什么是图像分割
图像分割(Image Segmentation)是图像处理最重要的处理手段之一
图像分割的目标是将图像中像素根据一定的规则分为若干(N)个cluster集合，每个集合包含一类像素。
根据算法分为监督学习方法和无监督学习方法，图像分割的算法多数都是无监督学习方法 - KMeans
距离变换常见算法有两种
- 不断膨胀/腐蚀得到
- 基于倒角距离
分水岭变换常见的算法
- 基于浸泡理论实现
cv::distanceTransform(
InputArray src,
OutputArray dst,
OutputArray labels, //离散维诺图输出
int distanceType, // DIST_L1/DIST_L2,
int maskSize, // 3x3,最新的支持5x5，推荐3x3、
int labelType=DIST_LABEL_CCOMP //dst输出8位或者32位的浮点数，单一通道，大小与输入图像一致
)
cv::watershed(
InputArray image,
InputOutputArray markers
)
处理流程
1. 将白色背景变成黑色-目的是为后面的变换做准备
2. 使用filter2D与拉普拉斯算子实现图像对比度提高，sharp
3. 转为二值图像通过threshold
4. 距离变换
5. 对距离变换结果进行归一化到[0~1]之间
6. 使用阈值，再次二值化，得到标记
7. 腐蚀得到每个Peak - erode
8. 发现轮廓 – findContours
9. 绘制轮廓- drawContours
10. 分水岭变换 watershed
11. 对每个分割区域着色输出结果
int main(int argc, char** argv) {
char input_win[] = "input image";
char watershed_win[] = "watershed segmentation demo";
Mat src = imread(STRPAHT2);
if (src.empty()) {
printf("could not load image...\n");
return -1;
}
namedWindow(input_win, CV_WINDOW_AUTOSIZE);
imshow(input_win, src);
// 将白色背景变成黑色-为后面的变换做准备
for (int row = 0; row < src.rows; row++) {
for (int col = 0; col < src.cols; col++) {
if (src.at<Vec3b>(row, col) == Vec3b(255, 255, 255)) {
src.at<Vec3b>(row, col)[0] = 0;
src.at<Vec3b>(row, col)[1] = 0;
src.at<Vec3b>(row, col)[2] = 0;
}
}
}
//namedWindow("black background", CV_WINDOW_AUTOSIZE);
//imshow("black background", src);
// sharpen
Mat kernel = (Mat_<float>(3, 3) << 1, 1, 1, 1, -8, 1, 1, 1, 1);
Mat imgLaplance;
Mat sharpenImg = src;
//使用filter2D与拉普拉斯算子实现图像对比度提高，sharp
filter2D(src, imgLaplance, CV_32F, kernel, Point(-1, -1), 0, BORDER_DEFAULT);
src.convertTo(sharpenImg, CV_32F);
Mat resultImg = sharpenImg - imgLaplance;
resultImg.convertTo(resultImg, CV_8UC3);
imgLaplance.convertTo(imgLaplance, CV_8UC3);
imshow("sharpen image", resultImg);
// convert to binary
Mat binaryImg;
cvtColor(src, resultImg, CV_BGR2GRAY);
// 转为二值图像通过threshold
threshold(resultImg, binaryImg, 40, 255, THRESH_BINARY | THRESH_OTSU);
imshow("binary image", binaryImg);
Mat distImg;
// 每一个非零点距离离自己最近的零点的距离
distanceTransform(binaryImg, distImg, DIST_L1, CV_DIST_C, 5);
// 归一化
normalize(distImg, distImg, 0, 1, NORM_MINMAX);
imshow("distance result", distImg);
// 使用阈值，再次二值化，得到标记
threshold(distImg, distImg, .4, 1, THRESH_BINARY);
Mat k1 = Mat::ones(13, 13, CV_8UC1);
// 膨胀/腐蚀
erode(distImg, distImg, k1, Point(-1, -1));
imshow("distance binary image", distImg);
// markers
Mat dist_8u;
distImg.convertTo(dist_8u, CV_8U);
vector<vector<Point>> contours;
// 发现轮廓
findContours(dist_8u, contours, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE, Point(0, 0));
// 绘制轮廓
Mat markers = Mat::zeros(src.size(), CV_32SC1);
for (size_t i = 0; i < contours.size(); i++) {
drawContours(markers, contours, static_cast<int>(i), Scalar::all(static_cast<int>(i) + 1), -1);
}
circle(markers, Point(5, 5), 3, Scalar(255, 255, 255), -1);
imshow("my markers", markers * 1000);
// 分水岭变换
watershed(src, markers);
Mat mark = Mat::zeros(markers.size(), CV_8UC1);
markers.convertTo(mark, CV_8UC1);
bitwise_not(mark, mark, Mat());
imshow("watershed image", mark);
// 对每个分割区域着色输出结果
vector<Vec3b> colors;
for (size_t i = 0; i < contours.size(); i++) {
int r = theRNG().uniform(0, 255);
int g = theRNG().uniform(0, 255);
int b = theRNG().uniform(0, 255);
colors.push_back(Vec3b((uchar)b, (uchar)g, (uchar)r));
}
Mat dst = Mat::zeros(markers.size(), CV_8UC3);
for (int row = 0; row < markers.rows; row++) {
for (int col = 0; col < markers.cols; col++) {
int index = markers.at<int>(row, col);
if (index > 0 && index <= static_cast<int>(contours.size())) {
dst.at<Vec3b>(row, col) = colors[index - 1];
}
else {
dst.at<Vec3b>(row, col) = Vec3b(0, 0, 0);
}
}
}
imshow("Final Result", dst);
waitKey(0);
return 0;
}
