How to script this: returns all the x coordinates that distance between X and Y are bigger than r distant ?

I put together this, which is returning the y coordinates that are having greater distance than 2 e.g.

%
rng(1); % For reproducibility
X = randn(50,2);%GreenPeak
Y = randn(4,2);%RedPeak;
%imshow(Ifinalb); hold on ;
h = zeros(3,1);
figure;
h(1) = plot(X(:,1),X(:,2),'bx');
hold on;
h(2) = plot(Y(:,1),Y(:,2),'rs','MarkerSize',10);
%title('Heterogenous Data')

%%-----------------------
%Choose weights for each dimension, and specify the chi-square distance function. The distance function must:
%Take as input arguments one row of X, e.g., x, and the matrix Z.
%Compare x to each row of Z.
%Return a vector D of length $n_z$, where $n_z$ is the number of rows of Z.
%Each element of D is the distance between the observation corresponding to x and the observations corresponding to each row of Z
hold on
w = [2; 2];
chiSqrDist = @(x,Z)sqrt((bsxfun(@minus,x,Z).^2)*w);

%Find the indices of the three nearest observations in X to each
%observation in Y.k=3

k = 1;
[Idx,D] = knnsearch(X,Y,'Distance',chiSqrDist,'k',k);
%[Idx,D]= knnsearch(X,Y,'dist','cityblock','k',k);

TableDisInd(:,1)=Idx(:,1);
TableDisInd(:,2)=D(:,1);

Indx2=find(TableDisInd(:,1)>=2);
TableDisInd2=TableDisInd(Indx2,:);

[KSSV]

Indx2=find(TableDisInd(:,1)>=2);

What is 2 in the above? You are selecting the indices which are greater then 2.....which is doing it's job correct.

[Peyman Obeidy]

Thank you for your time. X have 50 coordinates and Y have 4. Only 1 of the Y coordinates is close to one from X list, so I want to exclude that and get all the other 49 coordinates of X.

Two is an example, it can be changed.

[KSSV]

In that case....pick the first index from Idx and remove it from X....

[Peyman Obeidy]

:) How to do this?

Answer 1

[KSSV]

X1 = X ;   % this your X coordinates, in which you want to remove one point 
X1(Idx(1),:) = [] ;   % remove the first index from Idx

[Peyman Obeidy]

Thank you, greatly appreciate your help.

[Peyman Obeidy]

with a bit of modification here is the code;

w = [2; 2];
chiSqrDist = @(x,Z)sqrt((bsxfun(@minus,x,Z).^2)*w);

%Find the indices of the three nearest observations in X to each
%observation in Y.k=3

k = 1;
[Idx,D] = knnsearch(X,Y,'Distance',chiSqrDist,'k',k);
%[Idx,D]= knnsearch(X,Y,'dist','cityblock','k',k);

TableDisInd(:,1)=Idx(:,1);
TableDisInd(:,2)=D(:,1);
% you are introduceing what needs to be delete, so if you want everything
% bigger than 4 you need to delet everything smaller than 4
Indx2=find(TableDisInd(:,2)<4);
TableDisInd2=TableDisInd(Indx2,:);

%use the first col of "TableDisInd2" to find the index in X table
Idx2=TableDisInd2(:,1);

X1 = X ;   % this your X coordinates, in which you want to remove one point 
%X1(Indx2(:,1),:) = [] ;   % remove the first index from Idx
X1(Idx2(:,1),:) = [] ;   % remove all the close distances from  X list