Java and haarcascade face and mouth detection - mouth as the nose

asked 2016-06-22 01:51:58 -0500

balu gravatar image

Today I begin to test the project which detects a smile in Java and OpenCv. To recognition face and mouth project used haarcascade_frontalface_alt and haarcascade_mcs_mouth But i don't understand why in some reasons project detect nose as a mouth. I have two methods:

private ArrayList<Mat> detectMouth(String filename) {
    int i = 0;
    ArrayList<Mat> mouths = new ArrayList<Mat>();
    // reading image in grayscale from the given path
    image = Highgui.imread(filename, Highgui.CV_LOAD_IMAGE_GRAYSCALE);
    MatOfRect faceDetections = new MatOfRect();
    // detecting face(s) on given image and saving them to MatofRect object
    faceDetector.detectMultiScale(image, faceDetections);
    System.out.println(String.format("Detected %s faces", faceDetections.toArray().length));
    MatOfRect mouthDetections = new MatOfRect();
    // detecting mouth(s) on given image and saving them to MatOfRect object
    mouthDetector.detectMultiScale(image, mouthDetections);
    System.out.println(String.format("Detected %s mouths", mouthDetections.toArray().length));
    for (Rect face : faceDetections.toArray()) {
        Mat outFace = image.submat(face);
        // saving cropped face to picture
        Highgui.imwrite("face" + i + ".png", outFace);
        for (Rect mouth : mouthDetections.toArray()) {
            // trying to find right mouth
            // if the mouth is in the lower 2/5 of the face
            // and the lower edge of mouth is above of the face
            // and the horizontal center of the mouth is the enter of the face
            if (mouth.y > face.y + face.height * 3 / 5 && mouth.y + mouth.height < face.y + face.height
                    && Math.abs((mouth.x + mouth.width / 2)) - (face.x + face.width / 2) < face.width / 10) {
                Mat outMouth = image.submat(mouth);
                // resizing mouth to the unified size of trainSize
                Imgproc.resize(outMouth, outMouth, trainSize);
                mouths.add(outMouth);
                // saving mouth to picture 
                Highgui.imwrite("mouth" + i + ".png", outMouth);
                i++;
            }
        }
    }
    return mouths;
}

and detect smile

private void detectSmile(ArrayList<Mat> mouths) {
        trainSVM();
        CvSVMParams params = new CvSVMParams();
        // set linear kernel (no mapping, regression is done in the original feature space)
        params.set_kernel_type(CvSVM.LINEAR);
    // train SVM with images in trainingImages, labels in trainingLabels, given params with empty samples
        clasificador = new CvSVM(trainingImages, trainingLabels, new Mat(), new Mat(), params);
        // save generated SVM to file, so we can see what it generated
        clasificador.save("svm.xml");
        // loading previously saved file
        clasificador.load("svm.xml");
        // returnin, if there aren't any samples
        if (mouths.isEmpty()) {
            System.out.println("No mouth detected");
            return;
        }
        for (Mat mouth : mouths) {
            Mat out = new Mat();
            // converting to 32 bit floating point in gray scale
            mouth.convertTo(out, CvType.CV_32FC1);
            if (clasificador.predict(out.reshape(1, 1)) == 1.0) {
                System.out.println("Detected happy face");
            } else {
                System.out.println("Detected not a happy face");
            }
        }
    }

training method:

private void train(String flag) {
        String path;
        if (flag.equalsIgnoreCase("positive")) {
            path = trainPath + "smile/";
        } else {
            path = trainPath + "neutral/";
        }
        for (File file : new File(path).listFiles()) {
            Mat img = new Mat();
            Mat con = Highgui.imread(file.getAbsolutePath(), Highgui.CV_LOAD_IMAGE_GRAYSCALE);
            con.convertTo(img, CvType.CV_32FC1, 1.0 / 255.0);
            Imgproc.resize(img, img, trainSize);
            trainingImages.push_back(img.reshape(1, 1));
            if (flag.equalsIgnoreCase("positive")) {
                trainingLabels.push_back(Mat.ones(new Size(1, 1), CvType.CV_32FC1));
            } else {
                trainingLabels.push_back(Mat.zeros(new Size(1, 1), CvType.CV_32FC1));
            }
        }
    }

Examples: For that picture

image description

correctly detects ... (more)

edit retag flag offensive close merge delete

Comments

Aahhh the world of computer vision, where visual agreement is not the same as how patches are represented inside the feature space. Take a look at this research of MIT, and you will discover quite fast why an in the first place, not mouth image, can still be classified as mouth by a model :)

StevenPuttemans gravatar imageStevenPuttemans ( 2016-06-30 07:34:48 -0500 )edit