image is damaged by the addition of "salt and pepper" noise; that is, individual pixels have been randomly modified. The result looks unrecognizable, but there is still a great deal of the original information. The approach is to split the color image into R, G and B planes, and to average the color information locally over each plane. In this way, lone error pixels will tend to get blended away.

The function has the form:

function [ x, y, z ] = image_fun ( )

• x is an array containing the original image;
• y is an array containing the noisy image;
• z is an array containing the filtered image;

Depending on the situation, the function could be executed in parallel:

• interactively, and locally, using the matlabpool command;
• indirectly, and locally, using the batch command;
• indirectly, and on the Ithaca cluster, using the batch command;
• indirectly, and on the FSU HPC cluster, using the fsuClusterMatlab command;

Licensing:

The computer code and data files described and made available on this web page are distributed under the GNU LGPL license.

Related Data and Programs:

CONTRAST_SPMD, a MATLAB program which demonstrates the SPMD parallel programming feature for image operations; the client reads an image, the workers increase contrast over separate portions, and the client assembles and displays the results.

CONTRAST2_SPMD, a MATLAB program which demonstrates the SPMD parallel programming feature for image operations; this improves the contrast_spmd program by allowing the workers to share some data; this makes it possible to eliminate artificial "seams" in the processed image.

DIJKSTRA_SPMD, a MATLAB program which uses the SPMD feature to parallelize a simple example of Dijkstra's minimum distance algorithm for graphs.

FACE_SPMD, a MATLAB program which demonstrates the SPMD parallel programming feature; the client has a 3D box that has been dissected into tetrahedrons. Multiple workers cooperate to construct a list of the triangular faces that lie on the boundaries of the box.

FD2D_HEAT_EXPLICIT_SPMD, a MATLAB program which uses the finite difference method and explicit time stepping to solve the time dependent heat equation in 2D. A black and white image is used as the "initial condition". MATLAB's SPMD facility is used to carry out the computation in parallel.

FMINCON_PARALLEL, a MATLAB program which demonstrates the use of MATLAB's FMINCON constrained minimization function, taking advantage of MATLAB's Parallel Computing Toolbox for faster execution.

IMAGE_DENOISE, a MATLAB program which applies image processing techniques to remove noise from an image.

LINEAR_SOLVE_DISTRIBUTED, a MATLAB program which solves a linear system A*x=b using MATLAB's spmd facility, so that the matrix A is "distributed" across multiple MATLAB workers.

MATLAB_PARALLEL, MATLAB programs which illustrate "local" parallel programming on a single computer with MATLAB's Parallel Computing Toolbox.

MATRIX_ASSEMBLE_SPMD, a MATLAB program which demonstrates the SPMD parallel programming feature by having each worker assemble part of the Hilbert matrix, which is then combined into one array by the client program.

PLOT_SPMD, a MATLAB library which demonstrates the SPMD parallel programming feature, by having a number of labs compute parts of a sine plot, which is then displayed by the client process.

PRIME_SPMD, a MATLAB program which counts the number of primes between 1 and N; running in parallel using MATLAB's "SPMD" feature.

QUAD_SPMD, a MATLAB program which estimates an integral using quadrature; running in parallel using MATLAB's "SPMD" feature.

Reference:

The User's Guide for the Parallel Computing Toolbox is available at http://www.mathworks.com/access/helpdesk/help/pdf_doc/distcomp/distcomp.pdf

MathWorks documentation for the Image Processing Toolbox is available at http://www.mathworks.com/access/helpdesk/help/pdf_doc/images/images_tb.pdf.

• Gaurav Sharma, Jos Martin,
  MATLAB: A Language for Parallel Computing,
  International Journal of Parallel Programming,
  Volume 37, Number 1, pages 3-36, February 2009.

Source Code:

• image_fun.m, a MATLAB function which carries out the image operation.
• image_pool.m a script which uses the MATLABPOOL command to run the function locally and interactively.
• image_script.m, a MATLAB script file which simply invokes the function.
• image_batch_local.m, a batch command to run the job indirectly on the local system, plus a few more commands to monitor its progress, print the diary, and destroy the job at the end.
• image_batch_ithaca.m, a batch command to run the job indirectly on the Ithaca cluster, plus a few more commands to monitor its progress, print the diary, and destroy the job at the end.
• image_fsu.m a script which uses the fsuClusterMatlab command to run the function indirectly on the FSU HPC cluster.
• balloons.tif, a TIF image.
• balloons.png, a PNG version of the image.
• balloons_noisy.tif, the noisy image.
• balloons_noisy.png, a PNG version of the image.
• balloons_filtered.tif, the filtered image.
• balloons_filtered.png, a PNG version of the image.
• all_three.png, an image that shows the original picture, the noisy version, and the filtered result.

You can go up one level to the MATLAB source codes.