OpenCV  
Open Source Computer Vision
All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Properties Friends Macros Modules Pages
Image Segmentation with Distance Transform and Watershed Algorithm

Goal

In this tutorial you will learn how to:

Theory

Code

This tutorial code's is shown lines below. You can also download it from here.

#include <opencv2/core.hpp>
#include <iostream>
using namespace std;
using namespace cv;
int main(int argc, char *argv[])
{
// Load the image
CommandLineParser parser( argc, argv, "{@input | ../data/cards.png | input image}" );
Mat src = imread( parser.get<String>( "@input" ) );
if( src.empty() )
{
cout << "Could not open or find the image!\n" << endl;
cout << "Usage: " << argv[0] << " <Input image>" << endl;
return -1;
}
// Show source image
imshow("Source Image", src);
// Change the background from white to black, since that will help later to extract
// better results during the use of Distance Transform
for ( int i = 0; i < src.rows; i++ ) {
for ( int j = 0; j < src.cols; j++ ) {
if ( src.at<Vec3b>(i, j) == Vec3b(255,255,255) )
{
src.at<Vec3b>(i, j)[0] = 0;
src.at<Vec3b>(i, j)[1] = 0;
src.at<Vec3b>(i, j)[2] = 0;
}
}
}
// Show output image
imshow("Black Background Image", src);
// Create a kernel that we will use to sharpen our image
Mat kernel = (Mat_<float>(3,3) <<
1, 1, 1,
1, -8, 1,
1, 1, 1); // an approximation of second derivative, a quite strong kernel
// do the laplacian filtering as it is
// well, we need to convert everything in something more deeper then CV_8U
// because the kernel has some negative values,
// and we can expect in general to have a Laplacian image with negative values
// BUT a 8bits unsigned int (the one we are working with) can contain values from 0 to 255
// so the possible negative number will be truncated
Mat imgLaplacian;
filter2D(src, imgLaplacian, CV_32F, kernel);
Mat sharp;
src.convertTo(sharp, CV_32F);
Mat imgResult = sharp - imgLaplacian;
// convert back to 8bits gray scale
imgResult.convertTo(imgResult, CV_8UC3);
imgLaplacian.convertTo(imgLaplacian, CV_8UC3);
// imshow( "Laplace Filtered Image", imgLaplacian );
imshow( "New Sharped Image", imgResult );
// Create binary image from source image
Mat bw;
cvtColor(imgResult, bw, COLOR_BGR2GRAY);
threshold(bw, bw, 40, 255, THRESH_BINARY | THRESH_OTSU);
imshow("Binary Image", bw);
// Perform the distance transform algorithm
Mat dist;
distanceTransform(bw, dist, DIST_L2, 3);
// Normalize the distance image for range = {0.0, 1.0}
// so we can visualize and threshold it
normalize(dist, dist, 0, 1.0, NORM_MINMAX);
imshow("Distance Transform Image", dist);
// Threshold to obtain the peaks
// This will be the markers for the foreground objects
threshold(dist, dist, 0.4, 1.0, THRESH_BINARY);
// Dilate a bit the dist image
Mat kernel1 = Mat::ones(3, 3, CV_8U);
dilate(dist, dist, kernel1);
imshow("Peaks", dist);
// Create the CV_8U version of the distance image
// It is needed for findContours()
Mat dist_8u;
dist.convertTo(dist_8u, CV_8U);
// Find total markers
vector<vector<Point> > contours;
// Create the marker image for the watershed algorithm
Mat markers = Mat::zeros(dist.size(), CV_32S);
// Draw the foreground markers
for (size_t i = 0; i < contours.size(); i++)
{
drawContours(markers, contours, static_cast<int>(i), Scalar(static_cast<int>(i)+1), -1);
}
// Draw the background marker
circle(markers, Point(5,5), 3, Scalar(255), -1);
imshow("Markers", markers*10000);
// Perform the watershed algorithm
watershed(imgResult, markers);
Mat mark;
markers.convertTo(mark, CV_8U);
bitwise_not(mark, mark);
// imshow("Markers_v2", mark); // uncomment this if you want to see how the mark
// image looks like at that point
// Generate random colors
vector<Vec3b> colors;
for (size_t i = 0; i < contours.size(); i++)
{
int b = theRNG().uniform(0, 256);
int g = theRNG().uniform(0, 256);
int r = theRNG().uniform(0, 256);
colors.push_back(Vec3b((uchar)b, (uchar)g, (uchar)r));
}
// Create the result image
Mat dst = Mat::zeros(markers.size(), CV_8UC3);
// Fill labeled objects with random colors
for (int i = 0; i < markers.rows; i++)
{
for (int j = 0; j < markers.cols; j++)
{
int index = markers.at<int>(i,j);
if (index > 0 && index <= static_cast<int>(contours.size()))
{
dst.at<Vec3b>(i,j) = colors[index-1];
}
}
}
// Visualize the final image
imshow("Final Result", dst);
return 0;
}

Explanation / Result

// Load the image
CommandLineParser parser( argc, argv, "{@input | ../data/cards.png | input image}" );
Mat src = imread( parser.get<String>( "@input" ) );
if( src.empty() )
{
cout << "Could not open or find the image!\n" << endl;
cout << "Usage: " << argv[0] << " <Input image>" << endl;
return -1;
}
// Show source image
imshow("Source Image", src);
source.jpeg
// Change the background from white to black, since that will help later to extract
// better results during the use of Distance Transform
for ( int i = 0; i < src.rows; i++ ) {
for ( int j = 0; j < src.cols; j++ ) {
if ( src.at<Vec3b>(i, j) == Vec3b(255,255,255) )
{
src.at<Vec3b>(i, j)[0] = 0;
src.at<Vec3b>(i, j)[1] = 0;
src.at<Vec3b>(i, j)[2] = 0;
}
}
}
// Show output image
imshow("Black Background Image", src);
black_bg.jpeg
// Create a kernel that we will use to sharpen our image
Mat kernel = (Mat_<float>(3,3) <<
1, 1, 1,
1, -8, 1,
1, 1, 1); // an approximation of second derivative, a quite strong kernel
// do the laplacian filtering as it is
// well, we need to convert everything in something more deeper then CV_8U
// because the kernel has some negative values,
// and we can expect in general to have a Laplacian image with negative values
// BUT a 8bits unsigned int (the one we are working with) can contain values from 0 to 255
// so the possible negative number will be truncated
Mat imgLaplacian;
filter2D(src, imgLaplacian, CV_32F, kernel);
Mat sharp;
src.convertTo(sharp, CV_32F);
Mat imgResult = sharp - imgLaplacian;
// convert back to 8bits gray scale
imgResult.convertTo(imgResult, CV_8UC3);
imgLaplacian.convertTo(imgLaplacian, CV_8UC3);
// imshow( "Laplace Filtered Image", imgLaplacian );
imshow( "New Sharped Image", imgResult );
laplace.jpeg
sharp.jpeg
// Create binary image from source image
Mat bw;
cvtColor(imgResult, bw, COLOR_BGR2GRAY);
threshold(bw, bw, 40, 255, THRESH_BINARY | THRESH_OTSU);
imshow("Binary Image", bw);
bin.jpeg
// Perform the distance transform algorithm
Mat dist;
distanceTransform(bw, dist, DIST_L2, 3);
// Normalize the distance image for range = {0.0, 1.0}
// so we can visualize and threshold it
normalize(dist, dist, 0, 1.0, NORM_MINMAX);
imshow("Distance Transform Image", dist);
dist_transf.jpeg
// Threshold to obtain the peaks
// This will be the markers for the foreground objects
threshold(dist, dist, 0.4, 1.0, THRESH_BINARY);
// Dilate a bit the dist image
Mat kernel1 = Mat::ones(3, 3, CV_8U);
dilate(dist, dist, kernel1);
imshow("Peaks", dist);
peaks.jpeg
// Create the CV_8U version of the distance image
// It is needed for findContours()
Mat dist_8u;
dist.convertTo(dist_8u, CV_8U);
// Find total markers
vector<vector<Point> > contours;
// Create the marker image for the watershed algorithm
Mat markers = Mat::zeros(dist.size(), CV_32S);
// Draw the foreground markers
for (size_t i = 0; i < contours.size(); i++)
{
drawContours(markers, contours, static_cast<int>(i), Scalar(static_cast<int>(i)+1), -1);
}
// Draw the background marker
circle(markers, Point(5,5), 3, Scalar(255), -1);
imshow("Markers", markers*10000);
markers.jpeg
// Perform the watershed algorithm
watershed(imgResult, markers);
Mat mark;
markers.convertTo(mark, CV_8U);
bitwise_not(mark, mark);
// imshow("Markers_v2", mark); // uncomment this if you want to see how the mark
// image looks like at that point
// Generate random colors
vector<Vec3b> colors;
for (size_t i = 0; i < contours.size(); i++)
{
int b = theRNG().uniform(0, 256);
int g = theRNG().uniform(0, 256);
int r = theRNG().uniform(0, 256);
colors.push_back(Vec3b((uchar)b, (uchar)g, (uchar)r));
}
// Create the result image
Mat dst = Mat::zeros(markers.size(), CV_8UC3);
// Fill labeled objects with random colors
for (int i = 0; i < markers.rows; i++)
{
for (int j = 0; j < markers.cols; j++)
{
int index = markers.at<int>(i,j);
if (index > 0 && index <= static_cast<int>(contours.size()))
{
dst.at<Vec3b>(i,j) = colors[index-1];
}
}
}
// Visualize the final image
imshow("Final Result", dst);
final.jpeg