help with object recognition matlab

*hello everyone I have this code working for object recognition with one image: http://i32.photobucket.com/albums/d26/blinketo/recon7.jpg *

    RGB = imread('recon7.jpg');
    figure, imshow(RGB);

    %%Step 2: Threshold the Image
    % Convert the image to black and white in order to prepare for
    % boundary tracing using |bwboundaries|.

    I = rgb2gray(RGB);
    %I = wiener2(I1,[5 5]); %function!
    threshold = graythresh(I);
    bw = im2bw(I,threshold);
    figure, imshow(bw)

    %%Step 3: Remove the Noise
    % Using morphology functions, remove pixels which do not belong to the
    % objects of interest.
    BWnobord = imclearborder(bw);
    %BWnobord=bw;
    % remove all object containing fewer than 1000 pixels
    BWnobord = bwareaopen(BWnobord,5000);

    % fill a gap in the pen's cap
    se = strel('disk',20);
    BWnobord = imclose(BWnobord,se);

    % fill any holes, so that regionprops can be used to estimate
    % the area enclosed by each of the boundaries
    BWnobord = imfill(BWnobord,'holes');

    figure, imshow(BWnobord)

    %%Step 4: Find the Boundaries
    % Concentrate only on the exterior boundaries.  Option 'noholes' will
    % accelerate the processing by preventing |bwboundaries| from searching 
    % for inner contours.

    [B,L] = bwboundaries(BWnobord,'noholes');

    % Display the label matrix and draw each boundary
    figure, imshow(label2rgb(L, @jet, [.5 .5 .5]))
    hold on
    for k = 1:length(B)
      boundary = B{k};
      plot(boundary(:,2), boundary(:,1), 'w', 'LineWidth', 2)
    end

    stats = regionprops(L,'Area','Centroid');

    %threshold = 0.94;

    % loop over the boundaries

      % obtain (X,Y) boundary coordinates corresponding to label 'k'
      boundary = B{1};

      % compute a simple estimate of the object's perimeter
      delta_sq = diff(boundary).^2;    
      perimeter = sum(sqrt(sum(delta_sq,2)));

      % obtain the area calculation corresponding to label 'k'
      area = stats(1).Area;

      % compute the roundness metric
      %metric = 4*pi*area/perimeter^2;
      metric= perimeter;
      % display the results
      metric_string = sprintf('%2.2f',metric);

      % mark objects above the threshold with a black circle
      if metric > threshold
        centroid = stats(1).Centroid;
        plot(centroid(1),centroid(2),'ko');
      end

      text(boundary(1,2)-35,boundary(1,1)+13,metric_string,'Color','y',...
           'FontSize',14,'FontWeight','bold');

    title(['Areas or Perimeters of the objects']);
  *

    but the code is not detecting objects in the following image:

http://i32.photobucket.com/albums/d26/blinketo/new.jpg

any suggestions to improve the code so I can detect the object in the second image? thank you in advance.*

Answer 1

[Diamela Duverge]

it doesnt work :(

Answer 2

[Image Analyst]

You'll have to try another method that will handle more situations. It could be color classification, or it could be something else.