I am currently working to develop an automated diabetic retinopathy detection system. I've used GLCM for feature extraction obtaining Contrast, Correlation, Energy & Homogeneity values. How can I perform classification using these values ?

Question

GANESH SUBRAMANIAM 2014-10-9

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/158024-i-am-currently-working-to-develop-an-automated-diabetic-retinopathy-detection-system-i-ve-used-glcm

评论： GANESH SUBRAMANIAM 2014-10-17

采纳的回答： Greg Heath

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2014-10-10

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/158024-i-am-currently-working-to-develop-an-automated-diabetic-retinopathy-detection-system-i-ve-used-glcm#answer_154637

在 MATLAB Online 中打开

The obvious answer is to use patternnet with

 [ I N] = size(input) % I = 4
 [ C N ] = size(target) % C = Number of classes

Columns of target are {0 1} C-dimensional unit vectors.

For patternnet documentation

 help patternnet
 doc patternnet

For examples of classification data

 help nndatasets
 doc nndatasets

Hope this helps.

Thank you for formally accepting my answer

Greg

3 个评论
显示 1更早的评论隐藏 1更早的评论

GANESH SUBRAMANIAM 2014-10-10

编辑：GANESH SUBRAMANIAM 2014-10-16

Thank You for the reply. But I am not clear how to implement the lines you added. I am adding my code below. { function bloodVessels = ADNPDR(x, threshold)

%Clear Memory & Command Window clc; clear all; close all;

%Read Input Retina Image [f,p] = uigetfile ('*jpg'); x = imread ([p f]); y = rgb2gray(x);

figure (1) subplot (1,1,1) imshow (x,[]),title ('Input Image'); improfile; xlabel (' line segment ') ylabel (' Distance along the ') zlabel ('Intensity Values')

figure (3) subplot (1,1,1) imshow (y), title ('Grayscale Image');

figure (4) subplot (2,2,1:2), imhist (y) title (' a) Histogram'); xlabel('Grayscale Values') ylabel('n^t^h pixel in the grayscale')

HE = histeq(y); subplot (2,2,3:4), imhist (HE) title (' b) Equilized Histogram'); xlabel('Grayscale Values') ylabel('n^t^h pixel in the grayscale')

red_channel = x(:,:,1); green_channel = x(:,:,2); blue_channel = x(:,:,3);

figure (5) subplot (2,2,1) imshow(red_channel), title ('Red Channel'); subplot (2,2,2) imshow(green_channel), title ('Green Channel'); subplot (2,2,3:4) imshow(blue_channel), title ('Blue Channel'); I=green_channel;

%Image adjustment using Adaptive H.E img_adjusted = zeros (size(I), 'uint8'); for ch = 1 : 1 img_adjusted(:,:,ch) = adapthisteq (I(:,:,ch)); end figure (6) subplot (1,2,1) imshow (img_adjusted), title ('Adjusted Input'); subplot (1,2,2) imcontour (img_adjusted,3), title ('Contour Mapping');

%Kirsch's Templates h1=[5 -3 -3; 5 0 -3; 5 -3 -3]/15; h2=[-3 -3 5; -3 0 5; -3 -3 5]/15; h3=[-3 -3 -3; 5 0 -3; 5 5 -3]/15; h4=[-3 5 5; -3 0 5; -3 -3 -3]/15; h5=[-3 -3 -3; -3 0 -3; 5 5 5]/15; h6=[ 5 5 5; -3 0 -3; -3 -3 -3]/15; h7=[-3 -3 -3; -3 0 5; -3 5 5]/15; h8=[ 5 5 -3; 5 0 -3; -3 -3 -3]/15;

%Spatial Filtering by Kirsch's Templates t1=filter2(h1,img_adjusted); t2=filter2(h2,img_adjusted); t3=filter2(h3,img_adjusted); t4=filter2(h4,img_adjusted); t5=filter2(h5,img_adjusted); t6=filter2(h6,img_adjusted); t7=filter2(h7,img_adjusted); t8=filter2(h8,img_adjusted);

figure (7) subplot (2,2,1) imshow(t1), title ('Vessel Extract 1') subplot (2,2,2) imshow(t2), title ('Vessel Extract 2') subplot (2,2,3) imshow(t3), title ('Vessel Extract 3') subplot (2,2,4) imshow(t4), title ('Vessel Extract 4')

figure (8) subplot (2,2,1) imshow(t5), title ('Vessel Extract 5') subplot (2,2,2) imshow(t6), title ('Vessel Extract 6') subplot (2,2,3) imshow(t7), title ('Vessel Extract 7') subplot (2,2,4) imshow(t8), title ('Vessel Extract 8')

% Eccentricity Plot & Value Calculation s = regionprops (green_channel, 'Eccentricity'); Eccentricity = cat (1,s.Eccentricity); figure (9) subplot (1,1,1) plot (Eccentricity), title ('Eccentricity'); hold on plot (Eccentricity (:,1), 'b*'); xlabel('Pixel Value'); ylabel(' Foci of the Ellipse'); hold off disp(Eccentricity), title ('Eccentricity');

% Area Plot & Value Calculation s = regionprops (green_channel, 'Area'); %Finding the actual number of pixels in the region Area = cat (1,s.Area); figure (10) plot (Area), title ('Area'); hold on plot (Area (:,1), 'b*') xlabel('Pixel Value'); ylabel('Axis Length'); hold off disp(Area), title ('Area');

glcms = graycomatrix(green_channel,'Offset',[0 1]); stats = graycoprops(glcms)

% Train Inputs............................................

traininputs=(xlsread('TrainTest.xlsx'))'; traininputs=normc(traininputs); traintargets=(xlsread('tttargets3.xlsx'))';

% nprtool : % Neural Network Pattern Recognition Tool

net = create_pr_net(traininputs,traintargets); trainOutputs = sim(net,traininputs);

disp (trainOutputs); view (net); }

Greg Heath 2014-10-17

>> net = create_pr_net(X,T);

Undefined function 'create_pr_net' for input arguments of type 'double'.

Where is it defined?

GANESH SUBRAMANIAM 2014-10-17

I ain't getting any error like that

请先登录，再进行评论。

I am currently working to develop an automated diabetic retinopathy detection system. I've used GLCM for feature extraction obtaining Contrast, Correlation, Energy & Homogeneity values. How can I perform classification using these values ?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

3 个评论
显示 1更早的评论隐藏 1更早的评论

更多回答（0 个）

另请参阅

类别

标签

产品

Community Treasure Hunt

I am currently working to develop an automated diabetic retinopathy detection system. I've used GLCM for feature extraction obtaining Contrast, Correlation, Energy & Homogeneity values. How can I perform classification using these values ?

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

3 个评论 显示 1更早的评论隐藏 1更早的评论

更多回答（0 个）

另请参阅

类别

标签

产品

Community Treasure Hunt

WeChat

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

3 个评论
显示 1更早的评论隐藏 1更早的评论