二 opencv核心模块
5.1 离散傅里叶变换
傅立叶变换会将图像分解成其正弦和余弦分量。换句话说,它将图像从空间域转换到频率域。这个想法是,任何函数都可以用无限的正弦和余弦函数之和精确地近似。傅立叶变换是一种方法。数学上,二维图像的傅里叶变换为:
5.2 代码解析
#include "opencv2/core.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/highgui.hpp"
#include <iostream>
using namespace cv;
using namespace std;
static void help(char ** argv)
{
cout << endl
<< "This program demonstrated the use of the discrete Fourier transform (DFT). " << endl
<< "The dft of an image is taken and it's power spectrum is displayed." << endl << endl
<< "Usage:" << endl
<< argv[0] << " [image_name -- default lena.jpg]" << endl << endl;
}
int main(int argc, char ** argv)
{
help(argv);
const char* filename = argc >=2 ? argv[1] : "lena.jpg";
Mat I = imread( samples::findFile( filename ), IMREAD_GRAYSCALE);
if( I.empty()){
cout << "Error opening image" << endl;
return EXIT_FAILURE;
}
Mat padded; //expand input image to optimal size
int m = getOptimalDFTSize( I.rows );
int n = getOptimalDFTSize( I.cols ); // on the border add zero values
copyMakeBorder(I, padded, 0, m - I.rows, 0, n - I.cols, BORDER_CONSTANT, Scalar::all(0));
Mat planes[] = {Mat_<float>(padded), Mat::zeros(padded.size(), CV_32F)};
Mat complexI;
merge(planes, 2, complexI); // Add to the expanded another plane with zeros
dft(complexI, complexI); // this way the result may fit in the source matrix
// compute the magnitude and switch to logarithmic scale
// => log(1 + sqrt(Re(DFT(I))^2 + Im(DFT(I))^2))
split(complexI, planes); // planes[0] = Re(DFT(I), planes[1] = Im(DFT(I))
magnitude(planes[0], planes[1], planes[0]);// planes[0] = magnitude
Mat magI = planes[0];
magI += Scalar::all(1); // switch to logarithmic scale
log(magI, magI);
// crop the spectrum, if it has an odd number of rows or columns
magI = magI(Rect(0, 0, magI.cols & -2, magI.rows & -2));
// rearrange the quadrants of Fourier image so that the origin is at the image center
int cx = magI.cols/2;
int cy = magI.rows/2;
Mat q0(magI, Rect(0, 0, cx, cy)); // Top-Left - Create a ROI per quadrant
Mat q1(magI, Rect(cx, 0, cx, cy)); // Top-Right
Mat q2(magI, Rect(0, cy, cx, cy)); // Bottom-Left
Mat q3(magI, Rect(cx, cy, cx, cy)); // Bottom-Right
Mat tmp; // swap quadrants (Top-Left with Bottom-Right)
q0.copyTo(tmp);
q3.copyTo(q0);
tmp.copyTo(q3);
q1.copyTo(tmp); // swap quadrant (Top-Right with Bottom-Left)
q2.copyTo(q1);
tmp.copyTo(q2);
normalize(magI, magI, 0, 1, NORM_MINMAX); // Transform the matrix with float values into a
// viewable image form (float between values 0 and 1).
imshow("Input Image" , I ); // Show the result
imshow("spectrum magnitude", magI);
waitKey();
return EXIT_SUCCESS;
}
- 放大图像至最佳尺寸
DFT的性能取决于图像大小。对于数字二,三和五的倍数的图像,它通常是转换的。因此,要获得最佳性能,通常最好将边框值填充到图像上并具有这样的效果。特征的尺寸。所述getOptimalDFTSize()返回该最佳尺寸和我们可以使用copyMakeBorder()函数以展开的图像(在预先估计与零初始化)的边界:
Mat padded; //expand input image to optimal size
int m = getOptimalDFTSize( I.rows );
int n = getOptimalDFTSize( I.cols ); // on the border add zero values
copyMakeBorder(I, padded, 0, m - I.rows, 0, n - I.cols, BORDER_CONSTANT, Scalar::all(0));
- 兼顾复杂和真实的价值
傅立叶变换的结果很复杂。这意味着对于每个图像值,结果是两个图像值(每个分量一个)。而且,频域范围比其空间对应范围大幅度。因此,我们通常至少以浮点格式存储这些内容。因此,我们将输入图像转换尺寸类型,并使用另一个通道将其扩展以容纳复杂值:
Mat planes[] = {Mat_<float>(padded), Mat::zeros(padded.size(), CV_32F)};
Mat complexI;
merge(planes, 2, complexI); // Add to the expanded another plane with zeros
- 进行离散傅立叶变换
dft(complexI, complexI); // this way the result may fit in the source matrix
- 将真实和复杂的值转换为幅度
公式:
split(complexI, planes); // planes[0] = Re(DFT(I), planes[1] = Im(DFT(I))
magnitude(planes[0], planes[1], planes[0]);// planes[0] = magnitude
Mat magI = planes[0];
- 切换到对数刻度
公式: M1=log(1+M)
magI += Scalar::all(1); // switch to logarithmic scale
log(magI, magI);
- 裁剪和重新划分
// crop the spectrum, if it has an odd number of rows or columns
magI = magI(Rect(0, 0, magI.cols & -2, magI.rows & -2));
// rearrange the quadrants of Fourier image so that the origin is at the image center
int cx = magI.cols/2;
int cy = magI.rows/2;
Mat q0(magI, Rect(0, 0, cx, cy)); // Top-Left - Create a ROI per quadrant
Mat q1(magI, Rect(cx, 0, cx, cy)); // Top-Right
Mat q2(magI, Rect(0, cy, cx, cy)); // Bottom-Left
Mat q3(magI, Rect(cx, cy, cx, cy)); // Bottom-Right
Mat tmp; // swap quadrants (Top-Left with Bottom-Right)
q0.copyTo(tmp);
q3.copyTo(q0);
tmp.copyTo(q3);
q1.copyTo(tmp); // swap quadrant (Top-Right with Bottom-Left)
q2.copyTo(q1);
tmp.copyTo(q2);
- 归一化
出于可视化目的再次进行此操作。现在我们有了幅度,但是这仍然超出了我们的图像显示范围(从零到一)。我们使用cv::normalize()函数将值标准化到该范围。
normalize(magI, magI, 0, 1, NORM_MINMAX); // Transform the matrix with float values into a
// viewable image form (float between values 0 and 1).