How can I display not recognized for someone not in the database?

Hi everyone!I am working on real time face recognition, I have made classifier. The problem that I am having is that if someone outside the database comes in it(the code) will classify him/her inside the database. So how can I determine if someone is not in the database and display not recognized? I am tracking face using KLT algorithm and here's the code in comment

[Ali Subhan]

%%

clear all;

clc;

%%

convnet = alexnet;

featureLayer = 'fc7';

load('FACE_classifier');

% Create the face detector object.

faceDetector = vision.CascadeObjectDetector();

faceDetector.MergeThreshold=9;

% Create the point tracker object.

pointTracker = vision.PointTracker('MaxBidirectionalError', 2);

% Create the webcam object.

cam = webcam();

% Capture one frame to get its size.

videoFrame = snapshot(cam);

frameSize = size(videoFrame);

% Create the video player object.

videoPlayer = vision.VideoPlayer('Position', [100 100 [frameSize(2),

frameSize(1)]+30]);

%%

runLoop = true;

numPts = 0;

frameCount = 0;

while runLoop

    % Get the next frame.
    videoFrame = snapshot(cam);
    videoFrameGray = rgb2gray(videoFrame);
    frameCount = frameCount + 1;

    if numPts < 10
        % Detection mode.
        bbox = faceDetector.step(videoFrameGray);

        if ~isempty(bbox)
            % Find corner points inside the detected region.
            points = detectMinEigenFeatures(videoFrameGray, 'ROI', bbox(1, :));

            % Re-initialize the point tracker.
            xyPoints = points.Location;
            numPts = size(xyPoints,1);
            pause(0.5); title('test Image');
            test=imcrop(videoFrame,bbox);
            imshow(test);
            testSet = imresize(test, [227 227]);
            testFeatures = activations(convnet, testSet, featureLayer);
            predictedLabels = predict(FACE_classifier, testFeatures)
            release(pointTracker);
            initialize(pointTracker, xyPoints, videoFrameGray);

            % Save a copy of the points.
            oldPoints = xyPoints;

            % Convert the rectangle represented as [x, y, w, h] into an
            % M-by-2 matrix of [x,y] coordinates of the four corners. This
            % is needed to be able to transform the bounding box to display
            % the orientation of the face.
            bboxPoints = bbox2points(bbox(1, :));  

            % Convert the box corners into the [x1 y1 x2 y2 x3 y3 x4 y4] 
            % format required by insertShape.
            bboxPolygon = reshape(bboxPoints', 1, []);

            % Display a bounding box around the detected face.
            videoFrame = insertShape(videoFrame, 'Polygon', bboxPolygon, 'LineWidth', 3);

            % Display detected corners.
            videoFrame = insertMarker(videoFrame, xyPoints, '+', 'Color', 'white');

        end

    else
        % Tracking mode.
        [xyPoints, isFound] = step(pointTracker, videoFrameGray);
        visiblePoints = xyPoints(isFound, :);
        oldInliers = oldPoints(isFound, :);

        numPts = size(visiblePoints, 1);       

        if numPts >= 10
            % Estimate the geometric transformation between the old points
            % and the new points.
            [xform, oldInliers, visiblePoints] = estimateGeometricTransform(...
                oldInliers, visiblePoints, 'similarity', 'MaxDistance', 4);            

            % Apply the transformation to the bounding box.
            bboxPoints = transformPointsForward(xform, bboxPoints);

            % Convert the box corners into the [x1 y1 x2 y2 x3 y3 x4 y4] 
            % format required by insertShape.
            bboxPolygon = reshape(bboxPoints', 1, []);            

            % Display a bounding box around the face being tracked.
            videoFrame = insertShape(videoFrame, 'Polygon', bboxPolygon, 'LineWidth', 3);

            % Display tracked points.
            videoFrame = insertMarker(videoFrame, visiblePoints, '+', 'Color', 'white');

            % Reset the points.
            oldPoints = visiblePoints;
            setPoints(pointTracker, oldPoints);
        end

    end

    % Display the annotated video frame using the video player object.
    step(videoPlayer, videoFrame);

    % Check whether the video player window has been closed.
    runLoop = isOpen(videoPlayer);
end

% Clean up. clear cam; release(videoPlayer); release(pointTracker); release(faceDetector);

Answer 1

[Image Analyst]

How about this:

uiwait(warndlg('Not recognized!'));

Oh, and please see this link.

[Ali Subhan]

sorry, I am a newbie don't know how to use it.

[Ali Subhan]

and thanks for the link :)

[sparrow Jr]

Hello, Sir.. Thank you so much for your comment in my thread. I would like to ask you further questions about matlab. Would you mind if I send you an email? Iam so sorry for my comment here.

Best regard, Sparrow.

[Image Analyst]

I don't work in the face recognition field.

You'll get more answers about MATLAB is you ask here than if you ask only one person (me), so ask here.

[Ali Subhan]

Image Analyst what I am trying to say is how can I determine if someone doesn't belong in database?

[Image Analyst]

Measure features about the test face. Compare all those features against the same set of features for every face in your database and compute some sort of distance metric. If the distance metric is small enough, then it's possible they were in the database. If the distance is too high then they probably are not any of the faces in the database. What features did you measure? Keep in mind that I can't write a full blown facial recognition system for you - that would take months if not years.

[Ali Subhan]

I don't know Alex net does the feature extraction. How can I compute distance metric.

[Image Analyst]

Alexnet will tell you. You'll have an output for every person in the database. You should have one of those outputs be true if the person is in there. If the person is not in the training set, then all of the outputs will be false.