如何减少以下代码的执行时间

我试图为图像提供一些草图效果，因为我在opencv中使用了高斯建模技术，但我面临一个问题，即执行需要更多时间。当图片大小较小时，时间会减少，如果大小较大，则需要更多时间。请任何人告诉如何在不更改以下代码的图像实际大小的情况下减少执行时间

#include "opencv2/opencv.hpp"
#include <iostream>
#include <vector>
#include "opencv2/ml/ml.hpp"
#include <list>
#include <iostream>
using namespace cv;
using namespace std;
void clustrize_colors(Mat& src,Mat& dst)
{
	// Number of clusters
	int NrGMMComponents = 96;
	cv::GaussianBlur(src,src,Size(3,3),1);
	int srcHeight = src.rows;
	int srcWidth  = src.cols;
	// Get datapoints
	vector<Vec3d> ListSamplePoints;
	for (int y=0; y<srcHeight; y++)
	{
		for (int x=0; x<srcWidth; x++)
		{
			// Collecting points from image
			Vec3b bgrPixel = src.at<Vec3b>(y, x);
			uchar b = bgrPixel.val[0];
			uchar g = bgrPixel.val[1];
			uchar r = bgrPixel.val[2];
			if(rand()%25==0) // peek every 25-th
			{
				ListSamplePoints.push_back(Vec3d(b,g,r));
			}
		} // for (x)
	} // for (y)
	// Form training matrix
	int NrSamples = ListSamplePoints.size();    
	Mat samples( NrSamples, 3, CV_64FC1 );
	for (int s=0; s<NrSamples; s++)
	{
		Vec3d v = ListSamplePoints.at(s);
		samples.at<double>(s,0) = (float) v[0];
		samples.at<double>(s,1) = (float) v[1];
		samples.at<double>(s,2) = (float) v[2];
	}    
	// 
	cout << "Learning to represent the sample distributions with " << NrGMMComponents << " gaussians." << endl;
	cout << "Started GMM training" << endl;
	Ptr<cv::ml::EM> em_model;
	cv::ml::EM::Params params(NrGMMComponents,cv::ml::EM::COV_MAT_GENERIC);
	Mat labels(NrSamples,1,CV_32SC1);
	Mat logLikelihoods( NrSamples, 1, CV_64FC1 );
	// Train classifier
	em_model=cv::ml::EM::train(samples,logLikelihoods,labels,noArray(),params);
	cout << "Finished GMM training" << endl;
	// result image
	Mat img  = Mat::zeros( Size( srcWidth, srcHeight ), CV_8UC3 );
	// predict cluster
	Mat sample( 1, 3, CV_64FC1 );
	Mat means=em_model->getMeans();
	for(int i = 0; i < img.rows; i++ )
	{
		for(int j = 0; j < img.cols; j++ )
		{
			Vec3b v=src.at<Vec3b>(i,j);
			sample.at<double>(0,0) = (float) v[0];
			sample.at<double>(0,1) = (float) v[1];
			sample.at<double>(0,2) = (float) v[2];
			int response = cvRound(em_model->predict( sample ));
			img.at<Vec3b>(i,j)[0]=means.at<double>(response,0);
			img.at<Vec3b>(i,j)[1]=means.at<double>(response,1);
			img.at<Vec3b>(i,j)[2]=means.at<double>(response,2);
		}
	}
	img.convertTo(img,CV_8UC3);
        namedWindow("result",WINDOW_AUTOSIZE);
	imshow("result",img);
        imwrite("D:\nfr.jpg",img);
	waitKey();
	dst=img;
}
void processLayer(Mat& src,Mat& dst)
{
	Mat tmp=src.clone();
	Mat gx,gy,mag,blurred;
	Sobel( src, gx, -1, 1, 0, 3);
	Sobel( src, gy, -1, 0, 1, 3);
	magnitude(gx,gy,mag);
	//GaussianBlur(mag,blurred,Size(3,3),2);
	//mag+=blurred;
	normalize(mag,mag,0,1,cv::NORM_MINMAX);
	//sqrt(mag,dst);
	dst=mag.clone();
	normalize(dst,dst,0,1,cv::NORM_MINMAX);
}
int main(int ac, char** av)
{
	Mat clusterized;
	Mat frame=imread("image path"); ////load an image//////
        //resize(frame,frame,Size(256,256),0,0,INTER_LINEAR);
	clustrize_colors(frame,clusterized);
	clusterized.convertTo(clusterized,CV_32FC3,1.0/255.0);
	frame.convertTo(frame,CV_32FC3,1.0/255.0);
	Mat result1;
	vector<Mat> ch;
	split(frame, ch);
	processLayer(ch[0],ch[0]);
	processLayer(ch[1],ch[1]);
	processLayer(ch[2],ch[2]);
	merge(ch,result1);
	result1=(0.5*frame-0.9*result1+0.3*clusterized)*2.0;
        namedWindow("result1",WINDOW_AUTOSIZE);
	imshow("result1",result1);
        //cout<<result1;
        imwrite("D:\finalresult.jpg",result1);
	waitKey(0);
	//destroyAllWindows();
	return 0;
}