# MATLAB IMAGE PROCESSING PROJECTS

Matlab image processing projects are created and implemented for engineering students and some research scholars. Matlab tool supports to develop image processing concepts with the help of graphics, data import and export, mathematics, programming scripts and functions Matlab contains several toolboxes to easily perform operations for image processing projects.

## ToolBox Used in Matlab Image Processing Projects.

• Communication System Toolbox.
• Bioinformatics Toolbox.
• Data Acquisition Toolbox.
• Computer Vision Toolbox.
• DSP System Toolbox.
• Neural Network Toolbox.

Mathematical Functions used in Matlab Image Processing Projects:

• Fourier analysis.
• Numerical integration.
• Filtering.
• Solving ordinary differential equations.
• Linear Algebra.
• Completed Matlab Image Processing Projects 81%
• ON Going Matlab Image Processing Projects 31%

### Applications of Matlab Image Processing Projects:

• Medical Imaging.
• Video and Image Compression and Transmission.
• Computer graphics.
• Computer vision.
• Optical imaging. Steps followed in Matlab Image Processing Projects:

• Image Acquisition.
• Pre-Processing.
• Image Formation.
• Image Enhancement.
• Segmentation.
• Feature Extraction.
• Feature Selection.
• Classification.

Application areas of image processing:

• Artificial intelligence
• Pattern recognition
• Biological vision
• Robot Vision
• Machine learning
• Map revision

Sample code for Data Acquisition [ Matlab Image Processing Projects]

% Write and Read to a NI USB-6008 DAQ device
clear
clc
% Initialization———————–
% Analog Output:
ao = analogoutput(‘nidaq’, ‘Dev1’);
% Analog Output – Channel 0
% Write Data—————————
ao_value = 3.5;
putsample(ao, ao_value)
ai_value = getsample(ai)
% Cleaning Up————————–
delete(ai)
delete(ao)

Sample Code for Machine Learning: Naïve Bayes Classification [ Matlab Image Processing Projects]

% The multivariate multinomial distribution (_mvmn_) is appropriate for
% categorical features
dist = repmat({‘normal’},1,ncols-1);
dist(catPred) = {‘mvmn’};

% Train the classifier
Nb = NaiveBayes.fit(Xtrain,Ytrain,’Distribution’,dist);

% Make a prediction for the test set
Y_Nb = Nb.predict(Xtest);

% Compute the confusion matrix
C_nb = confusionmat(Ytest,Y_Nb);
% Examine the confusion matrix for each class as a percentage of the true class
C_nb = bsxfun(@rdivide,C_nb,sum(C_nb,2)) * 100