fanfuhan OpenCV 教學111 ~ opencv-111-KMeans圖像分割

資料來源: https://fanfuhan.github.io/

https://fanfuhan.github.io/2019/05/23/opencv-111/

GITHUB:https://github.com/jash-git/fanfuhan_ML_OpenCV

KMean不光可以對數據進行分類，還可以實現對圖像分割，什麼圖像分割，簡單的說就要圖像的各種像素值，分割為幾個指定類別顏色值，

這種分割有兩個應用，一個可以實現圖像主色彩的簡單提取，

另外針對特定的應用場景可以實現證件照片的背景替換效果，這個方面早期最好的例子就是證件之星上面的背景替換。

當然要想實現類似的效果，絕對不是簡單的KMeans就可以做到的，還有一系列後續的交互操作需要完成。

對圖像數據來說，要把每個像素點作為單獨的樣本，按行組織。

C++

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

using namespace cv;
using namespace std;

int main(int argc, char** argv) {
	Mat src = imread("D:/projects/opencv_tutorial/data/images/toux.jpg");
	if (src.empty()) {
		printf("could not load image...\n");
		return -1;
	}
	namedWindow("input image", WINDOW_AUTOSIZE);
	imshow("input image", src);

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

	// 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)[0] = colorTab[label][0];
			result.at<Vec3b>(row, col)[1] = colorTab[label][1];
			result.at<Vec3b>(row, col)[2] = colorTab[label][2];
		}
	}

	imshow("KMeans-image-Demo", result);
	waitKey(0);
	return 0;
}

Python

"""
KMeans 图像分割
"""

import cv2 as cv
import numpy as np

image = cv.imread('images/toux.jpg')
cv.imshow("input", image)

# 构建图像数据
data = image.reshape((-1, 3))
data = np.float32(data)

# 图像分割
criteria = (cv.TERM_CRITERIA_EPS + cv.TERM_CRITERIA_MAX_ITER, 10, 1.0)
num_clusters = 4
ret, label, center = cv.kmeans(data, num_clusters, None, criteria, num_clusters, cv.KMEANS_RANDOM_CENTERS)
center = np.uint8(center)
res = center[label.flatten()]

# 显示
result = res.reshape((image.shape))
cv.imshow("result", result)

cv.waitKey(0)
cv.destroyAllWindows()