I see that there's a nice little script in the facerec tutorial that aligns faces in images given positions for the eyes.
I need to get the coordinates for the eyes, though, somehow. Would it work to use the CascadeClassifier with the haarcascade_mcs_eyepair_big model?
I understand that there are many ways to do it (including the patented ASEF technique). I'm just wondering if this is a good way to get started.
how can I align Face Images
↧
↧
OpenCV Developer for Project needed
HI,
I am afraid this is not the right place to ask, but maybe someone can reference me to a good place.
My company develop Solutions to create customized Photobook Solutions. Some years ago we integrated a Third Party SDK to analyse a set of images to do the following:
- Analyse if images show the same or similar objects/scenery
- How many faces are on the image if any (only the number)
- Analyse the image and rate the quality of the image (sharpness, noise, contrast).
The result was each image was rated regarding quality and group the images that show same/similar objects. WE use this input to create automatic photobooks for example.
We looking now for a software developer with OpenCV Experience that develop for us / with us this from scratch, because i do not think there existing ready-to-go SDKs doing this. Enviroment would be C/C++ for use on Windows/Mac/Linux as part of a Qt Framework Solution.
Did anyone interest to work with us on that as part of a contract?
best regards
Frank
↧
how to detect which side of face looking at camera using openCV?
i want to detect the angle of face
↧
Face recognition using haar classifier:How to train and compare with stored images
Hi friends
I'm gonna create a simple face recognizer.
In fact I can detect the face using haar classifier, but I want to compare it with a stored image in my file in order to determine that the detected face is who? (as an example tell me the owner name of the detected image)
Can someone help me?
I read some source codes in the different websites but unfortunately they are not clear for me because I'm beginner.
I greatly appreciate if you guide me step by step or put the source code in answer section.(c++ code)
↧
Myproject.exe has triggered a breakpoint.
Hi guys
When I compile my code I face this error:
> kooh1.exe has triggered a breakpoint.
, I don't know exactly what the problem is!
maybe the size of the array caused this error:
here is a part of my code:**(when it detects a face this error appears)**
if (!frame.empty()){
//clone from original frame
original = frame.clone();
//convert image to gray scale and equalize
cvtColor(original, graySacleFrame, CV_BGR2GRAY);
//equalizeHist(graySacleFrame, graySacleFrame);
//detect face in gray image
face_cascade.detectMultiScale(graySacleFrame, faces, 1.1, 3, 0, cv::Size(90, 90));
//number of faces detected
cout predict(face_resized, label, confidence);
cout getDouble("threshold") = 0) cout
↧
↧
How to get better results with OpenCV face recognition
I'm trying to use OpenCV's face recognition module to recognize 2 faces from a video. I cropped 20 face images of the first subject and 20 face images of the second subject from the video and I use these as my training set.
I've tested Fisherfaces but I'm not getting good results in this program. Sometimes the first subject is classified as the second subject and vice-verse (I mean sometimes it detects the correct lable sometimes it predict incorrectly ), sometimes false detections are classified as one of the two subjects and sometimes other people in the video are classified as one of the two subjects.
How can I improve performance?
I think increasing the face samples may not solve it completely!So what I should do here:
here is a part of my code which check the condition of labels:
if (label == 2){
//string text = format("Person is = %d", label);
Pname = "Mehdi";
}
else if(label == 3)
{
Pname = "Kourosh";
}
else{
Pname = "unknown";
}
↧
Android + OpenCV + Face detection + Custom Layout
Hi,
I am using:
- Android 4.0.3
- OpenCV 2.4.2
- Samsung Galaxy S2
The face-detection example (from the opencv 2.4.2) is working perfectly.
But now, I would like to create a custom layout and actually work with just the data extracted from face detection and build a game on it. Not necessarily having the FdView surface taking the entire screen.
I have done these modifications below, but just a black screen is displayed.
Added a fd.xml layout:
↧
Face stitch - Doubt
Hello guys, good night. I am studying to assemble the mosaic of a face. Does anyone know tell me what function can I use to join the yellow dots on the left of the image with the yellow dots on the right image and assemble the mosaic?I need to modify the image left joins the right. I appreciate the help.
↧
Method to detect eye, nose and mouth
There is another method besides Haar to detect eye, nose and mouth in the image? Because I was using the Haar and when the face is up, it detects more than one eye, nose and mouth.
Can someone help me.
↧
↧
Will decreasing the video dimension will reduce the resolution?
In order to speed up face detection process, some will reduce the video or image dimension. Will it makes the resolution become worst and effect the face recognition process?
↧
Like the facerec module in OPENCV for Face Recognition, is there any support for GPU with OpenCV in facerecognition
Would like to know if it is possible to do face recognition using GPU accelerated OpenCV
↧
How does stereocam prevents anti face spoofing?
I am struck with face spoofing. Right now I can setup stereo webcam and take images from left and right webcam simulatenously(at least, I am practicing concurrent programming to do this job).
I can extract the eyes, nose, mouth, face center correctly. I had search on face spoofing publication. I usually found texture, skin, or something similar analysis on the single picture. And the prominent technique is 3D face scanner by maser
**Question:**
I do not know how to let computer distinguish between single picture(spoofing case) and real face(human face).
I heard that is not difficult, but I could not figure out.
Please guide me some clue then I will report back what I found.
I can extract the eyes, nose, mouth, face center correctly. I had search on face spoofing publication. I usually found texture, skin, or something similar analysis on the single picture. And the prominent technique is 3D face scanner by maser
**Question:**
I do not know how to let computer distinguish between single picture(spoofing case) and real face(human face).
I heard that is not difficult, but I could not figure out.
Please guide me some clue then I will report back what I found.
↧
Native method not found: org.opencv.imgproc.Imgproc.rectangle_1:(JDDDDDDDDI)V
Hello there.
I'm syafiq and I'm new to OpenCv. I'm currently developing an Face Recognition on Android Studio. I have obtain a source code from github, but the source code using an old version of OpenCV (OpenCV 2.4.10) and I'm using the latest version which is 3.0.0. There's no error on the code and It successful to open the app, and the camera works fine. But when I pointed to someone face it's suddenly stop working.
The error that I've received is:
Process: com.example.syafiq.test, PID: 3249
java.lang.UnsatisfiedLinkError: Native method not found: org.opencv.imgproc.Imgproc.rectangle_1:(JDDDDDDDDI)V
at org.opencv.imgproc.Imgproc.rectangle_1(Native Method)
at org.opencv.imgproc.Imgproc.rectangle(Imgproc.java:2779)
at com.example.syafiq.test.FdActivity.onCameraFrame(FdActivity.java:431)
at org.opencv.android.CameraBridgeViewBase.deliverAndDrawFrame(CameraBridgeViewBase.java:393)
at org.opencv.android.JavaCameraView$CameraWorker.run(JavaCameraView.java:346)
at java.lang.Thread.run(Thread.java:841)
The (Imgproc.java:2779) pointed here:
rectangle_1(img.nativeObj, pt1.x, pt1.y, pt2.x, pt2.y, color.val[0], color.val[1], color.val[2], color.val[3], thickness);
The (FdActivity.java:431) pointed here:
(line430) for (int i = 0; i
↧
↧
Android Source code for face recognition using OpenCV
I have searched and got source code but all are unfortunately stopped. Can anyone provide me a link please.
Thank you in advance.
↧
OpenCV 3.1.0 Face module built , can't import in Python
I cmaked OpenCV 3.1.0 with success and then cmaked extras:
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D BUILD_PYTHON_SUPPORT=ON ..
cmake -D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib/modules ..
sudo make
sudo make install
sudo ldconfig
I think Face module is OK also:
$~/opencv/build/lib$ ls libopencv_face.so*
libopencv_face.so libopencv_face.so.3.1 libopencv_face.so.3.1.0
/usr/local/lib$ ls libopencv_face*
libopencv_face.so libopencv_face.so.3.1 libopencv_face.so.3.1.0
However, I can't import Face module in Python:
>>> import cv2>>> cv2.face
Traceback (most recent call last):
File "", line 1, in
AttributeError: 'module' object has no attribute 'face'
Thanks in advance.
↧
how to improve the accuracy of face recognition
Hi, I want to test the code about face recognition below on the page
http://docs.opencv.org/2.4/modules/contrib/doc/facerec/tutorial/facerec_video_recognition.html
Compiling was successful. So I made face image database which consists of my picture and several celebrities on the internet, But the accuracy was very poor. Could you tell me how to improve the accuracy of face recognition? I do not have any idea about it.
Thank you for your reading.
↧
How to install extra modules ( eg : face ) of opencv 3.1.1 on ubuntu
Please provide the details . I am new to opencv
I got an error when i tried recog = cv.createFisherfaceRecognizer()
↧
↧
face detection of animated face
Is it possible for opencv to execute face recognition of an animated face and not a face in a picture that was just put in front of the camera ?
↧
Build Opencv 3.1 + Contrib (face module) for Java
Hi guys,
I'm looking to use in my Java application the face recognition features provided in the contrib modules but I'm facing a blocking issue : I can't manage to build the opencv_java310.dll.
I have read a lot and tried all that I could think about and today I'm requesting your help please.
In brief, the log file (opencv\build\modules\java\opencv_java.dir\Debug\opencv_java.log) after the build process fails show:
>[...]> face.cpp
1>C:\DEV\C\opencv\build\modules\java\face.cpp(1726):> error C2664: 'bool> cv::face::TopNPredictCollector::filter(int> *,double *,const int)' : cannot convert argument 1 from 'jint *' to> 'int *'> Types pointed to are unrelated; conversion requires> reinterpret_cast, C-style cast or> function-style cast>>1>C:\DEV\C\opencv\build\modules\java\face.cpp(1961):> error C2664: 'bool> cv::face::PredictCollector::defaultFilter(int> *,double *,const int)' : cannot convert argument 1 from 'jint *' to> 'int *'> Types pointed to are unrelated; conversion requires> reinterpret_cast, C-style cast or> function-style cast>>1>C:\DEV\C\opencv\build\modules\java\face.cpp(2032):> error C2664: 'bool> cv::face::PredictCollector::filter(int> *,double *,const int)' : cannot convert argument 1 from 'jint *' to> 'int *'> Types pointed to are unrelated; conversion requires> reinterpret_cast, C-style cast or> function-style cast>>1>C:\DEV\C\opencv\build\modules\java\face.cpp(2504):> error C2664: 'bool> cv::face::MinDistancePredictCollector::filter(int> *,double *,const int)' : cannot convert argument 1 from 'jint *' to> 'int *'> Types pointed to are unrelated; conversion requires> reinterpret_cast, C-style cast or> function-style cast>>1>Done Building Project "C:\DEV\C\opencv\build\modules\java\opencv_java.vcxproj">(Rebuild target(s)) -- FAILED.
My cmake log shows:
-Python 3.4.4 64 bits
-Ant 1.8.4
-Java jdk 1.7 64 bits
I'm building with Visual Studio 12 (2013)
Below are the changes I made in cmake:
- BUILD_SHARED_LIBS:BOOL=0
- BUILD_opencv_line_descriptor:BOOL=0
- BUILD_opencv_bgsegm:BOOL=0
- OPENCV_EXTRA_MODULES_PATH:PATH=C:/DEV/C/opencv_contrib-master/modules
- BUILD_opencv_rgbd:BOOL=0
- BUILD_opencv_stitching:BOOL=0
- BUILD_TESTS:BOOL=0
- BUILD_opencv_surface_matching:BOOL=0
- BUILD_opencv_videostab:BOOL=0
- BUILD_opencv_saliency:BOOL=0
- BUILD_opencv_reg:BOOL=0
- BUILD_opencv_bioinspired:BOOL=0
- BUILD_opencv_calib3d:BOOL=0
- BUILD_PERF_TESTS:BOOL=0
- BUILD_opencv_datasets:BOOL=0
- BUILD_opencv_features2d:BOOL=0
- BUILD_DOCS:BOOL=0
- BUILD_opencv_ccalib:BOOL=0
- BUILD_opencv_optflow:BOOL=0
I have also tried to build contrib with the version 2.4.9 and 3.0 in case there was a compatibiliy issue but no luck.
Please let me know if you need any other information. That's my last hope I fear.
Thanks.
↧
face recognition
Who tells me where to find the source (C ++) of a program to do face recognition from webcam. Including training needed to recognize faces in the video. I would not lose too much time because looking on the internet it seems that many have already done something similar. So as to devote to its integration in a project of mine. Thank you
↧
More Pages to Explore .....
