Hi everyone, I modified this code designed for detecting and tracking faces captured by a camera to work with a recorded video. Now, I want to crop the detected and tracked faces into a separate folder

Hi everyone, I modified this code designed for detecting and tracking faces captured by a camera to work with a recorded video. Now, I want to crop the detected and tracked faces into a separate folder but was given me error. Please, someone should help me with the cropping. The code is as shown below. Thanks

clear classes;

Instantiate video device, face detector, and KLT object tracker

vidObj = 'C:\Users\Asirajdin\Documents\T Chapters\Practical Implementation of face detection in matlab\New folder\matlab-viola-jones-master\detectAndTrackFaces1\classroom.mp4';

v = VideoReader(vidObj);

faceDetector = vision.CascadeObjectDetector(); % Finds faces by default

tracker = MultiObjectTrackerKLT;

vision.VideoFileReader

Get a frame for frame-size information

frame = read(v,1);

frameSize = size(frame);

Create a video player instance

videoPlayer = vision.VideoPlayer('Position',[200 100 fliplr(frameSize(1:2)+30)]);

Iterate until we have successfully detected a face

bboxes = [];

while isempty(bboxes)

framergb = readFrame(v,'native');

frame = rgb2gray(framergb);

bboxes = faceDetector.step(frame);

end

tracker.addDetections(frame, bboxes);

And loop until the player is closed

frameNumber = 0;

keepRunning = true;

disp('Press Ctrl-C to exit...');

pathName ='C:\Users\Asirajdin\Documents\T Chapters\Practical Implementation of face detection in matlab\New folder\matlab-viola-jones-master\detectAndTrackFaces1\Cropped';

while keepRunning

if v.NumFrames==0

break

end

framergb = readFrame(v,'native');

frame = rgb2gray(framergb);

if mod(frameNumber, 10) == 0

% (Re)detect faces.

%

% NOTE: face detection is more expensive than imresize; we can

% speed up the implementation by reacquiring faces using a

% downsampled frame:

% bboxes = faceDetector.step(frame);

bboxes = 2 * faceDetector.step(imresize(frame, 0.5));

if ~isempty(bboxes)

tracker.addDetections(frame, bboxes);

end

else

% Track faces

tracker.track(frame);

end

% Display bounding boxes and tracked points.

displayFrame = insertObjectAnnotation(framergb, 'rectangle',...

tracker.Bboxes, tracker.BoxIds);

displayFrame = insertMarker(displayFrame, tracker.Points);

videoPlayer.step(displayFrame);

for i = 1 : size(displayFrame, 1)

J = imcrop(videoPlayer.step(displayFrame),displayFrame(i,:));

fileName = fullfile(pathName,sprintf('Face%d.png',frameNumber));

imwrite(J,fileName) ; % Save image

imshow(J);

end

frameNumber = frameNumber + 1;

end

[asirajdin]

I want the faces detected and tracked to be cropped at the end of the whole video session. Thanks

Answer 1

[asirajdin]

Due to continuous effort, I am able to modified the code and its now working properly. see the working code below:

Thanks.

clear classes;

%Instantiate video device, face detector, and KLT object tracker

vidObj = 'specify the video file directory';

v = VideoReader(vidObj);

faceDetector = vision.CascadeObjectDetector(); % Finds faces by default

tracker = MultiObjectTrackerKLT;

vision.VideoFileReader

%Get a frame for frame-size information

frame = read(v,1);

frameSize = size(frame);

%Create a video player instance

videoPlayer = vision.VideoPlayer('Position',[200 100 fliplr(frameSize(1:2)+30)]);

%Iterate until we have successfully detected a face

bboxes = [];

while isempty(bboxes)

framergb = readFrame(v,'native');

frame = rgb2gray(framergb);

bboxes = faceDetector.step(frame);

end

tracker.addDetections(frame, bboxes);

%And loop until the player is closed

frameNumber = 0;

keepRunning = true;

pathName ='specify the path to the crop folder here';

while keepRunning

if frameNumber>=v.NumFrames

close(videoPlayer);

clear vidObj;

break;

end

framergb = readFrame(v,'native');

frame = rgb2gray(framergb);

if mod(frameNumber, 5) == 0

% (Re)detect faces.

%

% NOTE: face detection is more expensive than imresize; we can

% speed up the implementation by reacquiring faces using a

% downsampled frame:

% bboxes = faceDetector.step(frame);

bboxes = 2 * faceDetector.step(imresize(frame, 0.5));

if ~isempty(bboxes)

tracker.addDetections(frame, bboxes);

end

else

% Track faces

tracker.track(frame);

end

% Display bounding boxes and tracked points.

displayFrame = insertObjectAnnotation(framergb, 'rectangle',...

tracker.Bboxes, tracker.BoxIds);

displayFrame = insertMarker(displayFrame, tracker.Points);

videoPlayer.step(displayFrame);

for i = 1 : size(bboxes, 1)

J = imcrop(framergb,bboxes(i,:));

fileName = fullfile(pathName,sprintf('Face%d.png',i));

imwrite(J,fileName) ; % Save image

figure(2);

subplot(11, 3,i);

imshow(J);

end

frameNumber = frameNumber + 1;

end