OpenCV之C++经典案例

四个案例实战

1、刀片缺陷检测

2、自定义对象检测

3、实时二维码检测

4、图像分割与色彩提取

1、刀片缺陷检测

问题分析

解决思路

  • 尝试二值图像分析
  • 模板匹配技术

代码实现

#include <opencv2/opencv.hpp>
#include <iostream>

using namespace cv;
using namespace std;

Mat tpl;
void sort_box(vector<Rect> &boxes);
void detect_defect(Mat &binary, vector<Rect> rects, vector<Rect> &defect);
int main(int argc, char** argv) {
	Mat src = imread("D:/images/ce_01.jpg");
	if (src.empty()) {
		printf("could not load image file...");
		return -1;
	}
	namedWindow("input", WINDOW_AUTOSIZE);
	imshow("input", src);

	//图像二值化
	Mat gray, binary;
	cvtColor(src, gray, COLOR_BGR2GRAY);
	threshold(gray, binary, 0, 255, THRESH_BINARY_INV | THRESH_OTSU);  //全局阈值
	imshow("binary", binary);

	//定义结构元素,进行开操作去除小的干扰点
	Mat se = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));
	morphologyEx(binary, binary, MORPH_OPEN, se);
	imshow("open-binary", binary);

	//轮廓发现
	vector<vector<Point>> contours;
	vector<Vec4i> hierarchy;
	vector<Rect> rects;
	findContours(binary, contours, hierarchy, RETR_LIST, CHAIN_APPROX_SIMPLE);

	int height = src.rows;
	for (size_t t = 0; t < contours.size(); t++) {
		Rect rect = boundingRect(contours[t]);
		double area = contourArea(contours[t]);
		if (rect.height > (height / 2)) {
			continue;
		}
		if (area < 150) {
			continue;
		}
		rects.push_back(rect);  //不知道rects大小的情况下,向rects中放入rect
		//rectangle(src, rect, Scalar(0, 255, 0), 2, 8, 0);  //绘制矩形
		//drawContours(src, contours, t, Scalar(0, 0, 255), 2, 8);  //绘制轮廓
	}
	
	sort_box(rects);
	tpl = binary(rects[1]);

	//for (int i = 0; i < rects.size(); i++) {
	//	  putText(src, format("%d", i), rects[i].tl(), FONT_HERSHEY_PLAIN, 1.0, Scalar(0, 255, 0), 1, 8);
	//}
	vector<Rect> defects;
	detect_defect(binary, rects, defects);

	for (int i = 0; i < defects.size(); i++) {  //将检测到的缺陷部分绘制出来
		rectangle(src, defects[i], Scalar(0, 0, 255), 2, 8, 0);
		putText(src, "bad", defects[i].tl(), FONT_HERSHEY_PLAIN, 1.0, Scalar(0, 255, 0), 1, 8);
	}
	imshow("result", src);
	waitKey(0);
	return 0;
}

void sort_box(vector<Rect> &boxes) {
	int size = boxes.size();
	for (int i = 0; i < size; i++) {
		for (int j = i; j < size; j++) {
			int x = boxes[j].x;
			int y = boxes[j].y;
			if (y < boxes[i].y) {
				Rect temp = boxes[i];
				boxes[i] = boxes[j];
				boxes[j] = temp;
			}
		}
	}
}

void detect_defect(Mat &binary, vector<Rect> rects, vector<Rect> &defect) {
	int h = tpl.rows;
	int w = tpl.cols;
	int size = rects.size();
	for (int i = 0; i < size; i++) {
		//构建diff
		Mat roi = binary(rects[i]);
		resize(roi, roi, tpl.size());  //将roi大小统一
		Mat mask;
		subtract(tpl, roi, mask);
		Mat se = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));  //开操作去除微小差异
		morphologyEx(mask, mask, MORPH_OPEN, se);
		threshold(mask, mask, 0, 255, THRESH_BINARY);  //将获取的mask二值化
		imshow("mask", mask);
		waitKey(0);

		//根据diff查找缺陷,阈值化
		int count = 0;
		for (int row = 0; row < h; row++) {
			for (int col = 0; col < w; col++) {
				int pv = mask.at<uchar>(row, col);  //获取每一个像素值,如果等于255则count+1
				if (pv == 255) {
					count++;
				}
			}
		}

		//填充一个像素块
		int mh = mask.rows + 2;
		int mw = mask.cols + 2;
		Mat m1 = Mat::zeros(Size(mw, mh), mask.type());
		Rect mroi;  //将mask复制到m1的mroi区域,并使mroi区域四周各有一个像素值为0
		mroi.x = 1;
		mroi.y = 1;
		mroi.height = mask.rows;
		mroi.width = mask.cols;
		mask.copyTo(m1(mroi));

		//轮廓分析,对每个矩形中的差异进行过滤
		vector<vector<Point>> contours;
		vector<Vec4i> hierarchy;
		findContours(m1, contours, hierarchy, RETR_LIST, CHAIN_APPROX_SIMPLE);  //查找每一个矩形中微小的差异轮廓
		bool find = false;
		for (size_t t = 0; t < contours.size(); t++) {  //循环判断矩形中的差异区域有无满足要求的,如果有则find=true
			Rect rect = boundingRect(contours[t]);
			float ratio = (float)rect.width / ((float)rect.height);  //计算矩形宽高比
			//将宽高比>4的并且位于上下边缘的差异区域过滤
			if (ratio > 4.0 && (rect.y < 5 || (m1.rows - (rect.height + rect.y)) < 10)) {  //将边缘的白色区域过滤
				continue;
			}
			double area = contourArea(contours[t]);
			if (area > 10) {
				printf("ratio:%.2f,area:%.2f \n", ratio, area);
				find = true;
			}
		}

		if (count > 50 && find) {  //如果等于255的像素个数>50并且符合以上判断要求,就将该矩形放入缺陷容器defect中
			printf("count:%d \n", count);
			defect.push_back(rects[i]);
		}
	}
	//返回结果
}

效果:

1、图像二值化并开操作

2、获取每个刀片区域并排序

3、根据与模板差异的像素个数筛选有缺陷的刀片

4、根据每个刀片区域与模板的差异部位宽高比、位置及像素个数筛选有缺陷的刀片

2、自定义对象检测

解决思路

  • OpenCV中对象检测类问题
    • 模板匹配
    • 特征匹配
    • 特征 + 机器学习
  • 选择HOG特征 + SVM机器学习生成模型
  • 开窗检测

HOG特征

  • 灰度图像转换
  • 梯度计算
  • 分网格的梯度方向直方图
  • 块描述子
  • 块描述子归一化
  • 特征数据与检测窗口
  • 匹配方法

  • 根据块的形状不一样HOG特征分为C-HOG和R-HOG

  • 基于 L2 实现块描述子归一化,归一化因子计算:

SVM简要介绍

  • 线性不可分映射为线性可分离
  • 核函数:线性、高斯、多项式等

首先svm算法,当遇到分布比较杂乱的函数时,可以进行升维处理,将二维不好处理的问题改为三维,是一个比较好的办法;

此外,svm分割数据的操作也比较合理,划分边界及区域在经过一些复杂的函数计算什么的,可以算出划分的边界的位置,划分好边界线,之后便可以划分边界区域,这样区分样本的时候就会事半功倍了。

对于升维进行计算数据的话,是存在一个核函数的,具体的讲解如下:

当样本在原始空间线性不可分时,可将样本从原始空间映射到一个更高维的特征空间,使得样本在这个特征空间内线性可分。而引入这样的映射后,所要求解的对偶问题的求解中,无需求解真正的映射函数,而只需要知道其核函数。

核函数的定义:K(x,y)=<ϕ(x),ϕ(y)>,即在特征空间的内积等于它们在原始样本空间中通过核函数 K 计算的结果。一方面数据变成了高维空间中线性可分的数据,另一方面不需要求解具体的映射函数,只需要给定具体的核函数即可,这样使得求解的难度大大降低。

代码实现

#include <opencv2/opencv.hpp>
#include <iostream>

using namespace cv;
using namespace cv::ml;
using namespace std;

string positive_dir = "D:/images/elec_watchzip/elec_watch/positive";
string negative_dir = "D:/images/elec_watchzip/elec_watch/negative";
void get_hog_descriptor(Mat &image, vector<float> &desc);
void generate_dataset(Mat &trainData, Mat &labels);
void svm_train(Mat &trainData, Mat &labels);
int main(int argc, char** argv) {
	//read data and generate dataset
	Mat trainData = Mat::zeros(Size(3780, 26), CV_32FC1);
	Mat labels = Mat::zeros(Size(1, 26), CV_32SC1);
	generate_dataset(trainData, labels);

	//SVM train and save model
	svm_train(trainData, labels);

	//load model
	Ptr<SVM> svm = SVM::load("D:/images/elec_watchzip/elec_watch/hog_elec.xml");  //读取训练好的模型
	
	//detect custom object
	Mat test = imread("D:/images/elec_watchzip/elec_watch/test/scene_01.jpg");
	resize(test, test, Size(0, 0), 0.2, 0.2);  //重新设置图像大小dsize与(fx、fy)不能同时为0
	imshow("input", test);
	Rect winRect;
	winRect.width = 64;
	winRect.height = 128;
	int sum_x = 0;
	int sum_y = 0;
	int count = 0;

	//开窗检测...
	for (int row = 64; row < test.rows - 64; row += 4) {
		for (int col = 32; col < test.cols - 32; col += 4) {
			winRect.x = col - 32;
			winRect.y = row - 64;
			vector<float> fv;
			Mat img = test(winRect);
			get_hog_descriptor(img, fv);
			Mat one_row = Mat::zeros(Size(fv.size(), 1), CV_32FC1);
			for (int i = 0; i < fv.size(); i++) {
				one_row.at<float>(0, i) = fv[i];
			}
			float result = svm->predict(one_row);
			if (result > 0) {
				//rectangle(test, winRect, Scalar(0, 0, 255), 1, 8, 0);
				count += 1;
				sum_x += winRect.x;
				sum_y += winRect.y;
			}
		}
	}
	//显示box
	winRect.x = sum_x / count;
	winRect.y = sum_y / count;
	rectangle(test, winRect, Scalar(255, 0, 0), 2, 8, 0);
	imshow("object detection result", test);
	waitKey(0);
	return 0;

}

void get_hog_descriptor(Mat &image, vector<float> &desc) {
	HOGDescriptor hog;  //HOG描述子
	int h = image.rows;
	int w = image.cols;
	float rate = 64.0 / w;
	Mat img, gray;
	resize(image, img, Size(64, int(rate*h)));  //保证宽为64,同时宽高比例与原图相同
	cvtColor(img, gray, COLOR_BGR2GRAY);
	Mat result = Mat::zeros(Size(64, 128), CV_8UC1);
	result = Scalar(127);
	Rect roi;
	roi.x = 0;
	roi.width = 64;
	roi.y = (128 - gray.rows) / 2;
	roi.height = gray.rows;
	gray.copyTo(result(roi));
	hog.compute(result, desc, Size(8, 8), Size(0, 0));
	printf("desc len:%d\n", desc.size());
}
void generate_dataset(Mat &trainData, Mat &labels) {
	vector<String> images;
	glob(positive_dir, images);  //扫描目录,得到所有正样本
	int pos_num = images.size();
	for (int i = 0; i < images.size(); i++) {
		Mat image = imread(images[i].c_str());
		vector<float> fv;
		get_hog_descriptor(image, fv);
		for (int j = 0; j < fv.size(); j++) {
			trainData.at<float>(i, j) = fv[j];
		}
		labels.at<int>(i, 0) = 1;
	}
	images.clear();
	glob(negative_dir, images);
	for (int i = 0; i < images.size(); i++) {
		Mat image = imread(images[i].c_str());
		vector<float> fv;
		get_hog_descriptor(image, fv);
		for (int j = 0; j < fv.size(); j++) {
			trainData.at<float>(i + pos_num, j) = fv[j];
		}
		labels.at<int>(i + pos_num, 0) = -1;
	}
}
void svm_train(Mat &trainData, Mat &labels) {
	printf("\n start SVM training... \n");
	Ptr<SVM> svm = SVM::create();
	svm->setC(2.67);  //值越大,分类模型越复杂
	svm->setType(SVM::C_SVC);  //分类器类型
	svm->setKernel(SVM::LINEAR);  //线性内核,速度快
	svm->setGamma(5.383);  //线性内核可以忽略,其他内核需要
	svm->train(trainData, ROW_SAMPLE, labels);  //按行读取
	clog << "....[Done]" << endl;
	printf("end train...\n");

	//save xml
	svm->save("D:/images/elec_watchzip/elec_watch/hog_elec.xml");  //保存路径

}

效果:

3、二维码检测与定位

二维定位检测知识点:

  • 二维码特征
  • 图像二值化
  • 轮廓提取
  • 透视变换
  • 几何分析

二维码特征

图像二值化与轮廓分析

  • 全局或者局部阈值选择
  • 全局阈值分割
  • 最外层轮廓与多层轮廓
  • 面积与几何形状过滤
  • 透视变换与单应性矩阵

几何分析

  • 寻找每个正方形
  • 寻找X方向1 : 1 : 3 : 1 : 1结构
  • 寻找Y方向比率结构
  • 得到输出结果

算法流程设计

  • 面积太小不能识别排除

代码层面知识点与运行

  • minAreaRect
  • findHomography
  • warpPerspective

代码实现

#include <opencv2/opencv.hpp>
#include <iostream>

using namespace cv;
using namespace std;

void scanAndDetectQRCode(Mat & image);
bool isXCorner(Mat &image);
bool isYCorner(Mat &image);
Mat transformCorner(Mat &image, RotatedRect &rect);
int main(int argc, char** argv) {
	// Mat src = imread("D:/images/qrcode.png");
	Mat src = imread("D:/images/qrcode_07.png");
	if (src.empty()) {
		printf("could not load image file...");
		return -1;
	}
	namedWindow("input", WINDOW_AUTOSIZE);
	imshow("input", src);
	scanAndDetectQRCode(src);
	waitKey(0);
	return 0;
}

void scanAndDetectQRCode(Mat & image) {
	Mat gray, binary;
	cvtColor(image, gray, COLOR_BGR2GRAY);
	threshold(gray, binary, 0, 255, THRESH_BINARY | THRESH_OTSU);
	imshow("binary", binary);

	// detect rectangle now
	vector<vector<Point>> contours;
	vector<Vec4i> hireachy;
	Moments monents;
	findContours(binary.clone(), contours, hireachy, RETR_LIST, CHAIN_APPROX_SIMPLE, Point());
	Mat result = Mat::zeros(image.size(), CV_8UC1);
	for (size_t t = 0; t < contours.size(); t++) {
		double area = contourArea(contours[t]);
		if (area < 100) continue;  //将面积<100的轮廓去掉

		RotatedRect rect = minAreaRect(contours[t]);
		float w = rect.size.width;
		float h = rect.size.height;
		float rate = min(w, h) / max(w, h);
		if (rate > 0.85 && w < image.cols / 4 && h < image.rows / 4) {  //根据宽高比进行过滤
			Mat qr_roi = transformCorner(image, rect);
			// 根据矩形特征进行几何分析
			if (isXCorner(qr_roi)) {
				drawContours(image, contours, static_cast<int>(t), Scalar(255, 0, 0), 2, 8);
				drawContours(result, contours, static_cast<int>(t), Scalar(255), 2, 8);
			}
		}
	}

	// scan all key points
	vector<Point> pts;
	for (int row = 0; row < result.rows; row++) {
		for (int col = 0; col < result.cols; col++) {
			int pv = result.at<uchar>(row, col);
			if (pv == 255) {
				pts.push_back(Point(col, row));  //向pts容器中添加白色像素点坐标
			}
		}
	}
	RotatedRect rrt = minAreaRect(pts);  //获取pts的最小外接矩形
	Point2f vertices[4];
	rrt.points(vertices);
	pts.clear();
	for (int i = 0; i < 4; i++) {  //绘制最小外接矩形的四根线
		line(image, vertices[i], vertices[(i + 1) % 4], Scalar(0, 255, 0), 2);
		pts.push_back(vertices[i]);
	}
	Mat mask = Mat::zeros(result.size(), result.type());  //将result绘制成指定形状
	vector<vector<Point>> cpts;
	cpts.push_back(pts);
	drawContours(mask, cpts, 0, Scalar(255), -1, 8);  //填充

	Mat dst;
	bitwise_and(image, image, dst, mask);  //通过与操作,获取二维码区域

	imshow("detect result", image);
	//imwrite("D:/case03.png", image);
	imshow("result-mask", mask);
	imshow("qrcode-roi", dst);
}
bool isXCorner(Mat &image) {  //对找到的候选轮廓进行分析
	Mat gray, binary;
	cvtColor(image, gray, COLOR_BGR2GRAY);
	threshold(gray, binary, 0, 255, THRESH_BINARY | THRESH_OTSU);
	int xb = 0, yb = 0;
	int w1x = 0, w2x = 0;
	int b1x = 0, b2x = 0;

	int width = binary.cols;
	int height = binary.rows;
	int cy = height / 2;
	int cx = width / 2;
	int pv = binary.at<uchar>(cy, cx);
	if (pv == 255) return false;  //判断中心像素是否为黑色
	// verfiy finder pattern
	bool findleft = false, findright = false;
	int start = 0, end = 0;
	int offset = 0;
	while (true) {  //从中间像素开始向两侧遍历查找
		offset++;
		if ((cx - offset) <= width / 8 || (cx + offset) >= width - 1) {
			start = -1;
			end = -1;
			break;
		}
		pv = binary.at<uchar>(cy, cx - offset);
		if (pv == 255) {
			start = cx - offset;
			findleft = true;
		}
		pv = binary.at<uchar>(cy, cx + offset);
		if (pv == 255) {
			end = cx + offset;
			findright = true;
		}
		if (findleft && findright) {  //当左右两侧都找到白色像素时终止循环,start和end分别保存起止坐标
			break;
		}
	}

	if (start <= 0 || end <= 0) {
		return false;
	}
	xb = end - start;
	for (int col = start; col > 0; col--) {
		pv = binary.at<uchar>(cy, col);
		if (pv == 0) {
			w1x = start - col;
			break;
		}
	}
	for (int col = end; col < width - 1; col++) {
		pv = binary.at<uchar>(cy, col);
		if (pv == 0) {
			w2x = col - end;
			break;
		}
	}
	for (int col = (end + w2x); col < width; col++) {
		pv = binary.at<uchar>(cy, col);
		if (pv == 255) {
			b2x = col - end - w2x;
			break;
		}
		else {
			b2x++;
		}
	}
	for (int col = (start - w1x); col > 0; col--) {
		pv = binary.at<uchar>(cy, col);
		if (pv == 255) {
			b1x = start - col - w1x;
			break;
		}
		else {
			b1x++;
		}
	}

	float sum = xb + b1x + b2x + w1x + w2x;
	//printf("xb : %d, b1x = %d, b2x = %d, w1x = %d, w2x = %d\n", xb , b1x , b2x , w1x , w2x);
	xb = static_cast<int>((xb / sum)*7.0 + 0.5);  //+0.5为了保证获取四舍五入的值,避免浮点数转换为0
	b1x = static_cast<int>((b1x / sum)*7.0 + 0.5);
	b2x = static_cast<int>((b2x / sum)*7.0 + 0.5);
	w1x = static_cast<int>((w1x / sum)*7.0 + 0.5);
	w2x = static_cast<int>((w2x / sum)*7.0 + 0.5);
	printf("xb : %d, b1x = %d, b2x = %d, w1x = %d, w2x = %d\n", xb, b1x, b2x, w1x, w2x);
	if ((xb == 3 || xb == 4) && b1x == b2x && w1x == w2x && w1x == b1x && b1x == 1) { // 1:1:3:1:1
		return true;
	}
	else {
		return false;
	}
}
bool isYCorner(Mat &image) {  //对中心像素一侧的像素进行检测,对黑白像素个数分别计数,
	Mat gray, binary;
	cvtColor(image, gray, COLOR_BGR2GRAY);
	threshold(gray, binary, 0, 255, THRESH_BINARY | THRESH_OTSU);
	int width = binary.cols;
	int height = binary.rows;
	int cy = height / 2;
	int cx = width / 2;
	int pv = binary.at<uchar>(cy, cx);
	int bc = 0, wc = 0;
	bool found = true;
	for (int row = cy; row > 0; row--) {
		pv = binary.at<uchar>(row, cx);
		if (pv == 0 && found) {
			bc++;
		}
		else if (pv == 255) {
			found = false;
			wc++;
		}
	}
	bc = bc * 2;
	if (bc <= wc) {  //如果白色像素个数大于等于黑色像素个数的两倍,返回false,黑色像素个数两倍正常是白色像素个数5倍
		return false;
	}
	return true;
}

Mat transformCorner(Mat &image, RotatedRect &rect) {  //单一性矩阵与透视变换
	int width = static_cast<int>(rect.size.width);
	int height = static_cast<int>(rect.size.height);
	Mat result = Mat::zeros(height, width, image.type());
	Point2f vertices[4];
	rect.points(vertices);
	vector<Point> src_corners;
	vector<Point> dst_corners;
	dst_corners.push_back(Point(0, 0));
	dst_corners.push_back(Point(width, 0));
	dst_corners.push_back(Point(width, height)); // big trick
	dst_corners.push_back(Point(0, height));
	for (int i = 0; i < 4; i++) {
		src_corners.push_back(vertices[i]);
	}
	Mat h = findHomography(src_corners, dst_corners);
	warpPerspective(image, result, h, result.size());
	return result;
}

过程分析

效果:

4、KMeans应用

  • 数据聚类
  • 图像聚类
  • 背景替换
  • 主色彩提取

KMeans聚类算法原理

  • 聚类中心
  • 根据距离分类

​ 聚类和分类最大的不同在于,分类的目标是事先已知的,而聚类则不一样,聚类事先不知道目标变量是什么,类别没有像分类那样被预先定义出来,也就是聚类分组不需要提前被告知所划分的组应该是什么样的,因为我们甚至可能都不知道我们再寻找什么,所以聚类是用于知识发现而不是预测,所以,聚类有时也叫无监督学习。

KMeans算法是最常用的聚类算法,主要思想是:在给定K值和K个初始类簇中心点的情况下,把每个点(亦即数据记录)分到离其最近的类簇中心点所代表的类簇中,所有点分配完毕之后,根据一个类簇内的所有点重新计算该类簇的中心点(取平均值),然后再迭代的进行分配点和更新类簇中心点的步骤,直至类簇中心点的变化很小,或者达到指定的迭代次数。

K-means过程:

  1. 首先选择k个类别的中心点
  2. 对任意一个样本,求其到各类中心的距离,将该样本归到距离最短的中心所在的类
  3. 聚好类后,重新计算每个聚类的中心点位置
  4. 重复2,3步骤迭代,直到k个类中心点的位置不变,或者达到一定的迭代次数,则迭代结束,否则继续迭代

代码实现

#include <opencv2/opencv.hpp>
#include <iostream>

using namespace cv;
using namespace std;

void kmeans_data_demo();
void kmeans_image_demo();
void kmeans_background_replace();
void kmeans_color_card();
int main(int argc, char** argv) {
	// kmeans_data_demo();
	// kmeans_image_demo();
	// kmeans_background_replace();
	kmeans_color_card();
	return 0;

	waitKey(0);
	return 0;
}

void kmeans_data_demo() {
	Mat img(500, 500, CV_8UC3);
	RNG rng(12345);

	Scalar colorTab[] = {
		Scalar(0, 0, 255),
		Scalar(255, 0, 0),
	};

	int numCluster = 2;  //聚类个数
	int sampleCount = rng.uniform(5, 500);  //随机产生的数据点个数,均匀分布
	Mat points(sampleCount, 1, CV_32FC2);  //矩阵大小为:数据点个数*1,每个点有两个维度

	// 生成随机数
	for (int k = 0; k < numCluster; k++) {
		Point center;
		center.x = rng.uniform(0, img.cols);
		center.y = rng.uniform(0, img.rows);
		//两次循环产生随机数的纵坐标范围不同
		Mat pointChunk = points.rowRange(k*sampleCount / numCluster,
			k == numCluster - 1 ? sampleCount : (k + 1)*sampleCount / numCluster);
		//使用指定范围二维随机数填充矩阵,填充方式为均匀分布或高斯分布
		rng.fill(pointChunk, RNG::NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));
	}
	randShuffle(points, 1, &rng);  //打乱随机数顺序

	// 使用KMeans
	Mat labels;
	Mat centers;
	//将这些点分为2类,每个点有一个标签,使用不同的初始聚类中心执行算法的次数,初始中心点选取方式
	kmeans(points, numCluster, labels, TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1), 3, KMEANS_PP_CENTERS, centers);

	// 用不同颜色显示分类
	img = Scalar::all(255);
	for (int i = 0; i < sampleCount; i++) {
		int index = labels.at<int>(i);
		Point p = points.at<Point2f>(i);
		circle(img, p, 2, colorTab[index], -1, 8);  //对不同标签的点按不同颜色进行填充
	}

	// 每个聚类的中心来绘制圆
	for (int i = 0; i < centers.rows; i++) {
		int x = centers.at<float>(i, 0);
		int y = centers.at<float>(i, 1);
		printf("c.x= %d, c.y=%d\n", x, y);
		circle(img, Point(x, y), 40, colorTab[i], 1, LINE_AA);
	}

	imshow("KMeans-Data-Demo", img);
	waitKey(0);
}
void kmeans_image_demo() {
	Mat src = imread("D:/images/toux.jpg");
	if (src.empty()) {
		printf("could not load image...\n");
		return;
	}
	namedWindow("input image", WINDOW_AUTOSIZE);
	imshow("input image", src);

	Vec3b colorTab[] = {
		Vec3b(0, 0, 255),
		Vec3b(0, 255, 0),
		Vec3b(255, 0, 0),
		Vec3b(0, 255, 255),
		Vec3b(255, 0, 255)
	};

	int width = src.cols;
	int height = src.rows;
	int dims = src.channels();

	// 初始化定义
	int sampleCount = width * height;
	int clusterCount = 3;
	Mat labels;
	Mat centers;

	// RGB 数据转换到样本数据
	Mat sample_data = src.reshape(3, sampleCount);  //将输入图像转换到特定维数
	Mat data;
	sample_data.convertTo(data, CV_32F);

	// 运行K-Means
	TermCriteria criteria = TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1);  //停止迭代判定条件,迭代10次,精度达到0.1
	kmeans(data, clusterCount, labels, criteria, clusterCount, KMEANS_PP_CENTERS, centers);

	// 显示图像分割结果
	int index = 0;
	Mat result = Mat::zeros(src.size(), src.type());
	for (int row = 0; row < height; row++) {
		for (int col = 0; col < width; col++) {
			index = row * width + col;
			int label = labels.at<int>(index, 0);
			result.at<Vec3b>(row, col) = colorTab[label];  //按不同标签对结果中的点设置不同颜色
		}
	}

	imshow("KMeans-image-Demo", result);
	waitKey(0);
}
void kmeans_background_replace() {
	Mat src = imread("D:/images/toux.jpg");
	if (src.empty()) {
		printf("could not load image...\n");
		return;
	}
	namedWindow("input image", WINDOW_AUTOSIZE);
	imshow("input image", src);

	int width = src.cols;
	int height = src.rows;
	int dims = src.channels();

	// 初始化定义
	int sampleCount = width * height;
	int clusterCount = 3;
	Mat labels;
	Mat centers;

	// RGB 数据转换到样本数据
	Mat sample_data = src.reshape(3, sampleCount);
	Mat data;
	sample_data.convertTo(data, CV_32F);

	// 运行K-Means
	TermCriteria criteria = TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1);
	kmeans(data, clusterCount, labels, criteria, clusterCount, KMEANS_PP_CENTERS, centers);

	// 生成mask
	Mat mask = Mat::zeros(src.size(), CV_8UC1);
	int index = labels.at<int>(0, 0);  //获取(0,0)点的label,与(0,0)点相同label的部分为背景
	labels = labels.reshape(1, height);
	for (int row = 0; row < height; row++) {
		for (int col = 0; col < width; col++) {
			int c = labels.at<int>(row, col);
			if (c == index) {
				mask.at<uchar>(row, col) = 255;  //将与(0,0)点相同label的部分像素值设为255
			}
		}
	}
	imshow("mask", mask);

	Mat se = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));
	dilate(mask, mask, se);  //背景白色区域膨胀操作

	// 生成高斯权重
	GaussianBlur(mask, mask, Size(5, 5), 0);  //通过高斯模糊,使轮廓边缘过度自然
	imshow("mask-blur", mask);

	// 基于高斯权重图像融合
	Mat result = Mat::zeros(src.size(), CV_8UC3);
	for (int row = 0; row < height; row++) {
		for (int col = 0; col < width; col++) {
			float w1 = mask.at<uchar>(row, col) / 255.0;
			Vec3b bgr = src.at<Vec3b>(row, col);
			bgr[0] = w1 * 255.0 + bgr[0] * (1.0 - w1);  //对bgr三通道进行分别融合
			bgr[1] = w1 * 0 + bgr[1] * (1.0 - w1);
			bgr[2] = w1 * 255.0 + bgr[2] * (1.0 - w1);
			result.at<Vec3b>(row, col) = bgr;
		}
	}
	imshow("background-replacement-demo", result);
	waitKey(0);
}
void kmeans_color_card() {
	Mat src = imread("D:/images/test.png");
	if (src.empty()) {
		printf("could not load image...\n");
		return;
	}
	namedWindow("input image", WINDOW_AUTOSIZE);
	imshow("input image", src);

	int width = src.cols;
	int height = src.rows;
	int dims = src.channels();

	// 初始化定义
	int sampleCount = width * height;
	int clusterCount = 4;
	Mat labels;
	Mat centers;

	// RGB 数据转换到样本数据
	Mat sample_data = src.reshape(3, sampleCount);
	Mat data;
	sample_data.convertTo(data, CV_32F);

	// 运行K-Means
	TermCriteria criteria = TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1);
	kmeans(data, clusterCount, labels, criteria, clusterCount, KMEANS_PP_CENTERS, centers);

	Mat card = Mat::zeros(Size(width, 50), CV_8UC3);  //初始化一个 输入图像宽*50 的色卡
	vector<float> clusters(clusterCount);

	// 生成色卡比率
	for (int i = 0; i < labels.rows; i++) {  //遍历标签
		clusters[labels.at<int>(i, 0)]++;
	}

	for (int i = 0; i < clusters.size(); i++) {  //将clusters对应位置保存其对应比例
		clusters[i] = clusters[i] / sampleCount;
	}
	int x_offset = 0;

	// 绘制色卡
	for (int x = 0; x < clusterCount; x++) {
		Rect rect;
		rect.x = x_offset;
		rect.y = 0;
		rect.height = 50;
		rect.width = round(clusters[x] * width);
		x_offset += rect.width;
		int b = centers.at<float>(x, 0);
		int g = centers.at<float>(x, 1);
		int r = centers.at<float>(x, 2);
		rectangle(card, rect, Scalar(b, g, r), -1, 8, 0);
	}

	imshow("Image Color Card", card);
	waitKey(0);
}

效果:

1、KMeans聚类示例

2、使用KMeans根据图像颜色分割

3、图像背景平滑置换

4、获取图片中占比最高的前四种颜色色卡

posted @ 2022-11-24 22:01  wydilearn  阅读(279)  评论(0编辑  收藏  举报