How can I mark corners on a binary image?

I have the nxt problem with my code, it's suppose to detect a hand... Here is the code:

if true
  function varargout = detenciondemano(varargin)
% DETENCIONDEMANO MATLAB code for detenciondemano.fig
%      DETENCIONDEMANO, by itself, creates a new DETENCIONDEMANO or raises the existing
%      singleton*.
%
%      H = DETENCIONDEMANO returns the handle to a new DETENCIONDEMANO or the handle to
%      the existing singleton*.
%
%      DETENCIONDEMANO('CALLBACK',hObject,eventData,handles,...) calls the local
%      function named CALLBACK in DETENCIONDEMANO.M with the given input arguments.
%
%      DETENCIONDEMANO('Property','Value',...) creates a new DETENCIONDEMANO or raises the
%      existing singleton*.  Starting from the left, property value pairs are
%      applied to the GUI before detenciondemano_OpeningFcn gets called.  An
%      unrecognized property name or invalid value makes property application
%      stop.  All inputs are passed to detenciondemano_OpeningFcn via varargin.
%
%      *See GUI Options on GUIDE's Tools menu.  Choose "GUI allows only one
%      instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help detenciondemano

% Last Modified by GUIDE v2.5 12-Dec-2014 19:25:18

% Begin initialization code - DO NOT EDIT gui_Singleton = 1; gui_State = struct('gui_Name', mfilename, ... 'gui_Singleton', gui_Singleton, ... 'gui_OpeningFcn', @detenciondemano_OpeningFcn, ... 'gui_OutputFcn', @detenciondemano_OutputFcn, ... 'gui_LayoutFcn', [] , ... 'gui_Callback', []); if nargin && ischar(varargin{1}) gui_State.gui_Callback = str2func(varargin{1}); end

if nargout [varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:}); else gui_mainfcn(gui_State, varargin{:}); end % End initialization code - DO NOT EDIT

% --- Executes just before detenciondemano is made visible. function detenciondemano_OpeningFcn(hObject, eventdata, handles, varargin) % This function has no output args, see OutputFcn. % hObject handle to figure % eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA) % varargin command line arguments to detenciondemano (see VARARGIN)

% Choose default command line output for detenciondemano handles.output = hObject;

% Update handles structure guidata(hObject, handles);

% UIWAIT makes detenciondemano wait for user response (see UIRESUME) % uiwait(handles.figure1);

% --- Outputs from this function are returned to the command line. function varargout = detenciondemano_OutputFcn(hObject, eventdata, handles) % varargout cell array for returning output args (see VARARGOUT); % hObject handle to figure % eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure varargout{1} = handles.output;

% --- Executes on button press in empezar. function empezar_Callback(hObject, eventdata, handles) % hObject handle to empezar (see GCBO) % eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA)

axes(handles.axes3)

vid = videoinput('macvideo', 1, 'YCbCr422_1280x720'); % Captura una trama por trigger vid.FramesPerTrigger=1; % Salida de la Imagen RGB=color/GRAYSCALE=escala grises vid.ReturnedColorSpace = 'rgb'; % Se le indica a Matlab que la camara no inicie Automaticamente sino a % peticion del usuario triggerconfig(vid,'manual'); % Adquirimos la altura y anchura de la imagen vidRes=get(vid,'VideoResolution'); % Altura de la Imagen imWidth = vidRes(1); % Anchura de la Imagen imHeight = vidRes(2); nBands = get(vid, 'NumberOfBands'); % Crea una Variable q contenga la Imagen para mostrala en el AXIS(handles.axes1) hImage = image(zeros(imHeight, imWidth, nBands), 'parent', handles.axes1); % Empieza Webcam Preview preview(vid, hImage);

for i=1:100 I=getsnapshot(vid); I=imresize(I,0.5); r=I(:,:,1); b=I(:,:,3); g=I(:,:,2); hand=r-b; hand=hand>30; hand=bwareaopen(hand, 13000); loc = regionprops(hand , {'centroid' , 'ConvexArea' , 'Orientation'}); [L , Ne] = bwlabel(hand); CH = bwconvhull(hand);

    if i>5

    BW = edge(CH, 'sobel');
    se = strel('disk', 2);
    BW = imdilate(BW,se);
    BW = imerode(BW,se);
    BW = imfill(BW, 'holes');
    B = bwboundaries(BW, 8, 'holes');
    B = B{1};

    objB = bsxfun(@minus, B, mean(B))
[theta, rho] = cart2pol(objB(:,2), objB(:,1));

%# find corners %#corners = find( diff(diff(rho)>0) < 0 ); %# find peaks [~,order] = sort(rho, 'descend'); corners = order(1:10);

%# plot boundary signature + corners %figure, plot(theta, rho, '.'), hold on %plot(theta(corners), rho(corners), 'ro'), hold off %xlim([-pi pi]), title('Boundary Signature'), xlabel('\theta'), ylabel('\rho')

%# plot image + corners imshow(BW), hold on plot(B(corners,2), B(corners,1), 's', 'MarkerSize',10, 'MarkerFaceColor','r') hold off end

    %imshow(label2rgb(L));
    drawnow;

end

stop(vid); close all clear all

end

Then, I want to mark every vertices from the convex hull image, but only show one... This is the output:

Where can i get and example for do this? I'm always searching and did not find anything... It can be done with OpenCV, but I really want to do it with MatLab..

And, another topic, I was reading about K-curvature but i didn't find any for matlab.

I appreciate very much your answers.

Answer 1

[Image Analyst]

Look at how the Computer Vision System Toolbox can track the man's head as it moves around: http://www.mathworks.com/products/computer-vision/features.html#object-tracking-and-motion-estimation

[Francisco Mendoza]

Yeah, i have already done, indeed, I have the code for tracking man's head at runtime using SURFF; the only problem is that is too slowly..

I want to use K-curvature and convex hull:(