Java Code Examples for org.opencv.core.Mat#clone()

/**
 * Process a image and return a mask
 * @param input - Input image to process
 * @param mask - Output mask
 */
@Override
public void process(Mat input, Mat mask) {
    // Copy the input to working mat
    workingMat = input.clone();
    // Convert the input to HSV color space
    Imgproc.cvtColor(workingMat,workingMat,Imgproc.COLOR_RGB2HSV_FULL);

    // Blur the imgae
    Imgproc.GaussianBlur(workingMat,workingMat,new Size(5,5),0);

    // Run a inRange mask using the color and range
    Scalar lower = new Scalar(perfect.val[0] - (range.val[0]/2), perfect.val[1] - (range.val[1]/2),perfect.val[2] - (range.val[2]/2));
    Scalar upper = new Scalar(perfect.val[0] + (range.val[0]/2), perfect.val[1] + (range.val[1]/2),perfect.val[2] + (range.val[2]/2));
    Core.inRange(workingMat,lower,upper,mask);
}
 

private static List<Mat> globalAdaptation(Mat b, Mat g, Mat r, int rows, int cols) {
	// Calculate Lw & maximum of Lw
	Mat Lw = new Mat(rows, cols, r.type());
	Core.multiply(r, new Scalar(rParam), r);
	Core.multiply(g, new Scalar(gParam), g);
	Core.multiply(b, new Scalar(bParam), b);
	Core.add(r, g, Lw);
	Core.add(Lw, b, Lw);
	double LwMax = Core.minMaxLoc(Lw).maxVal; // the maximum luminance value
	// Calculate log-average luminance and get global adaptation result
	Mat Lw_ = Lw.clone();
	Core.add(Lw_, new Scalar(0.001), Lw_);
	Core.log(Lw_, Lw_);
	double LwAver = Math.exp(Core.sumElems(Lw_).val[0] / (rows * cols));
	Mat Lg = Lw.clone();
	Core.divide(Lg, new Scalar(LwAver), Lg);
	Core.add(Lg, new Scalar(1.0), Lg);
	Core.log(Lg, Lg);
	Core.divide(Lg, new Scalar(Math.log(LwMax / LwAver + 1.0)), Lg); // Lg is the global adaptation
	List<Mat> list = new ArrayList<>();
	list.add(Lw);
	list.add(Lg);
	return list;
}
 

private static ArrayList<Rect> getContourArea(Mat mat) {
	Mat hierarchy = new Mat();
	Mat image = mat.clone();
	List<MatOfPoint> contours = new ArrayList<MatOfPoint>();
	Imgproc.findContours(image, contours, hierarchy, Imgproc.RETR_EXTERNAL, Imgproc.CHAIN_APPROX_SIMPLE);
	Rect rect = null;
	double maxArea = 300;
	ArrayList<Rect> arr = new ArrayList<Rect>();
	for (int i = 0; i < contours.size(); i++) {
		Mat contour = contours.get(i);
		double contourArea = Imgproc.contourArea(contour);
		if (contourArea > maxArea) {
			rect = Imgproc.boundingRect(contours.get(i));
			arr.add(rect);
		}
	}
	return arr;
}
 

/**
 *
 * 画出所有的矩形
 * 
 * @param src
 * @return
 */
public static Mat paintCon(Mat src) {
	Mat cannyMat = GeneralUtils.canny(src);
	List<MatOfPoint> contours = ContoursUtils.findContours(cannyMat);

	Mat rectMat = src.clone();
	Scalar scalar = new Scalar(0, 0, 255);
	for (int i = contours.size() - 1; i >= 0; i--) {
		MatOfPoint matOfPoint = contours.get(i);
		MatOfPoint2f matOfPoint2f = new MatOfPoint2f(matOfPoint.toArray());

		RotatedRect rect = Imgproc.minAreaRect(matOfPoint2f);

		Rect r = rect.boundingRect();

		System.out.println(r.area() + " --- " + i);

		rectMat = paintRect(rectMat, r, scalar);

	}

	return rectMat;
}
 

private static Mat calWeight(Mat img, Mat L) {
	Core.divide(L, new Scalar(255.0), L);
	L.convertTo(L, CvType.CV_32F);
	// calculate laplacian contrast weight
	Mat WL = FeatureWeight.LaplacianContrast(L);
	WL.convertTo(WL, L.type());
	// calculate Local contrast weight
	Mat WC = FeatureWeight.LocalContrast(L);
	WC.convertTo(WC, L.type());
	// calculate the saliency weight
	Mat WS = FeatureWeight.Saliency(img);
	WS.convertTo(WS, L.type());
	// calculate the exposedness weight
	Mat WE = FeatureWeight.Exposedness(L);
	WE.convertTo(WE, L.type());
	// sum
	Mat weight = WL.clone();
	Core.add(weight, WC, weight);
	Core.add(weight, WS, weight);
	Core.add(weight, WE, weight);
	return weight;
}
 

public static Mat[] LaplacianPyramid(Mat img, int level) {
	Mat[] lapPyr = new Mat[level];
	//Mat mask = filterMask(img);
	lapPyr[0] = img.clone();
	Mat tmpImg = img.clone();
	for (int i = 1; i < level; i++) {
		// resize image
		Imgproc.resize(tmpImg, tmpImg, new Size(), 0.5, 0.5, Imgproc.INTER_LINEAR);
		lapPyr[i] = tmpImg.clone();
	}
	// calculate the DoG
	for (int i = 0; i < level - 1; i++) {
		Mat tmpPyr = new Mat();
		Imgproc.resize(lapPyr[i + 1], tmpPyr, lapPyr[i].size(), 0, 0, Imgproc.INTER_LINEAR);
		Core.subtract(lapPyr[i], tmpPyr, lapPyr[i]);
	}
	return lapPyr;
}
 

private static Mat calWeight(Mat img, Mat L) {
	Core.divide(L, new Scalar(255.0), L);
	L.convertTo(L, CvType.CV_32F);
	// calculate laplacian contrast weight
	Mat WL = WeightCalculate.LaplacianContrast(L);
	WL.convertTo(WL, L.type());
	// calculate Local contrast weight
	Mat WC = WeightCalculate.LocalContrast(L);
	WC.convertTo(WC, L.type());
	// calculate the saliency weight
	Mat WS = WeightCalculate.Saliency(img);
	WS.convertTo(WS, L.type());
	// calculate the exposedness weight
	Mat WE = WeightCalculate.Exposedness(L);
	WE.convertTo(WE, L.type());
	// sum
	Mat weight = WL.clone();
	Core.add(weight, WC, weight);
	Core.add(weight, WS, weight);
	Core.add(weight, WE, weight);
	return weight;
}
 

@Override
public Mat process(@NonNull Mat frame) {
    if (frame.empty()) {
        Log.e("Invalid input frame.");
        return null;
    }
    Mat tmp = frame.clone();
    // Apply gaussian blur
    for (int i = 0; i < REPETITIONS; i++) {
        Imgproc.GaussianBlur(tmp, tmp, new Size(KERNEL_SIZE, KERNEL_SIZE), 0);
    }
    return tmp;
}
 

public static Rect detectBorder(Mat original){
    Mat src = original.clone();
    Log.d(TAG, "1 original: " + src.toString());

    Imgproc.GaussianBlur(src, src, new Size(3, 3), 0);
    Log.d(TAG, "2.1 --> Gaussian blur done\n blur: " + src.toString());

    Imgproc.cvtColor(src, src, Imgproc.COLOR_RGBA2GRAY);
    Log.d(TAG, "2.2 --> Grayscaling done\n gray: " + src.toString());

    Mat sobelX = new Mat();
    Mat sobelY = new Mat();

    Imgproc.Sobel(src, sobelX, CvType.CV_32FC1, 2, 0, 5, 1, 0);
    Log.d(TAG, "3.1 --> Sobel done.\n X: " + sobelX.toString());
    Imgproc.Sobel(src, sobelY, CvType.CV_32FC1, 0, 2, 5, 1, 0);
    Log.d(TAG, "3.2 --> Sobel done.\n Y: " + sobelY.toString());

    Mat sum_img = new Mat();
    Core.addWeighted(sobelX, 0.5, sobelY, 0.5, 0.5, sum_img);
    //Core.add(sobelX, sobelY, sum_img);
    Log.d(TAG, "4 --> Addition done. sum: " + sum_img.toString());

    sobelX.release();
    sobelY.release();

    Mat gray = new Mat();
    Core.normalize(sum_img, gray, 0, 255, Core.NORM_MINMAX, CvType.CV_8UC1);
    Log.d(TAG, "5 --> Normalization done. gray: " + gray.toString());
    sum_img.release();

    Mat row_proj = new Mat();
    Mat col_proj = new Mat();
    Core.reduce(gray, row_proj, 1, Core.REDUCE_AVG, CvType.CV_8UC1);
    Log.d(TAG, "6.1 --> Reduce done. row: " + row_proj.toString());

    Core.reduce(gray, col_proj, 0, Core.REDUCE_AVG, CvType.CV_8UC1);
    Log.d(TAG, "6.2 --> Reduce done. col: " + col_proj.toString());
    gray.release();

    Imgproc.Sobel(row_proj, row_proj, CvType.CV_8UC1, 0, 2);
    Log.d(TAG, "7.1 --> Sobel done. row: " + row_proj.toString());

    Imgproc.Sobel(col_proj, col_proj, CvType.CV_8UC1, 2, 0);
    Log.d(TAG, "7.2 --> Sobel done. col: " + col_proj.toString());

    Rect result = new Rect();

    int half_pos = (int) (row_proj.total()/2);
    Mat row_sub = new Mat(row_proj, new Range(0, half_pos), new Range(0, 1));
    Log.d(TAG, "8.1 --> Copy sub matrix done. row: " + row_sub.toString());
    result.y = (int) Core.minMaxLoc(row_sub).maxLoc.y;
    Log.d(TAG, "8.2 --> Minmax done. Y: " + result.y);
    row_sub.release();
    Mat row_sub2 = new Mat(row_proj, new Range(half_pos, (int) row_proj.total()), new Range(0, 1));
    Log.d(TAG, "8.3 --> Copy sub matrix done. row: " + row_sub2.toString());
    result.height = (int) (Core.minMaxLoc(row_sub2).maxLoc.y + half_pos - result.y);
    Log.d(TAG, "8.4 --> Minmax done. Height: " + result.height);
    row_sub2.release();

    half_pos = (int) (col_proj.total()/2);
    Mat col_sub = new Mat(col_proj, new Range(0, 1), new Range(0, half_pos));
    Log.d(TAG, "9.1 --> Copy sub matrix done. col: " + col_sub.toString());
    result.x = (int) Core.minMaxLoc(col_sub).maxLoc.x;
    Log.d(TAG, "9.2 --> Minmax done. X: " + result.x);
    col_sub.release();
    Mat col_sub2 = new Mat(col_proj, new Range(0, 1), new Range(half_pos, (int) col_proj.total()));
    Log.d(TAG, "9.3 --> Copy sub matrix done. col: " + col_sub2.toString());
    result.width = (int) (Core.minMaxLoc(col_sub2).maxLoc.x + half_pos - result.x);
    Log.d(TAG, "9.4 --> Minmax done. Width: " + result.width);
    col_sub2.release();

    row_proj.release();
    col_proj.release();
    src.release();

    return result;
}
 

public Mat createMask(Mat camera) {				
	// copy as we are going to destruct those images maybe
	Mat camBlur= camera.clone();
	Mat backgroundBlur = calib.getBackgroundImage().clone();

	// remove noise
	Imgproc.blur(backgroundBlur, backgroundBlur, new Size(calib.getBlurSize(), calib.getBlurSize()));
	Imgproc.blur(camBlur, camBlur, new Size(calib.getBlurSize(), calib.getBlurSize()));

	// take abs diff and create binary image in all 3 channels
	Mat diff = new Mat();
	Core.absdiff(backgroundBlur, camBlur, diff);
	Imgproc.threshold(diff, diff, calib.getSubtractionThreshold(), 255, Imgproc.THRESH_BINARY);

	// extract color channels and merge them to single bitmask
	Mat r = ColorSpace.getChannel(diff, 2);
	Mat g = ColorSpace.getChannel(diff, 1);
	Mat b = ColorSpace.getChannel(diff, 0);

	Mat mask = r.clone();
	Core.add(mask, g, mask);
	Core.add(mask, b, mask);
	
	// dilate to remove some black gaps within balls
	Imgproc.dilate(mask, mask, Imgproc.getStructuringElement(Imgproc.MORPH_ELLIPSE, new Size(calib.getMorphSize(), calib.getMorphSize())));

	return mask;
}
 

public void smoothImage() {
    // Smoothing, also called blurring, will make the edges soother.
    Mat source = Imgcodecs.imread("cat.jpg");
    Mat destination = source.clone();
    for (int i = 0; i < 25; i++) {
        Mat sourceImage = destination.clone();
        Imgproc.blur(sourceImage, destination, new Size(3.0, 3.0));
    }
    Imgcodecs.imwrite("smoothCat.jpg", destination);
}
 

public static double blkEstimateEachChannel(Mat blkIm, double airlight, double lambda, double fTrans) {
	double Trans = 0.0;
	double nTrans = Math.floor(1.0 / fTrans * 128);
	double fMinCost = Double.MAX_VALUE;
	int numberOfPixels = blkIm.rows() * blkIm.cols() * blkIm.channels();
	int nCounter = 0;
	while (nCounter < (int) (1 - fTrans) * 10) {
		// initial dehazing process to calculate the loss information
		Mat channel = blkIm.clone();
		channel = preDehaze(channel, airlight, nTrans);
		// find the pixels with over-255 value and below-0 value, and
		// calculate the sum of information loss
		double nSumOfLoss = 0.0;
		for (int i = 0; i < channel.rows(); i++) {
			for (int j = 0; j < channel.cols(); j++) {
				if (channel.get(i, j)[0] > 255.0) nSumOfLoss += (channel.get(i, j)[0] - 255.0) * (channel.get(i, j)[0] - 255.0);
				else if (channel.get(i, j)[0] < 0.0) nSumOfLoss += channel.get(i, j)[0] * channel.get(i, j)[0];
			}
		}
		// calculate the value of sum of square out
		double nSumOfSquareOuts = Core.sumElems(channel.mul(channel)).val[0];
		// calculate the value of sum of out
		double nSumOfOuts = Core.sumElems(channel).val[0];
		// calculate the mean value of the block image
		double fMean = nSumOfOuts / numberOfPixels;
		// calculate the cost function
		double fCost = lambda * nSumOfLoss / numberOfPixels - (nSumOfSquareOuts / numberOfPixels - fMean * fMean);
		// find the minimum cost and the related transmission
		if (nCounter == 0 || fMinCost > fCost) {
			fMinCost = fCost;
			Trans = fTrans;
		}
		fTrans = fTrans + 0.1;
		nTrans = 1.0 / fTrans * 128;
		nCounter = nCounter + 1;
	}
	return Trans;
}
 

private static Mat dehazeProcess(Mat img, Mat trans, double[] airlight) {
	Mat balancedImg = Filters.SimplestColorBalance(img, 5);
	Mat bCnl = new Mat();
	Core.extractChannel(balancedImg, bCnl, 0);
	Mat gCnl = new Mat();
	Core.extractChannel(balancedImg, gCnl, 1);
	Mat rCnl = new Mat();
	Core.extractChannel(balancedImg, rCnl, 2);
	// get mean value
	double bMean = Core.mean(bCnl).val[0];
	double gMean = Core.mean(gCnl).val[0];
	double rMean = Core.mean(rCnl).val[0];
	// get transmission map for each channel
	Mat Tb = trans.clone();
	Core.multiply(Tb, new Scalar(Math.max(bMean, Math.max(gMean, rMean)) / bMean * 0.8), Tb);
	Mat Tg = trans.clone();
	Core.multiply(Tg, new Scalar(Math.max(bMean, Math.max(gMean, rMean)) / gMean * 0.9), Tg);
	Mat Tr = trans.clone();
	Core.multiply(Tr, new Scalar(Math.max(bMean, Math.max(gMean, rMean)) / rMean * 0.8), Tr);
	// dehaze by formula
	// blue channel
	Mat bChannel = new Mat();
	Core.subtract(bCnl, new Scalar(airlight[0]), bChannel);
	Core.divide(bChannel, Tb, bChannel);
	Core.add(bChannel, new Scalar(airlight[0]), bChannel);
	// green channel
	Mat gChannel = new Mat();
	Core.subtract(gCnl, new Scalar(airlight[1]), gChannel);
	Core.divide(gChannel, Tg, gChannel);
	Core.add(gChannel, new Scalar(airlight[1]), gChannel);
	// red channel
	Mat rChannel = new Mat();
	Core.subtract(rCnl, new Scalar(airlight[2]), rChannel);
	Core.divide(rChannel, Tr, rChannel);
	Core.add(rChannel, new Scalar(airlight[2]), rChannel);
	Mat dehazed = new Mat();
	Core.merge(new ArrayList<>(Arrays.asList(bChannel, gChannel, rChannel)), dehazed);
	return dehazed;
}
 

public static List<MatOfPoint> findContoursForMRZ(Mat src){
    Mat img = src.clone();
    src.release();
    double ratio = getScaleRatio(img.size());
    int width = (int) (img.size().width / ratio);
    int height = (int) (img.size().height / ratio);
    Size newSize = new Size(width, height);
    Mat resizedImg = new Mat(newSize, CvType.CV_8UC4);
    Imgproc.resize(img, resizedImg, newSize);

    Mat gray = new Mat();
    Imgproc.cvtColor(resizedImg, gray, Imgproc.COLOR_BGR2GRAY);
    Imgproc.medianBlur(gray, gray, 3);
    //Imgproc.blur(gray, gray, new Size(3, 3));

    Mat morph = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(13, 5));
    Mat dilatedImg = new Mat();
    Imgproc.morphologyEx(gray, dilatedImg, Imgproc.MORPH_BLACKHAT, morph);
    gray.release();

    Mat gradX = new Mat();
    Imgproc.Sobel(dilatedImg, gradX, CvType.CV_32F, 1, 0);
    dilatedImg.release();
    Core.convertScaleAbs(gradX, gradX, 1, 0);
    Core.MinMaxLocResult minMax = Core.minMaxLoc(gradX);
    Core.convertScaleAbs(gradX, gradX, (255/(minMax.maxVal - minMax.minVal)),
            - ((minMax.minVal * 255) / (minMax.maxVal - minMax.minVal)));
    Imgproc.morphologyEx(gradX, gradX, Imgproc.MORPH_CLOSE, morph);

    Mat thresh = new Mat();
    Imgproc.threshold(gradX, thresh, 0, 255, Imgproc.THRESH_OTSU);
    gradX.release();
    morph.release();

    morph = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(21, 21));
    Imgproc.morphologyEx(thresh, thresh, Imgproc.MORPH_CLOSE, morph);
    Imgproc.erode(thresh, thresh, new Mat(), new Point(-1, -1), 4);
    morph.release();

    int col = (int) resizedImg.size().width;
    int p = (int) (resizedImg.size().width * 0.05);
    int row = (int) resizedImg.size().height;
    for(int i = 0; i < row; i++)
    {
        for(int j = 0; j < p; j++){
            thresh.put(i, j, 0);
            thresh.put(i, col-j, 0);
        }
    }

    List<MatOfPoint> contours = new ArrayList<>();
    Mat hierarchy = new Mat();
    Imgproc.findContours(thresh, contours, hierarchy, Imgproc.RETR_EXTERNAL, Imgproc.CHAIN_APPROX_SIMPLE);
    hierarchy.release();

    Log.d(TAG, "contours found: " + contours.size());

    Collections.sort(contours, new Comparator<MatOfPoint>() {
        @Override
        public int compare(MatOfPoint o1, MatOfPoint o2) {
            return Double.valueOf(Imgproc.contourArea(o2)).compareTo(Imgproc.contourArea(o1));
        }
    });

    return contours;
}
 

public static List<MatOfPoint> findContours(Mat src){
    Mat img = src.clone();

    //find contours
    double ratio = getScaleRatio(img.size());
    int width = (int) (img.size().width / ratio);
    int height = (int) (img.size().height / ratio);
    Size newSize = new Size(width, height);
    Mat resizedImg = new Mat(newSize, CvType.CV_8UC4);
    Imgproc.resize(img, resizedImg, newSize);
    img.release();

    Imgproc.medianBlur(resizedImg, resizedImg, 7);

    Mat cannedImg = new Mat(newSize, CvType.CV_8UC1);
    Imgproc.Canny(resizedImg, cannedImg, 70, 200, 3, true);
    resizedImg.release();

    Imgproc.threshold(cannedImg, cannedImg, 70, 255, Imgproc.THRESH_OTSU);

    Mat dilatedImg = new Mat(newSize, CvType.CV_8UC1);
    Mat morph = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(3, 3));
    Imgproc.dilate(cannedImg, dilatedImg, morph, new Point(-1, -1), 2, 1, new Scalar(1));
    cannedImg.release();
    morph.release();

    ArrayList<MatOfPoint> contours = new ArrayList<>();
    Mat hierarchy = new Mat();
    Imgproc.findContours(dilatedImg, contours, hierarchy, Imgproc.RETR_EXTERNAL, Imgproc.CHAIN_APPROX_SIMPLE);
    hierarchy.release();
    dilatedImg.release();

    Log.d(TAG, "contours found: " + contours.size());

    Collections.sort(contours, new Comparator<MatOfPoint>() {
        @Override
        public int compare(MatOfPoint o1, MatOfPoint o2) {
            return Double.valueOf(Imgproc.contourArea(o2)).compareTo(Imgproc.contourArea(o1));
        }
    });

    return contours;
}
 

public static void main(String[] args) {
	String imgPath = "images/5.jpg";
	Mat image = Imgcodecs.imread(imgPath, Imgcodecs.CV_LOAD_IMAGE_COLOR);
	new ImShow("original").showImage(image);
	// color balance
	Mat img1 = ColorBalance.SimplestColorBalance(image, 5);
	img1.convertTo(img1, CvType.CV_8UC1);
	// Perform sRGB to CIE Lab color space conversion
	Mat LabIm1 = new Mat();
	Imgproc.cvtColor(img1, LabIm1, Imgproc.COLOR_BGR2Lab);
	Mat L1 = new Mat();
	Core.extractChannel(LabIm1, L1, 0);
	// apply CLAHE
	Mat[] result = applyCLAHE(LabIm1, L1);
	Mat img2 = result[0];
	Mat L2 = result[1];
	// calculate normalized weight
	Mat w1 = calWeight(img1, L1);
	Mat w2 = calWeight(img2, L2);
	Mat sumW = new Mat();
	Core.add(w1, w2, sumW);
	Core.divide(w1, sumW, w1);
	Core.divide(w2, sumW, w2);
	// construct the gaussian pyramid for weight
	int level = 5;
	Mat[] weight1 = Pyramid.GaussianPyramid(w1, level);
	Mat[] weight2 = Pyramid.GaussianPyramid(w2, level);
	// construct the laplacian pyramid for input image channel
	img1.convertTo(img1, CvType.CV_32F);
	img2.convertTo(img2, CvType.CV_32F);
	List<Mat> bgr = new ArrayList<Mat>();
	Core.split(img1, bgr);
	Mat[] bCnl1 = Pyramid.LaplacianPyramid(bgr.get(0), level);
	Mat[] gCnl1 = Pyramid.LaplacianPyramid(bgr.get(1), level);
	Mat[] rCnl1 = Pyramid.LaplacianPyramid(bgr.get(2), level);
	bgr.clear();
	Core.split(img2, bgr);
	Mat[] bCnl2 = Pyramid.LaplacianPyramid(bgr.get(0), level);
	Mat[] gCnl2 = Pyramid.LaplacianPyramid(bgr.get(1), level);
	Mat[] rCnl2 = Pyramid.LaplacianPyramid(bgr.get(2), level);
	// fusion process
	Mat[] bCnl = new Mat[level];
	Mat[] gCnl = new Mat[level];
	Mat[] rCnl = new Mat[level];
	for (int i = 0; i < level; i++) {
		Mat cn = new Mat();
		Core.add(bCnl1[i].mul(weight1[i]), bCnl2[i].mul(weight2[i]), cn);
		bCnl[i] = cn.clone();
		Core.add(gCnl1[i].mul(weight1[i]), gCnl2[i].mul(weight2[i]), cn);
		gCnl[i] = cn.clone();
		Core.add(rCnl1[i].mul(weight1[i]), rCnl2[i].mul(weight2[i]), cn);
		rCnl[i] = cn.clone();
	}
	// reconstruct & output
	Mat bChannel = Pyramid.PyramidReconstruct(bCnl);
	Mat gChannel = Pyramid.PyramidReconstruct(gCnl);
	Mat rChannel = Pyramid.PyramidReconstruct(rCnl);
	Mat fusion = new Mat();
	Core.merge(new ArrayList<Mat>(Arrays.asList(bChannel, gChannel, rChannel)), fusion);
	fusion.convertTo(fusion, CvType.CV_8UC1);
	new ImShow("fusion").showImage(fusion);
}
 

public static Mat enhance(Mat image, double krnlRatio, double minAtmosLight, double eps) {
	image.convertTo(image, CvType.CV_32F);
	// extract each color channel
	List<Mat> rgb = new ArrayList<>();
	Core.split(image, rgb);
	Mat rChannel = rgb.get(0);
	Mat gChannel = rgb.get(1);
	Mat bChannel = rgb.get(2);
	int rows = rChannel.rows();
	int cols = rChannel.cols();
	// derive the dark channel from original image
	Mat dc = rChannel.clone();
	for (int i = 0; i < image.rows(); i++) {
		for (int j = 0; j < image.cols(); j++) {
			double min = Math.min(rChannel.get(i, j)[0], Math.min(gChannel.get(i, j)[0], bChannel.get(i, j)[0]));
			dc.put(i, j, min);
		}
	}
	// minimum filter
	int krnlSz = Double.valueOf(Math.max(Math.max(rows * krnlRatio, cols * krnlRatio), 3.0)).intValue();
	Mat kernel = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(krnlSz, krnlSz), new Point(-1, -1));
	Imgproc.erode(dc, dc, kernel);
	// get coarse transmission map
	Mat t = dc.clone();
	Core.subtract(t, new Scalar(255.0), t);
	Core.multiply(t, new Scalar(-1.0), t);
	Core.divide(t, new Scalar(255.0), t);
	// obtain gray scale image
	Mat gray = new Mat();
	Imgproc.cvtColor(image, gray, Imgproc.COLOR_RGB2GRAY);
	Core.divide(gray, new Scalar(255.0), gray);
	// refine transmission map
	int r = krnlSz * 4;
	t = Filters.GuidedImageFilter(gray, t, r, eps);
	// get minimum atmospheric light
	minAtmosLight = Math.min(minAtmosLight, Core.minMaxLoc(dc).maxVal);
	// dehaze each color channel
	rChannel = dehaze(rChannel, t, minAtmosLight);
	gChannel = dehaze(gChannel, t, minAtmosLight);
	bChannel = dehaze(bChannel, t, minAtmosLight);
	// merge three color channels to a image
	Mat outval = new Mat();
	Core.merge(new ArrayList<>(Arrays.asList(rChannel, gChannel, bChannel)), outval);
	outval.convertTo(outval, CvType.CV_8UC1);
	return outval;
}
 

/**
 * Locate rectangles in an image
 *
 * @param grayImage Grayscale image
 * @return Rectangle locations
 */
public RectangleLocationResult locateRectangles(Mat grayImage) {
    Mat gray = grayImage.clone();

    //Filter out some noise by halving then doubling size
    Filter.downsample(gray, 2);
    Filter.upsample(gray, 2);

    //Mat is short for Matrix, and here is used to store an image.
    //it is n-dimensional, but as an image, is two-dimensional
    Mat cacheHierarchy = new Mat();
    Mat grayTemp = new Mat();
    List<Rectangle> rectangles = new ArrayList<>();
    List<Contour> contours = new ArrayList<>();

    //This finds the edges using a Canny Edge Detector
    //It is sent the grayscale Image, a temp Mat, the lower detection threshold for an edge,
    //the higher detection threshold, the Aperture (blurring) of the image - higher is better
    //for long, smooth edges, and whether a more accurate version (but time-expensive) version
    //should be used (true = more accurate)
    //Note: the edges are stored in "grayTemp", which is an image where everything
    //is black except for gray-scale lines delineating the edges.
    Imgproc.Canny(gray, grayTemp, 0, THRESHOLD_CANNY, APERTURE_CANNY, true);
    //make the white lines twice as big, while leaving the image size constant
    Filter.dilate(gray, 2);

    List<MatOfPoint> contoursTemp = new ArrayList<>();
    //Find contours - the parameters here are very important to compression and retention
    //grayTemp is the image from which the contours are found,
    //contoursTemp is where the resultant contours are stored (note: color is not retained),
    //cacheHierarchy is the parent-child relationship between the contours (e.g. a contour
    //inside of another is its child),
    //Imgproc.CV_RETR_LIST disables the hierarchical relationships being returned,
    //Imgproc.CHAIN_APPROX_SIMPLE means that the contour is compressed from a massive chain of
    //paired coordinates to just the endpoints of each segment (e.g. an up-right rectangular
    //contour is encoded with 4 points.)
    Imgproc.findContours(grayTemp, contoursTemp, cacheHierarchy, Imgproc.CV_RETR_LIST, Imgproc.CHAIN_APPROX_SIMPLE);
    //MatOfPoint2f means that is a MatofPoint (Matrix of Points) represented by floats instead of ints
    MatOfPoint2f approx = new MatOfPoint2f();
    //For each contour, test whether the contour is a rectangle
    //List<Contour> contours = new ArrayList<>()
    for (MatOfPoint co : contoursTemp) {
        //converting the MatOfPoint to MatOfPoint2f
        MatOfPoint2f matOfPoint2f = new MatOfPoint2f(co.toArray());
        //converting the matrix to a Contour
        Contour c = new Contour(co);

        //Attempt to fit the contour to the best polygon
        //input: matOfPoint2f, which is the contour found earlier
        //output: approx, which is the MatOfPoint2f that holds the new polygon that has less vertices
        //basically, it smooths out the edges using the third parameter as its approximation accuracy
        //final parameter determines whether the new approximation must be closed (true=closed)
        Imgproc.approxPolyDP(matOfPoint2f, approx,
                c.arcLength(true) * EPLISON_APPROX_TOLERANCE_FACTOR, true);

        //converting the MatOfPoint2f to a contour
        Contour approxContour = new Contour(approx);

        //Make sure the contour is big enough, CLOSED (convex), and has exactly 4 points
        if (approx.toArray().length == 4 &&
                Math.abs(approxContour.area()) > 1000 &&
                approxContour.isClosed()) {

            //TODO contours and rectangles array may not match up, but why would they?
            contours.add(approxContour);

            //Check each angle to be approximately 90 degrees
            //Done by comparing the three points constituting the angle of each corner
            double maxCosine = 0;
            for (int j = 2; j < 5; j++) {
                double cosine = Math.abs(MathUtil.angle(approx.toArray()[j % 4],
                        approx.toArray()[j - 2], approx.toArray()[j - 1]));
                maxCosine = Math.max(maxCosine, cosine);
            }

            if (maxCosine < MAX_COSINE_VALUE) {
                //Convert the points to a rectangle instance
                rectangles.add(new Rectangle(approx.toArray()));
            }
        }
    }

    return new RectangleLocationResult(contours, rectangles);
}
 

/**
 * opencv自带的二值化
 * 
 * @param src
 * @return
 */
public static Mat binaryNative(Mat src) {
	Mat dst = src.clone();
	Imgproc.adaptiveThreshold(src, dst, 255, Imgproc.ADAPTIVE_THRESH_MEAN_C, Imgproc.THRESH_BINARY, 25, 10);
	return dst;
}
 

/**
 * canny算法，边缘检测
 *
 * @param src
 * @return
 */
public static Mat canny(Mat src) {
	Mat mat = src.clone();
	Imgproc.Canny(src, mat, 60, 200);
	return mat;
}