OpenCV之C++經典案例
2022-11-25 06:00:23
四個案例實戰
1、刀片缺陷檢測
2、自定義物件檢測
3、實時二維條碼檢測
4、影象分割與色彩提取
1、刀片缺陷檢測
問題分析
解決思路
- 嘗試二值影象分析
- 模板匹配技術
程式碼實現
#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);
//影象二值化
Mat gray, binary;
cvtColor(src, gray, COLOR_BGR2GRAY);
threshold(gray, binary, 0, 255, THRESH_BINARY_INV | THRESH_OTSU); //全域性閾值
imshow("binary", binary);
//定義結構元素，進行開操作去除小的干擾點
Mat se = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));
morphologyEx(binary, binary, MORPH_OPEN, se);
imshow("open-binary", binary);
//輪廓發現
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大小的情況下，向rects中放入rect
//rectangle(src, rect, Scalar(0, 255, 0), 2, 8, 0); //繪製矩形
//drawContours(src, contours, t, Scalar(0, 0, 255), 2, 8); //繪製輪廓
}
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++) { //將檢測到的缺陷部分繪製出來
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++) {
//構建diff
Mat roi = binary(rects[i]);
resize(roi, roi, tpl.size()); //將roi大小統一
Mat mask;
subtract(tpl, roi, mask);
Mat se = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1)); //開操作去除微小差異
morphologyEx(mask, mask, MORPH_OPEN, se);
threshold(mask, mask, 0, 255, THRESH_BINARY); //將獲取的mask二值化
imshow("mask", mask);
waitKey(0);
//根據diff查詢缺陷，閾值化
int count = 0;
for (int row = 0; row < h; row++) {
for (int col = 0; col < w; col++) {
int pv = mask.at<uchar>(row, col); //獲取每一個畫素值，如果等於255則count+1
if (pv == 255) {
count++;
}
}
}
//填充一個畫素塊
int mh = mask.rows + 2;
int mw = mask.cols + 2;
Mat m1 = Mat::zeros(Size(mw, mh), mask.type());
Rect mroi; //將mask複製到m1的mroi區域，並使mroi區域四周各有一個畫素值為0
mroi.x = 1;
mroi.y = 1;
mroi.height = mask.rows;
mroi.width = mask.cols;
mask.copyTo(m1(mroi));
//輪廓分析，對每個矩形中的差異進行過濾
vector<vector<Point>> contours;
vector<Vec4i> hierarchy;
findContours(m1, contours, hierarchy, RETR_LIST, CHAIN_APPROX_SIMPLE); //查詢每一個矩形中微小的差異輪廓
bool find = false;
for (size_t t = 0; t < contours.size(); t++) { //迴圈判斷矩形中的差異區域有無滿足要求的，如果有則find=true
Rect rect = boundingRect(contours[t]);
float ratio = (float)rect.width / ((float)rect.height); //計算矩形寬高比
//將寬高比>4的並且位於上下邊緣的差異區域過濾
if (ratio > 4.0 && (rect.y < 5 || (m1.rows - (rect.height + rect.y)) < 10)) { //將邊緣的白色區域過濾
continue;
}
double area = contourArea(contours[t]);
if (area > 10) {
printf("ratio:%.2f,area:%.2f \n", ratio, area);
find = true;
}
}
if (count > 50 && find) { //如果等於255的畫素個數>50並且符合以上判斷要求，就將該矩形放入缺陷容器defect中
printf("count:%d \n", count);
defect.push_back(rects[i]);
}
}
//返回結果
}
效果：
1、影象二值化並開操作
2、獲取每個刀片區域並排序
3、根據與模板差異的畫素個數篩選有缺陷的刀片
4、根據每個刀片區域與模板的差異部位寬高比、位置及畫素個數篩選有缺陷的刀片
2、自定義物件檢測
解決思路
- OpenCV中物件檢測類問題
- 模板匹配
- 特徵匹配
- 特徵 + 機器學習
- 選擇HOG特徵 + SVM機器學習生成模型
- 開窗檢測
HOG特徵
- 灰度影象轉換
- 梯度計算
- 分網格的梯度方向直方圖
- 塊描述子
- 塊描述子歸一化
- 特徵資料與檢測視窗
- 匹配方法
-
根據塊的形狀不一樣HOG特徵分為C-HOG和R-HOG
-
基於 L2 實現塊描述子歸一化，歸一化因子計算：
SVM簡要介紹
- 線性不可分對映為線性可分離
- 核函數：線性、高斯、多項式等
首先svm演演算法，當遇到分佈比較雜亂的函數時，可以進行升維處理，將二維不好處理的問題改為三維，是一個比較好的辦法；
此外，svm分割資料的操作也比較合理，劃分邊界及區域在經過一些複雜的函數計算什麼的，可以算出劃分的邊界的位置，劃分好邊界線，之後便可以劃分邊界區域，這樣區分樣本的時候就會事半功倍了。
對於升維進行計算資料的話，是存在一個核函數的，具體的講解如下：
當樣本在原始空間線性不可分時，可將樣本從原始空間對映到一個更高維的特徵空間，使得樣本在這個特徵空間內線性可分。而引入這樣的對映後，所要求解的對偶問題的求解中，無需求解真正的對映函數，而只需要知道其核函數。
核函數的定義：K(x,y)=<ϕ(x),ϕ(y)>，即在特徵空間的內積等於它們在原始樣本空間中通過核函數 K 計算的結果。一方面資料變成了高維空間中線性可分的資料，另一方面不需要求解具體的對映函數，只需要給定具體的核函數即可，這樣使得求解的難度大大降低。
程式碼實現
#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"); //讀取訓練好的模型
//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); //重新設定影象大小dsize與（fx、fy）不能同時為0
imshow("input", test);
Rect winRect;
winRect.width = 64;
winRect.height = 128;
int sum_x = 0;
int sum_y = 0;
int count = 0;
//開窗檢測...
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;
}
}
}
//顯示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))); //保證寬為64，同時寬高比例與原圖相同
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); //掃描目錄，得到所有正樣本
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，分類模型越複雜
svm->setType(SVM::C_SVC); //分類器型別
svm->setKernel(SVM::LINEAR); //線性核心，速度快
svm->setGamma(5.383); //線性核心可以忽略，其他核心需要
svm->train(trainData, ROW_SAMPLE, labels); //按行讀取
clog << "....[Done]" << endl;
printf("end train...\n");
//save xml
svm->save("D:/images/elec_watchzip/elec_watch/hog_elec.xml"); //儲存路徑
}
效果：
3、二維條碼檢測與定位
二維定位檢測知識點：
- 二維條碼特徵
- 影象二值化
- 輪廓提取
- 透視變換
- 幾何分析
二維條碼特徵
影象二值化與輪廓分析
- 全域性或者區域性閾值選擇
- 全域性閾值分割
- 最外層輪廓與多層輪廓
- 面積與幾何形狀過濾
- 透視變換與單應性矩陣
幾何分析
- 尋找每個正方形
- 尋找X方向1 : 1 : 3 : 1 : 1結構
- 尋找Y方向比率結構
- 得到輸出結果
演演算法流程設計
- 面積太小不能識別排除
程式碼層面知識點與執行
- minAreaRect
- findHomography
- warpPerspective
程式碼實現
#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; //將面積<100的輪廓去掉
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) { //根據寬高比進行過濾
Mat qr_roi = transformCorner(image, rect);
// 根據矩形特徵進行幾何分析
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容器中新增白色畫素點座標
}
}
}
RotatedRect rrt = minAreaRect(pts); //獲取pts的最小外接矩形
Point2f vertices[4];
rrt.points(vertices);
pts.clear();
for (int i = 0; i < 4; i++) { //繪製最小外接矩形的四根線
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()); //將result繪製成指定形狀
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); //通過與操作，獲取二維條碼區域
imshow("detect result", image);
//imwrite("D:/case03.png", image);
imshow("result-mask", mask);
imshow("qrcode-roi", dst);
}
bool isXCorner(Mat &image) { //對找到的候選輪廓進行分析
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; //判斷中心畫素是否為黑色
// verfiy finder pattern
bool findleft = false, findright = false;
int start = 0, end = 0;
int offset = 0;
while (true) { //從中間畫素開始向兩側遍歷查詢
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) { //當左右兩側都找到白色畫素時終止迴圈，start和end分別儲存起止座標
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為了保證獲取四捨五入的值，避免浮點數轉換為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) { //對中心畫素一側的畫素進行檢測，對黑白畫素個數分別計數，
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) { //如果白色畫素個數大於等於黑色畫素個數的兩倍，返回false，黑色畫素個數兩倍正常是白色畫素個數5倍
return false;
}
return true;
}
Mat transformCorner(Mat &image, RotatedRect &rect) { //單一性矩陣與透視變換
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;
}
過程分析
效果：
4、KMeans應用
- 資料聚類
- 影象聚類
- 背景替換
- 主色彩提取
KMeans聚類演演算法原理
- 聚類中心
- 根據距離分類
聚類和分類最大的不同在於，分類的目標是事先已知的，而聚類則不一樣，聚類事先不知道目標變數是什麼，類別沒有像分類那樣被預先定義出來，也就是聚類分組不需要提前被告知所劃分的組應該是什麼樣的，因為我們甚至可能都不知道我們再尋找什麼，所以聚類是用於知識發現而不是預測，所以，聚類有時也叫無監督學習。
KMeans演演算法是最常用的聚類演演算法，主要思想是:在給定K值和K個初始類簇中心點的情況下，把每個點(亦即資料記錄)分到離其最近的類簇中心點所代表的類簇中，所有點分配完畢之後，根據一個類簇內的所有點重新計算該類簇的中心點(取平均值)，然後再迭代的進行分配點和更新類簇中心點的步驟，直至類簇中心點的變化很小，或者達到指定的迭代次數。
K-means過程：
- 首先選擇k個類別的中心點
- 對任意一個樣本，求其到各類中心的距離，將該樣本歸到距離最短的中心所在的類
- 聚好類後，重新計算每個聚類的中心點位置
- 重複2,3步驟迭代，直到k個類中心點的位置不變，或者達到一定的迭代次數，則迭代結束，否則繼續迭代
程式碼實現
#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; //聚類個數
int sampleCount = rng.uniform(5, 500); //隨機產生的資料點個數，均勻分佈
Mat points(sampleCount, 1, CV_32FC2); //矩陣大小為：資料點個數*1，每個點有兩個維度
// 生成亂數
for (int k = 0; k < numCluster; k++) {
Point center;
center.x = rng.uniform(0, img.cols);
center.y = rng.uniform(0, img.rows);
//兩次迴圈產生亂數的縱座標範圍不同
Mat pointChunk = points.rowRange(k*sampleCount / numCluster,
k == numCluster - 1 ? sampleCount : (k + 1)*sampleCount / numCluster);
//使用指定範圍二維亂數填充矩陣，填充方式為均勻分佈或高斯分佈
rng.fill(pointChunk, RNG::NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));
}
randShuffle(points, 1, &rng); //打亂亂數順序
// 使用KMeans
Mat labels;
Mat centers;
//將這些點分為2類，每個點有一個標籤，使用不同的初始聚類中心執行演演算法的次數，初始中心點選取方式
kmeans(points, numCluster, labels, TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1), 3, KMEANS_PP_CENTERS, centers);
// 用不同顏色顯示分類
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); //對不同標籤的點按不同顏色進行填充
}
// 每個聚類的中心來繪製圓
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();
// 初始化定義
int sampleCount = width * height;
int clusterCount = 3;
Mat labels;
Mat centers;
// RGB 資料轉換到樣本資料
Mat sample_data = src.reshape(3, sampleCount); //將輸入影象轉換到特定維數
Mat data;
sample_data.convertTo(data, CV_32F);
// 執行K-Means
TermCriteria criteria = TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 0.1); //停止迭代判定條件，迭代10次，精度達到0.1
kmeans(data, clusterCount, labels, criteria, clusterCount, KMEANS_PP_CENTERS, centers);
// 顯示影象分割結果
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]; //按不同標籤對結果中的點設定不同顏色
}
}
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();
// 初始化定義
int sampleCount = width * height;
int clusterCount = 3;
Mat labels;
Mat centers;
// RGB 資料轉換到樣本資料
Mat sample_data = src.reshape(3, sampleCount);
Mat data;
sample_data.convertTo(data, CV_32F);
// 執行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); //獲取(0,0)點的label，與(0,0)點相同label的部分為背景
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; //將與(0,0)點相同label的部分畫素值設為255
}
}
}
imshow("mask", mask);
Mat se = getStructuringElement(MORPH_RECT, Size(3, 3), Point(-1, -1));
dilate(mask, mask, se); //背景白色區域膨脹操作
// 生成高斯權重
GaussianBlur(mask, mask, Size(5, 5), 0); //通過高斯模糊，使輪廓邊緣過度自然
imshow("mask-blur", mask);
// 基於高斯權重影象融合
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); //對bgr三通道進行分別融合
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();
// 初始化定義
int sampleCount = width * height;
int clusterCount = 4;
Mat labels;
Mat centers;
// RGB 資料轉換到樣本資料
Mat sample_data = src.reshape(3, sampleCount);
Mat data;
sample_data.convertTo(data, CV_32F);
// 執行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); //初始化一個 輸入影象寬*50 的色卡
vector<float> clusters(clusterCount);
// 生成色卡比率
for (int i = 0; i < labels.rows; i++) { //遍歷標籤
clusters[labels.at<int>(i, 0)]++;
}
for (int i = 0; i < clusters.size(); i++) { //將clusters對應位置儲存其對應比例
clusters[i] = clusters[i] / sampleCount;
}
int x_offset = 0;
// 繪製色卡
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聚類範例
2、使用KMeans根據影象顏色分割
3、影象背景平滑置換
4、獲取圖片中佔比最高的前四種顏色色卡
