Scribd
Upload
4 views

Assignment 3

Uploaded by

Naman Bhatia
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

Assignment 3

Uploaded by

Naman Bhatia
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Q 1.

write a program to read an image and add noise in it, then apply CNN model to remove
it

Q2. Write a program to Create CNN model, and apply it to enhance the image picture
quality

Q 3. Explain the DL with the help of Applications of deep learning in object recognition

Q 4. Write short notes

(1).study on chest X-rays (2). CT Scan

(3). 3D radiological images Visualization (4). unsupervised learning and Supervised


learning

Q 5. Explain faster recurrent neural networks (FRNN) for disease detection and
visualization

Q 6. Explain the Role of machine learning and deep learning in disease visualization

CNN code:-

clc

clear all

close all

% % load data

imds = imageDatastore('C:\Users\vijaykumars\Downloads\cnncode (1)',...

'IncludeSubfolders',true,...

'LabelSource','foldernames');

dnds = denoisingImageDatastore(imds,...

'PatchesPerImage',512,...

'PatchSize',50,...

'GaussianNoiseLevel',[0.01 0.1],...

'ChannelFormat','grayscale')

% % layer design
layers = [ ...

imageInputLayer([50 50 1])

convolution2dLayer(3,64,'Stride',1,'Padding',[1 1 1 1])

reluLayer

convolution2dLayer(3,64,'Stride',1,'Padding',[2 2 2 2])

reluLayer

convolution2dLayer(3,64,'Stride',1,'Padding',[1 1 1 1])

reluLayer

convolution2dLayer(3,1)

regressionLayer]

options = trainingOptions('adam', ...

'MiniBatchSize',128, ...

'MaxEpochs',20, ... % was 6

'ValidationFrequency',5, ...

'InitialLearnRate',1e-4,'Plots','training-progress');

% % network training

[convnet, traininfo] = trainNetwork(dnds,layers,options);

%inp=imread('cameraman.tif');

inp=imread('C:\Users\vijaykumars\Downloads\cnncode (1)\peppers256.PNG');

noise=imnoise(inp,'gaussian',0.1,0.001);

figure,

imshow(noise)

title('noisy image ')


denoisedR = denoiseImage(noise,convnet);

figure,

subplot(2,1,1)

imshow(noise);

title('noisy')

subplot(2,1,2)

imshow(denoisedR )

title('denoised ')

You might also like