[英]Canny Edge Detection using Processing
我正在尋找處理語言中 Canny Edge Detection 的復制粘貼實現。 盡管我對 java 非常了解,但我對圖像處理的想法為零,對處理的線索也很少。
一些加工專家可以告訴我是否有辦法在加工中實現這個http://www.tomgibara.com/computer-vision/CannyEdgeDetector.java ?
我認為如果你從Java
的角度來處理processing
,那么一些問題可以很容易地解決。 這意味着您可以使用 Java 類。
對於演示,我正在使用您共享的實現。
>>原圖
>>更改圖像
>>代碼
import java.awt.image.BufferedImage;
import java.util.Arrays;
PImage orig;
PImage changed;
void setup() {
orig = loadImage("c:/temp/image.png");
size(250, 166);
CannyEdgeDetector detector = new CannyEdgeDetector();
detector.setLowThreshold(0.5f);
detector.setHighThreshold(1f);
detector.setSourceImage((java.awt.image.BufferedImage)orig.getImage());
detector.process();
BufferedImage edges = detector.getEdgesImage();
changed = new PImage(edges);
noLoop();
}
void draw()
{
//image(orig, 0,0, width, height);
image(changed, 0,0, width, height);
}
// The code below is taken from "http://www.tomgibara.com/computer-vision/CannyEdgeDetector.java"
// I have stripped the comments for conciseness
public class CannyEdgeDetector {
// statics
private final static float GAUSSIAN_CUT_OFF = 0.005f;
private final static float MAGNITUDE_SCALE = 100F;
private final static float MAGNITUDE_LIMIT = 1000F;
private final static int MAGNITUDE_MAX = (int) (MAGNITUDE_SCALE * MAGNITUDE_LIMIT);
// fields
private int height;
private int width;
private int picsize;
private int[] data;
private int[] magnitude;
private BufferedImage sourceImage;
private BufferedImage edgesImage;
private float gaussianKernelRadius;
private float lowThreshold;
private float highThreshold;
private int gaussianKernelWidth;
private boolean contrastNormalized;
private float[] xConv;
private float[] yConv;
private float[] xGradient;
private float[] yGradient;
// constructors
/**
* Constructs a new detector with default parameters.
*/
public CannyEdgeDetector() {
lowThreshold = 2.5f;
highThreshold = 7.5f;
gaussianKernelRadius = 2f;
gaussianKernelWidth = 16;
contrastNormalized = false;
}
public BufferedImage getSourceImage() {
return sourceImage;
}
public void setSourceImage(BufferedImage image) {
sourceImage = image;
}
public BufferedImage getEdgesImage() {
return edgesImage;
}
public void setEdgesImage(BufferedImage edgesImage) {
this.edgesImage = edgesImage;
}
public float getLowThreshold() {
return lowThreshold;
}
public void setLowThreshold(float threshold) {
if (threshold < 0) throw new IllegalArgumentException();
lowThreshold = threshold;
}
public float getHighThreshold() {
return highThreshold;
}
public void setHighThreshold(float threshold) {
if (threshold < 0) throw new IllegalArgumentException();
highThreshold = threshold;
}
public int getGaussianKernelWidth() {
return gaussianKernelWidth;
}
public void setGaussianKernelWidth(int gaussianKernelWidth) {
if (gaussianKernelWidth < 2) throw new IllegalArgumentException();
this.gaussianKernelWidth = gaussianKernelWidth;
}
public float getGaussianKernelRadius() {
return gaussianKernelRadius;
}
public void setGaussianKernelRadius(float gaussianKernelRadius) {
if (gaussianKernelRadius < 0.1f) throw new IllegalArgumentException();
this.gaussianKernelRadius = gaussianKernelRadius;
}
public boolean isContrastNormalized() {
return contrastNormalized;
}
public void setContrastNormalized(boolean contrastNormalized) {
this.contrastNormalized = contrastNormalized;
}
// methods
public void process() {
width = sourceImage.getWidth();
height = sourceImage.getHeight();
picsize = width * height;
initArrays();
readLuminance();
if (contrastNormalized) normalizeContrast();
computeGradients(gaussianKernelRadius, gaussianKernelWidth);
int low = Math.round(lowThreshold * MAGNITUDE_SCALE);
int high = Math.round( highThreshold * MAGNITUDE_SCALE);
performHysteresis(low, high);
thresholdEdges();
writeEdges(data);
}
// private utility methods
private void initArrays() {
if (data == null || picsize != data.length) {
data = new int[picsize];
magnitude = new int[picsize];
xConv = new float[picsize];
yConv = new float[picsize];
xGradient = new float[picsize];
yGradient = new float[picsize];
}
}
private void computeGradients(float kernelRadius, int kernelWidth) {
//generate the gaussian convolution masks
float kernel[] = new float[kernelWidth];
float diffKernel[] = new float[kernelWidth];
int kwidth;
for (kwidth = 0; kwidth < kernelWidth; kwidth++) {
float g1 = gaussian(kwidth, kernelRadius);
if (g1 <= GAUSSIAN_CUT_OFF && kwidth >= 2) break;
float g2 = gaussian(kwidth - 0.5f, kernelRadius);
float g3 = gaussian(kwidth + 0.5f, kernelRadius);
kernel[kwidth] = (g1 + g2 + g3) / 3f / (2f * (float) Math.PI * kernelRadius * kernelRadius);
diffKernel[kwidth] = g3 - g2;
}
int initX = kwidth - 1;
int maxX = width - (kwidth - 1);
int initY = width * (kwidth - 1);
int maxY = width * (height - (kwidth - 1));
//perform convolution in x and y directions
for (int x = initX; x < maxX; x++) {
for (int y = initY; y < maxY; y += width) {
int index = x + y;
float sumX = data[index] * kernel[0];
float sumY = sumX;
int xOffset = 1;
int yOffset = width;
for(; xOffset < kwidth ;) {
sumY += kernel[xOffset] * (data[index - yOffset] + data[index + yOffset]);
sumX += kernel[xOffset] * (data[index - xOffset] + data[index + xOffset]);
yOffset += width;
xOffset++;
}
yConv[index] = sumY;
xConv[index] = sumX;
}
}
for (int x = initX; x < maxX; x++) {
for (int y = initY; y < maxY; y += width) {
float sum = 0f;
int index = x + y;
for (int i = 1; i < kwidth; i++)
sum += diffKernel[i] * (yConv[index - i] - yConv[index + i]);
xGradient[index] = sum;
}
}
for (int x = kwidth; x < width - kwidth; x++) {
for (int y = initY; y < maxY; y += width) {
float sum = 0.0f;
int index = x + y;
int yOffset = width;
for (int i = 1; i < kwidth; i++) {
sum += diffKernel[i] * (xConv[index - yOffset] - xConv[index + yOffset]);
yOffset += width;
}
yGradient[index] = sum;
}
}
initX = kwidth;
maxX = width - kwidth;
initY = width * kwidth;
maxY = width * (height - kwidth);
for (int x = initX; x < maxX; x++) {
for (int y = initY; y < maxY; y += width) {
int index = x + y;
int indexN = index - width;
int indexS = index + width;
int indexW = index - 1;
int indexE = index + 1;
int indexNW = indexN - 1;
int indexNE = indexN + 1;
int indexSW = indexS - 1;
int indexSE = indexS + 1;
float xGrad = xGradient[index];
float yGrad = yGradient[index];
float gradMag = hypot(xGrad, yGrad);
//perform non-maximal supression
float nMag = hypot(xGradient[indexN], yGradient[indexN]);
float sMag = hypot(xGradient[indexS], yGradient[indexS]);
float wMag = hypot(xGradient[indexW], yGradient[indexW]);
float eMag = hypot(xGradient[indexE], yGradient[indexE]);
float neMag = hypot(xGradient[indexNE], yGradient[indexNE]);
float seMag = hypot(xGradient[indexSE], yGradient[indexSE]);
float swMag = hypot(xGradient[indexSW], yGradient[indexSW]);
float nwMag = hypot(xGradient[indexNW], yGradient[indexNW]);
float tmp;
if (xGrad * yGrad <= (float) 0 /*(1)*/
? Math.abs(xGrad) >= Math.abs(yGrad) /*(2)*/
? (tmp = Math.abs(xGrad * gradMag)) >= Math.abs(yGrad * neMag - (xGrad + yGrad) * eMag) /*(3)*/
&& tmp > Math.abs(yGrad * swMag - (xGrad + yGrad) * wMag) /*(4)*/
: (tmp = Math.abs(yGrad * gradMag)) >= Math.abs(xGrad * neMag - (yGrad + xGrad) * nMag) /*(3)*/
&& tmp > Math.abs(xGrad * swMag - (yGrad + xGrad) * sMag) /*(4)*/
: Math.abs(xGrad) >= Math.abs(yGrad) /*(2)*/
? (tmp = Math.abs(xGrad * gradMag)) >= Math.abs(yGrad * seMag + (xGrad - yGrad) * eMag) /*(3)*/
&& tmp > Math.abs(yGrad * nwMag + (xGrad - yGrad) * wMag) /*(4)*/
: (tmp = Math.abs(yGrad * gradMag)) >= Math.abs(xGrad * seMag + (yGrad - xGrad) * sMag) /*(3)*/
&& tmp > Math.abs(xGrad * nwMag + (yGrad - xGrad) * nMag) /*(4)*/
) {
magnitude[index] = gradMag >= MAGNITUDE_LIMIT ? MAGNITUDE_MAX : (int) (MAGNITUDE_SCALE * gradMag);
//NOTE: The orientation of the edge is not employed by this
//implementation. It is a simple matter to compute it at
//this point as: Math.atan2(yGrad, xGrad);
} else {
magnitude[index] = 0;
}
}
}
}
private float hypot(float x, float y) {
return (float) Math.hypot(x, y);
}
private float gaussian(float x, float sigma) {
return (float) Math.exp(-(x * x) / (2f * sigma * sigma));
}
private void performHysteresis(int low, int high) {
Arrays.fill(data, 0);
int offset = 0;
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
if (data[offset] == 0 && magnitude[offset] >= high) {
follow(x, y, offset, low);
}
offset++;
}
}
}
private void follow(int x1, int y1, int i1, int threshold) {
int x0 = x1 == 0 ? x1 : x1 - 1;
int x2 = x1 == width - 1 ? x1 : x1 + 1;
int y0 = y1 == 0 ? y1 : y1 - 1;
int y2 = y1 == height -1 ? y1 : y1 + 1;
data[i1] = magnitude[i1];
for (int x = x0; x <= x2; x++) {
for (int y = y0; y <= y2; y++) {
int i2 = x + y * width;
if ((y != y1 || x != x1)
&& data[i2] == 0
&& magnitude[i2] >= threshold) {
follow(x, y, i2, threshold);
return;
}
}
}
}
private void thresholdEdges() {
for (int i = 0; i < picsize; i++) {
data[i] = data[i] > 0 ? -1 : 0xff000000;
}
}
private int luminance(float r, float g, float b) {
return Math.round(0.299f * r + 0.587f * g + 0.114f * b);
}
private void readLuminance() {
int type = sourceImage.getType();
if (type == BufferedImage.TYPE_INT_RGB || type == BufferedImage.TYPE_INT_ARGB) {
int[] pixels = (int[]) sourceImage.getData().getDataElements(0, 0, width, height, null);
for (int i = 0; i < picsize; i++) {
int p = pixels[i];
int r = (p & 0xff0000) >> 16;
int g = (p & 0xff00) >> 8;
int b = p & 0xff;
data[i] = luminance(r, g, b);
}
} else if (type == BufferedImage.TYPE_BYTE_GRAY) {
byte[] pixels = (byte[]) sourceImage.getData().getDataElements(0, 0, width, height, null);
for (int i = 0; i < picsize; i++) {
data[i] = (pixels[i] & 0xff);
}
} else if (type == BufferedImage.TYPE_USHORT_GRAY) {
short[] pixels = (short[]) sourceImage.getData().getDataElements(0, 0, width, height, null);
for (int i = 0; i < picsize; i++) {
data[i] = (pixels[i] & 0xffff) / 256;
}
} else if (type == BufferedImage.TYPE_3BYTE_BGR) {
byte[] pixels = (byte[]) sourceImage.getData().getDataElements(0, 0, width, height, null);
int offset = 0;
for (int i = 0; i < picsize; i++) {
int b = pixels[offset++] & 0xff;
int g = pixels[offset++] & 0xff;
int r = pixels[offset++] & 0xff;
data[i] = luminance(r, g, b);
}
} else {
throw new IllegalArgumentException("Unsupported image type: " + type);
}
}
private void normalizeContrast() {
int[] histogram = new int[256];
for (int i = 0; i < data.length; i++) {
histogram[data[i]]++;
}
int[] remap = new int[256];
int sum = 0;
int j = 0;
for (int i = 0; i < histogram.length; i++) {
sum += histogram[i];
int target = sum*255/picsize;
for (int k = j+1; k <=target; k++) {
remap[k] = i;
}
j = target;
}
for (int i = 0; i < data.length; i++) {
data[i] = remap[data[i]];
}
}
private void writeEdges(int pixels[]) {
if (edgesImage == null) {
edgesImage = new BufferedImage(width, height, BufferedImage.TYPE_INT_ARGB);
}
edgesImage.getWritableTile(0, 0).setDataElements(0, 0, width, height, pixels);
}
}
我在 Gibara Canny 的實現上花了一些時間,我傾向於同意上面 Settembrini 的評論; 更進一步,需要更改高斯 Kernel 代的實現。
Gibara Canny 使用:
(g1 + g2 + g3) / 3f / (2f * (float) Math.PI * kernelRadius * kernelRadius)
(g1 + g2 + g3) / 3f
中的一個像素(+-0.5 像素)的平均值很好,但是單維方程下半部分的正確方差計算是:
(g1 + g2 + g3) / 3f / (Math.sqrt(2f * (float) Math.PI) * kernelRadius)
標准偏差kernelRadius
是以下等式中的 sigma:單向高斯
我假設 Gibara 正在嘗試從以下等式實現二維高斯:二維高斯,其中卷積是每個高斯的直接乘積。 雖然這可能是可能的並且更簡潔,但以下代碼將使用上述方差計算正確地在兩個方向上進行卷積:
// First Convolution
for (int x = initX; x < maxX; x++) {
for (int y = initY; y < maxY; y += sourceImage.width) {
int index = x + y;
float sumX = data[index] * kernel[0];
int xOffset = 1;
int yOffset = sourceImage.width;
for(; xOffset < k ;) {;
sumX += kernel[xOffset] * (data[index - xOffset] + data[index + xOffset]);
yOffset += sourceImage.width;
xOffset++;
}
xConv[index] = sumX;
}
}
// Second Convolution
for (int x = initX; x < maxX; x++) {
for (int y = initY; y < maxY; y += sourceImage.width) {
int index = x + y;
float sumY = xConv[index] * kernel[0];
int xOffset = 1;
int yOffset = sourceImage.width;
for(; xOffset < k ;) {;
sumY += xConv[xOffset] * (xConv[index - xOffset] + xConv[index + xOffset]);
yOffset += sourceImage.width;
xOffset++;
}
yConv[index] = sumY;
}
}
注意yConv[]
現在是雙向卷積,所以下面的 Sobel 梯度計算如下:
for (int x = initX; x < maxX; x++) {
for (int y = initY; y < maxY; y += sourceImage.width) {
float sum = 0f;
int index = x + y;
for (int i = 1; i < k; i++)
sum += diffKernel[i] * (yConv[index - i] - yConv[index + i]);
xGradient[index] = sum;
}
}
for (int x = k; x < sourceImage.width - k; x++) {
for (int y = initY; y < maxY; y += sourceImage.width) {
float sum = 0.0f;
int index = x + y;
int yOffset = sourceImage.width;
for (int i = 1; i < k; i++) {
sum += diffKernel[i] * (yConv[index - yOffset] - yConv[index + yOffset]);
yOffset += sourceImage.width;
}
yGradient[index] = sum;
}
}
Gibara 非常簡潔的非極大值抑制實現要求單獨計算這些梯度,但是如果你想 output 具有這些梯度的圖像,可以使用歐幾里得或曼哈頓距離對它們求和,歐幾里得看起來像這樣:
// Calculate the Euclidean distance between x & y gradients prior to suppression
int [] gradients = new int [picsize];
for (int i = 0; i < xGradient.length; i++) {
gradients[i] = Math.sqrt(Math.sq(xGradient[i]) + Math.sq(yGradient[i]));
}
希望這會有所幫助,一切正常,並為我的代碼道歉! 歡迎批評
除了 Favonius 的回答之外,您可能還想嘗試Greg 的 OpenCV Processing 庫,您現在可以通過Sketch > Import Library... > Add Library...輕松安裝該庫...
安裝庫后,您可以使用FindEdges 示例:
import gab.opencv.*;
OpenCV opencv;
PImage src, canny, scharr, sobel;
void setup() {
src = loadImage("test.jpg");
size(src.width, src.height);
opencv = new OpenCV(this, src);
opencv.findCannyEdges(20,75);
canny = opencv.getSnapshot();
opencv.loadImage(src);
opencv.findScharrEdges(OpenCV.HORIZONTAL);
scharr = opencv.getSnapshot();
opencv.loadImage(src);
opencv.findSobelEdges(1,0);
sobel = opencv.getSnapshot();
}
void draw() {
pushMatrix();
scale(0.5);
image(src, 0, 0);
image(canny, src.width, 0);
image(scharr, 0, src.height);
image(sobel, src.width, src.height);
popMatrix();
text("Source", 10, 25);
text("Canny", src.width/2 + 10, 25);
text("Scharr", 10, src.height/2 + 25);
text("Sobel", src.width/2 + 10, src.height/2 + 25);
}
正如我旁注一樣。 前段時間研究了 Gibara Canny 的實現,發現了一些缺陷。 例如,他在 x 和 y 方向上分離一維濾波器中的高斯濾波(這樣可以且有效),但隨后他沒有應用這些濾波器的兩次通過(一個接一個),而只是將 SobelX 應用於 x- first-pass-Gauss 和 SobelY 到 y-first-pass-Gauss,這當然會導致低質量梯度。 因此,僅通過復制此類代碼時要小心。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.