Index exceeds the number of array elements (2).

load featurs_T
load featurs_S
load Group_Train
load Group_Test
load featurs_TLBP
load featurs_SLBP




 result= multisvm(Feat1,Group_Train1,Feat2,Group_Test1);
result1= result;


 result= multisvm(Feat1LBP,Group_Train1,Feat2LBP,Group_Test1);
result2=result;


% First we concatenate all prediciton arrays into one big matrix. 
% Make sure that all prediction arrays are of the same type, I am assumming here that they
% are type double. I am also assuming that all prediction arrays are column vectors.

Prediction = [result1,result2];
Final_decision = zeros(length(Feat2),1);
all_results = [1,2]; %possible outcomes
for row = 1:length(Feat2)
    election_array = zeros(1,2); 
    for col = 1:2 %your five different classifiers
       election_array(Prediction(row,col)) = ... 
           election_array(Prediction(row,col))+1;
    end 
    [~,I] = max(election_array);
    Final_decision(row) = all_results(I);
end

[Benjamin Thompson]

What is your question?

[sun rise]

This error appeared to me

Index exceeds the number of array elements (2).

Error in HOG2 (line 62)
election_array(Prediction(row,col))+1;

[Torsten]

Either "Prediction(row,col)" has less than "(row,col)" elements or "election_array(Prediction(row,col))" has less than "Prediction(row,col)" elements.

You can check by outputting "size(Prediction)" and "size(election_array)".

[Jan]

The error message is clear. We cannot run your code due to the missing inputs. So how can we help you?

[sun rise]

I have two classifiers SVM. I want to combine the results of these two classifiers on a dataset by using majority voting method,and choose the max accuracy among the two classifiers for each image. I'll be gratefull to your help

[Jan]

You still did not ask a question. Torsten gave you a hint how to check the sizes of the arrays. If there is no 2nd element, the readers cannot invent one. Again: How can we help you?

[sun rise]

I have attached a picture. Sizes are shown in work space

[sun rise]

I used the code in this link

https://www.mathworks.com/matlabcentral/answers/460240-how-to-apply-majority-voting-for-classification-ensemble-in-matlab#answer_376487

Answer 1

[Walter Roberson]

max() of a 2d array is a vector so I is a vector. all_results(I) is a vector. You are trying to assign that vector to a scalar left side.