import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public BufferedImage getResolvedImage(BufferedImage src)
{
	Planar<GrayF32> input = ConvertBufferedImage.convertFromMulti(src, null, true, GrayF32.class);

	RemovePerspectiveDistortion<Planar<GrayF32>> removePerspective =
			new RemovePerspectiveDistortion<>(300, 300, ImageType.pl(3, GrayF32.class));

	if( !removePerspective.apply(input,
			new Point2D_F64(points[0].x,points[0].y),
			new Point2D_F64(points[1].x,points[1].y),
			new Point2D_F64(points[2].x,points[2].y),
			new Point2D_F64(points[3].x,points[3].y)
							) ){
		return null;
	}

	Planar<GrayF32> output = removePerspective.getOutput();
	return ConvertBufferedImage.convertTo_F32(output,null,true);
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * HSV stores color information in Hue and Saturation while intensity is in Value.  This computes a 2D histogram
 * from hue and saturation only, which makes it lighting independent.
 */
public static double[] coupledHueSat(BufferedImage image) {
    Planar<GrayF32> rgb = new Planar<>(GrayF32.class, image.getWidth(), image.getHeight(), 3);
    Planar<GrayF32> hsv = new Planar<>(GrayF32.class, image.getWidth(), image.getHeight(), 3);

    ConvertBufferedImage.convertFrom(image, rgb, true);
    ColorHsv.rgbToHsv_F32(rgb, hsv);

    Planar<GrayF32> hs = hsv.partialSpectrum(0, 1);

    // The number of bins is an important parameter.  Try adjusting it
    Histogram_F64 histogram = new Histogram_F64(10, 10);
    histogram.setRange(0, 0, 2.0 * Math.PI); // range of hue is from 0 to 2PI
    histogram.setRange(1, 0, 1.0);         // range of saturation is from 0 to 1

    // Compute the histogram
    GHistogramFeatureOps.histogram(hs, histogram);
    histogram.value[0] = 0.0; // remove black

    UtilFeature.normalizeL2(histogram); // normalize so that image size doesn't matter

    return histogram.value;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * Constructs a 3D histogram using RGB.  RGB is a popular color space, but the resulting histogram will
 * depend on lighting conditions and might not produce the accurate results.
 */
public static double[] coupledRGB(BufferedImage image) {

    Planar<GrayF32> rgb = new Planar<>(GrayF32.class,1,1,3);

    rgb.reshape(image.getWidth(), image.getHeight());
    ConvertBufferedImage.convertFrom(image, rgb, true);

    // The number of bins is an important parameter.  Try adjusting it
    Histogram_F64 histogram = new Histogram_F64(5,5,5);
    histogram.setRange(0, 0, 255);
    histogram.setRange(1, 0, 255);
    histogram.setRange(2, 0, 255);

    GHistogramFeatureOps.histogram(rgb,histogram);
    histogram.value[0] = 0.0; // remove black

    UtilFeature.normalizeL2(histogram); // normalize so that image size doesn't matter

    return histogram.value;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public static BufferedImage removeGray(BufferedImage image) {
    Planar<GrayF32> input = ConvertBufferedImage.convertFromMulti(image, null, true, GrayF32.class);
    BufferedImage output = new BufferedImage(input.width, input.height, BufferedImage.TYPE_INT_RGB);
    for (int y = 0; y < input.height; y++) {
        for (int x = 0; x < input.width; x++) {
            float v0 = input.getBand(0).get(x, y);
            float v1 = input.getBand(1).get(x, y);
            float v2 = input.getBand(2).get(x, y);
            int tol = 20;
            if (!(Math.abs(v0 - v1) < tol && Math.abs(v1 - v2) < tol && Math.abs(v0 - v2) < tol)) {
                output.setRGB(x, y, image.getRGB(x, y));
            }
        }
    }
    return output;

}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * Applies a contour-detection algorithm on the provided image and returns a list of detected contours. First, the image
 * is converted to a BinaryImage using a threshold algorithm (Otsu). Afterwards, blobs in the image are detected using
 * an 8-connect rule.
 *
 * @param image BufferedImage in which contours should be detected.
 * @return List of contours.
 */
public static List<Contour> getContours(BufferedImage image) {
    /* Draw a black frame around to image so as to make sure that all detected contours are internal contours. */
    BufferedImage resized = new BufferedImage(image.getWidth() + 4, image.getHeight() + 4, image.getType());
    Graphics g = resized.getGraphics();
    g.setColor(Color.BLACK);
    g.fillRect(0,0,resized.getWidth(),resized.getHeight());
    g.drawImage(image, 2,2, image.getWidth(), image.getHeight(), null);

    /* Convert to BufferedImage to Gray-scale image and prepare Binary image. */
    GrayF32 input = ConvertBufferedImage.convertFromSingle(resized, null, GrayF32.class);
    GrayU8 binary = new GrayU8(input.width,input.height);
    GrayS32 label = new GrayS32(input.width,input.height);

    /* Select a global threshold using Otsu's method and apply that threshold. */
    double threshold = GThresholdImageOps.computeOtsu(input, 0, 255);
    ThresholdImageOps.threshold(input, binary,(float)threshold,true);

    /* Remove small blobs through erosion and dilation;  The null in the input indicates that it should internally
     * declare the work image it needs this is less efficient, but easier to code. */
    GrayU8 filtered = BinaryImageOps.erode8(binary, 1, null);
    filtered = BinaryImageOps.dilate8(filtered, 1, null);

    /* Detect blobs inside the image using an 8-connect rule. */
    return BinaryImageOps.contour(filtered, ConnectRule.EIGHT, label);
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public static boolean[] getEdgePixels(MultiImage img, boolean[] out) {
	LOGGER.traceEntry();

	if (out == null || out.length != img.getWidth() * img.getHeight()) {
		out = new boolean[img.getWidth() * img.getHeight()];
	}

	GrayU8 gray = ConvertBufferedImage.convertFrom(img.getBufferedImage(), (GrayU8) null);

	if(!isSolid(gray)){
		getCanny().process(gray, THRESHOLD_LOW, THRESHOLD_HIGH, gray);
		
	}

	for (int i = 0; i < gray.data.length; ++i) {
		out[i] = (gray.data[i] != 0);
	}

	LOGGER.traceExit();
	return out;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
protected void processRgb(FrameMode mode, ByteBuffer frame, int timestamp) {
	if (mode.getVideoFormat() != VideoFormat.RGB) {
		System.out.println("Bad rgb format!");
	}

	if (outRgb == null) {
		rgb.reshape(mode.getWidth(), mode.getHeight());
		outRgb = new BufferedImage(rgb.width, rgb.height, BufferedImage.TYPE_INT_RGB);
		guiRgb = ShowImages.showWindow(outRgb, "RGB Image");
	}

	App.bufferRgbToMsU8(frame, rgb);
	ConvertBufferedImage.convertTo_U8(rgb, outRgb, true);

	drawButton(buttonMove, outRgb);
	drawButton(buttonStop, outRgb);
	drawButton(buttonLeft, outRgb);
	drawButton(buttonRight, outRgb);

	processButtonStatePhaseTwo(buttonMove, outRgb);
	processButtonStatePhaseTwo(buttonStop, outRgb);
	processButtonStatePhaseTwo(buttonLeft, outRgb);
	processButtonStatePhaseTwo(buttonRight, outRgb);

	guiRgb.repaint();
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * Count pills.
 *
 * @param image the image
 * @return the int
 * @throws Exception the exception
 */
public static int countPills( BufferedImage image ) throws Exception {
	GrayF32 input = ConvertBufferedImage.convertFromSingle(image, null, GrayF32.class);
	GrayU8 binary = new GrayU8(input.width,input.height);
	int totPixels = 0;
	for( int x = 0 ; x<input.width ; x++ ) {
		for( int y=0 ; y<input.height ; y++ ) {
			int binout = input.get(x, y) < PIXEL_THRESHOLD ? 0 : 1;
			binary.set(x, y, binout );
			totPixels += binout;
		}
	}
	dumpImage(binary, input.width, input.height );
	
	int numPills = -1;
	for( int checkNumPills=1 ; checkNumPills<CHECK_MAX_NUM_PILLS ; checkNumPills++ ) {
		int checkMaxPixels = (int)(checkNumPills * PIXELS_PER_PILL * PIXELS_PER_PILL_FUDGE_FACTOR);
		if( totPixels <= checkMaxPixels ) {
			numPills = checkNumPills;
			break;
		}
	}
	logger.info("NumPills found in image: {}", numPills);
	return numPills;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
protected void processRgb(FrameMode mode, ByteBuffer frame, int timestamp) {
  if (mode.getVideoFormat() != VideoFormat.RGB) {
    System.out.println("Bad rgb format!");
  }

  System.out.println("Got rgb!   " + timestamp);

  if (outRgb == null) {
    rgb.reshape(mode.getWidth(), mode.getHeight());
    outRgb = new BufferedImage(rgb.width, rgb.height, BufferedImage.TYPE_INT_RGB);
    guiRgb = ShowImages.showWindow(outRgb, "RGB Image");
  }

  UtilOpenKinect.bufferRgbToMsU8(frame, rgb);
  ConvertBufferedImage.convertTo_U8(rgb, outRgb, true);

  guiRgb.repaint();
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public static List<Contour> getCannyContours(BufferedImage image) {
	GrayU8 gray = ConvertBufferedImage.convertFrom(image, (GrayU8) null);
	GrayU8 edgeImage = gray.createSameShape();
	canny.process(gray, 0.1f, 0.3f, edgeImage);
	List<Contour> contours = BinaryImageOps.contour(edgeImage, ConnectRule.EIGHT, null);

	return contours;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public ImageDesc(BufferedImage in)
{
	if(!AverageHash.isInitiated())
	{
		AverageHash.init(2, 2);
	}
	hash = AverageHash.avgHash(in,2,2);
	GrayF32 img = ConvertBufferedImage.convertFromSingle(in, null, GrayF32.class);
	desc.reset();
	describeImage(img,desc);
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * Computes two independent 1D histograms from hue and saturation.  Less affects by sparsity, but can produce
 * worse results since the basic assumption that hue and saturation are decoupled is most of the time false.
 */
public static double[] independentHueSat(BufferedImage image) {
    // The number of bins is an important parameter.  Try adjusting it
    TupleDesc_F64 histogramHue = new TupleDesc_F64(5);
    TupleDesc_F64 histogramValue = new TupleDesc_F64(5);

    List<TupleDesc_F64> histogramList = new ArrayList<>();
    histogramList.add(histogramHue); histogramList.add(histogramValue);

    Planar<GrayF32> rgb = new Planar<>(GrayF32.class,1,1,3);
    Planar<GrayF32> hsv = new Planar<>(GrayF32.class,1,1,3);

    rgb.reshape(image.getWidth(), image.getHeight());
    hsv.reshape(image.getWidth(), image.getHeight());
    ConvertBufferedImage.convertFrom(image, rgb, true);
    ColorHsv.rgbToHsv_F32(rgb, hsv);

    GHistogramFeatureOps.histogram(hsv.getBand(0), 0, 2*Math.PI,histogramHue);
    GHistogramFeatureOps.histogram(hsv.getBand(1), 0, 1, histogramValue);

    // need to combine them into a single descriptor for processing later on
    TupleDesc_F64 imageHist = UtilFeature.combine(histogramList,null);

    UtilFeature.normalizeL2(imageHist); // normalize so that image size doesn't matter

    return imageHist.value;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public static BufferedImage filterBackgroundOut(BufferedImage image) {

        Planar<GrayF32> input = ConvertBufferedImage.convertFromMulti(image, null, true, GrayF32.class);
        Planar<GrayF32> hsv = new Planar<>(GrayF32.class, input.getWidth(), input.getHeight(), 3);

        // Convert into HSV
        ColorHsv.rgbToHsv_F32(input, hsv);

        // Euclidean distance squared threshold for deciding which pixels are members of the selected set
        float maxDist2 = 0.4f * 0.4f;

        // Extract hue and saturation bands which are independent of intensity
        GrayF32 H = hsv.getBand(0);
        GrayF32 S = hsv.getBand(1);

        float hue = H.get(1, 1);
        float saturation = S.get(1, 1);

        // Adjust the relative importance of Hue and Saturation.
        // Hue has a range of 0 to 2*PI and Saturation from 0 to 1.
        float adjustUnits = (float) (Math.PI / 2.0);

        // step through each pixel and mark how close it is to the selected color
        BufferedImage output = new BufferedImage(input.width, input.height, BufferedImage.TYPE_INT_RGB);
        for (int y = 0; y < hsv.height; y++) {
            for (int x = 0; x < hsv.width; x++) {
                // Hue is an angle in radians, so simple subtraction doesn't work
                float dh = UtilAngle.dist(H.unsafe_get(x, y), hue);
                float ds = (S.unsafe_get(x, y) - saturation) * adjustUnits;

                // this distance measure is a bit naive, but good enough for to demonstrate the concept
                float dist2 = dh * dh + ds * ds;
                if (dist2 > maxDist2 * 4) {
                    output.setRGB(x, y, image.getRGB(x, y));
                }
            }
        }
        return output;
    }
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public static BufferedImage maskBackground(BufferedImage image) {
    GrayU8 gray = ConvertBufferedImage.convertFromSingle(image, null, GrayU8.class);
    int threshold = gray.get(1, 1); // get background pixel - would be better to average some
    GrayU8 binary = ThresholdImageOps.threshold(gray, null, threshold, true);
    GrayF32 mask = ConvertImage.convert(binary, (GrayF32) null);
    return mask(image, mask);
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
private void run() throws IOException {
    BufferedImage image = UtilImageIO.loadImage(UtilIO.pathExample("C:\\development\\readySET\\deck\\1221.png"));

    GrayU8 gray = ConvertBufferedImage.convertFrom(image,(GrayU8)null);
    GrayU8 edgeImage = gray.createSameShape();

    // Create a canny edge detector which will dynamically compute the threshold based on maximum edge intensity
    // It has also been configured to save the trace as a graph.  This is the graph created while performing
    // hysteresis thresholding.
    CannyEdge<GrayU8,GrayS16> canny = FactoryEdgeDetectors.canny(2,true, true, GrayU8.class, GrayS16.class);

    // The edge image is actually an optional parameter.  If you don't need it just pass in null
    canny.process(gray,0.1f,0.3f,edgeImage);

    // First get the contour created by canny
    List<EdgeContour> edgeContours = canny.getContours();
    // The 'edgeContours' is a tree graph that can be difficult to process.  An alternative is to extract
    // the contours from the binary image, which will produce a single loop for each connected cluster of pixels.
    // Note that you are only interested in verticesnal contours.
    List<Contour> contours = BinaryImageOps.contour(edgeImage, ConnectRule.EIGHT, null);

    // display the results
    BufferedImage visualBinary = VisualizeBinaryData.renderBinary(edgeImage, false, null);
    BufferedImage visualCannyContour = VisualizeBinaryData.renderContours(edgeContours,null,
            gray.width,gray.height,null);
    BufferedImage visualEdgeContour = new BufferedImage(gray.width, gray.height,BufferedImage.TYPE_INT_RGB);
    VisualizeBinaryData.render(contours, (int[]) null, visualEdgeContour);

    ListDisplayPanel panel = new ListDisplayPanel();
    panel.addImage(visualBinary,"Binary Edges from Canny");
    panel.addImage(visualCannyContour, "Canny Trace Graph");
    panel.addImage(visualEdgeContour,"Contour from Canny Binary");
    ShowImages.showWindow(panel,"Canny Edge", true);
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
static BufferedImage generateBlackWhiteImage(String path, boolean save) throws IOException {
    BufferedImage in = ImageIO.read(new File(path));

    // convert into a usable format
    GrayF32 input = ConvertBufferedImage.convertFromSingle(in, null, GrayF32.class);
    GrayU8 binary = new GrayU8(input.width, input.height);
    GrayS32 label = new GrayS32(input.width, input.height);

    // Select a global threshold using Otsu's method.
    double threshold = GThresholdImageOps.computeOtsu(input, 0, 255);

    // Apply the threshold to create a binary image
    ThresholdImageOps.threshold(input, binary, (float) threshold, true);

    // remove small blobs through erosion and dilation
    // The null in the input indicates that it should internally declare the work image it needs
    // this is less efficient, but easier to code.
    GrayU8 filtered = BinaryImageOps.erode8(binary, 1, null);
    filtered = BinaryImageOps.dilate8(filtered, 1, null);

    // Detect blobs inside the image using an 8-connect rule
    List<Contour> contours = BinaryImageOps.contour(filtered, ConnectRule.EIGHT, label);

    // display the results
    BufferedImage visualBinary = VisualizeBinaryData.renderBinary(binary, false, null);


    if (save) { // Save the image, if necessary
        File outputfile = new File("saved.png");
        ImageIO.write(visualBinary, "png", outputfile);
    }

    System.out.println("Done with part 1!");

    return visualBinary;

}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
protected static float[] process(MultiImage img, float[] hist) {
  GrayU8 gray = ConvertBufferedImage.convertFrom(img.getBufferedImage(), (GrayU8) null);
  int width = img.getWidth(), height = img.getHeight();
  for (int x = 0; x < 4; ++x) {
    for (int y = 0; y < 4; ++y) {
      GrayU8 subImage = gray
          .subimage(width * x / 4, height * y / 4, width * (x + 1) / 4, height * (y + 1) / 4,
              null);
      int count = 0;
      int[] tmp = new int[5];
      for (int xx = 0; xx < subImage.getWidth() - 1; xx += 2) {
        for (int yy = 0; yy < subImage.getHeight() - 1; yy += 2) {
          count++;
          int index = edgeType(
              subImage.unsafe_get(xx, yy),
              subImage.unsafe_get(xx + 1, yy),
              subImage.unsafe_get(xx, yy + 1),
              subImage.unsafe_get(xx + 1, yy + 1)
          );
          if (index > -1) {
            tmp[index]++;
          }
        }
      }
      int offset = (4 * x + y) * 5;
      for (int i = 0; i < 5; ++i) {
        hist[offset + i] += ((float) tmp[i]) / (float) count;
      }
    }
  }
  return hist;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * Returns SURF descriptors for an image using the settings above. Uses the BoofCV stable SURF algorithm.
 *
 * @param image Image for which to obtain the SURF descriptors.
 * @return
 */
public static DetectDescribePoint<GrayF32, BrightFeature> getStableSurf(BufferedImage image) {
     /* Obtain raw SURF descriptors using the configuration above (FH-9 according to [1]). */
    GrayF32 gray = ConvertBufferedImage.convertFromSingle(image, null, GrayF32.class);
    ConfigFastHessian config = new ConfigFastHessian(0, 2, FH_MAX_FEATURES_PER_SCALE, FH_INITIAL_SAMPLE_SIZE, FH_INITIAL_SIZE, FH_NUMBER_SCALES_PER_OCTAVE, FH_NUMBER_OF_OCTAVES);
    DetectDescribePoint<GrayF32, BrightFeature> surf = FactoryDetectDescribe.surfStable(config, null, null, GrayF32.class);
    surf.detect(gray);
    return surf;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
/**
 * Returns SURF descriptors for an image using the settings above. Uses the BoofCV fast SURF algorithm,
 * which yields less images but operates a bit faster.
 *
 * @param image Image for which to obtain the SURF descriptors.
 * @return
 */
public static DetectDescribePoint<GrayF32, BrightFeature> getFastSurf(BufferedImage image) {
     /* Obtain raw SURF descriptors using the configuration above (FH-9 according to [1]). */
    GrayF32 gray = ConvertBufferedImage.convertFromSingle(image, null, GrayF32.class);
    ConfigFastHessian config = new ConfigFastHessian(0, 2, FH_MAX_FEATURES_PER_SCALE, FH_INITIAL_SAMPLE_SIZE, FH_INITIAL_SIZE, FH_NUMBER_SCALES_PER_OCTAVE, FH_NUMBER_OF_OCTAVES);
    DetectDescribePoint<GrayF32, BrightFeature> surf = FactoryDetectDescribe.surfFast(config, null, null, GrayF32.class);
    surf.detect(gray);
    return surf;
}
 

import boofcv.io.image.ConvertBufferedImage; //导入依赖的package包/类
public static MultiImage getEdgeImg(MultiImage img) {
	LOGGER.traceEntry();

	GrayU8 gray = ConvertBufferedImage.convertFrom(img.getBufferedImage(), (GrayU8) null);
	if(!isSolid(gray)){
		getCanny().process(gray, THRESHOLD_LOW, THRESHOLD_HIGH, gray);
	}

	BufferedImage bout = VisualizeBinaryData.renderBinary(gray, false, null);

	return LOGGER.traceExit(MultiImageFactory.newMultiImage(bout));
}