BJUT数字图像处理作业

一、

1) 将宽为2n的正方形图像，用FFT算法从空域变换到频域，并用频域图像的模来进行显示。

2) 使图像能量中心，对应到几何中心，并用频域图像的模来进行显示。

3)将频域图象，通过FFT逆变换到空域，并显示。

#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
using namespace cv;
using namespace std;

int main()
{

	//以灰度模式读取原始图像并显示
	Mat srcImage = imread("lena.png", 0);
	if (srcImage.empty())
	{
		cout << "打开图像失败！" << endl;
		return -1;
	}
	imshow("原始图像", srcImage);

	//将输入图像延扩到最佳的尺寸，边界用0补充
	int m = getOptimalDFTSize(srcImage.rows);
	int n = getOptimalDFTSize(srcImage.cols);
	//将添加的像素初始化为0.
	Mat padded;
	copyMakeBorder(srcImage, padded, 0, m - srcImage.rows, 0, n - srcImage.cols, BORDER_CONSTANT, Scalar::all(0));

	//为傅立叶变换的结果(实部和虚部)分配存储空间。
	//将planes数组组合合并成一个多通道的数组complexI
	Mat planes[] = { Mat_<float>(padded), Mat::zeros(padded.size(), CV_32F) };
	Mat complexI;
	merge(planes, 2, complexI);

	//进行就地离散傅里叶变换
	dft(complexI, complexI);

	//将复数转换为幅值，即=> log(1 + sqrt(Re(DFT(I))^2 + Im(DFT(I))^2))
	split(complexI, planes); // 将多通道数组complexI分离成几个单通道数组，planes[0] = Re(DFT(I), planes[1] = Im(DFT(I))
	magnitude(planes[0], planes[1], planes[0]);// planes[0] = magnitude
	Mat magnitudeImage = planes[0];

	//进行对数尺度(logarithmic scale)缩放
	magnitudeImage += Scalar::all(1);
	log(magnitudeImage, magnitudeImage);//求自然对数

	//剪切和重分布幅度图象限
	//若有奇数行或奇数列，进行频谱裁剪
	magnitudeImage = magnitudeImage(Rect(0, 0, magnitudeImage.cols & -2, magnitudeImage.rows & -2));
	//重新排列傅立叶图像中的象限，使得原点位于图像中心
	int cx = magnitudeImage.cols / 2;
	int cy = magnitudeImage.rows / 2;
	Mat q0(magnitudeImage, Rect(0, 0, cx, cy));   // ROI区域的左上
	Mat q1(magnitudeImage, Rect(cx, 0, cx, cy));  // ROI区域的右上
	Mat q2(magnitudeImage, Rect(0, cy, cx, cy));  // ROI区域的左下
	Mat q3(magnitudeImage, Rect(cx, cy, cx, cy)); // ROI区域的右下
	//交换象限（左上与右下进行交换）
	Mat tmp;
	q0.copyTo(tmp);
	q3.copyTo(q0);
	tmp.copyTo(q3);
	//交换象限（右上与左下进行交换）
	q1.copyTo(tmp);
	q2.copyTo(q1);
	tmp.copyTo(q2);

	//归一化，用0到1之间的浮点值将矩阵变换为可视的图像格式
	normalize(magnitudeImage, magnitudeImage, 0, 1, CV_MINMAX);

	//显示效果图
	imshow("频域", magnitudeImage);

	//频域-->空域
	Mat inversed;
	dft(complexI, inversed, DFT_INVERSE | DFT_REAL_OUTPUT);
	normalize(inversed, inversed, 0, 1, CV_MINMAX);
	imshow("空域", inversed);

	waitKey();

	return 0;
}

二、

对于下面这幅图像，请问可以通过那些图像增强的手段，达到改善视觉效果的目的？请显示处理结果，并附简要处理流程说明。

#include <opencv2/opencv.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
using namespace std;
using namespace cv;
int ContrastValue; //对比度值
int BrightValue;  //亮度值
Mat src, dst;
//改变图像对比度和亮度值的回调函数
static void ContrastAndBright(int, void *)
{
	//创建窗口
	namedWindow("【原始图窗口】", WINDOW_AUTOSIZE);
	for (int y = 0; y < src.rows; y++)
	{
		for (int x = 0; x < src.cols; x++)
		{
			for (int c = 0; c < 3; c++)
			{
				dst.at<Vec3b>(y, x)[c] = saturate_cast<uchar>((ContrastValue * 0.01)*(src.at<Vec3b>(y, x)[c]) + BrightValue);
			}
		}
	}
	//显示图像
	imshow("【原始图窗口】", src);
	imshow("【效果图窗口】", dst);
}

int main(int argc, char *argv[])
{
	//打开图像
	src = imread("two.png");
	if (src.empty())
	{
		cout << "打开图像失败！" << endl;
		return -1;
	}
	//中值滤波去噪
	medianBlur(src, src, 3);
	dst = Mat::zeros(src.size(), src.type());
	//设定对比度和亮度的初值
	ContrastValue = 80;
	BrightValue = 80;
	//创建窗口
	namedWindow("【效果图窗口】", WINDOW_AUTOSIZE);
	//创建轨迹条
	createTrackbar("对比度：", "【效果图窗口】", &ContrastValue, 300, ContrastAndBright);
	createTrackbar("亮   度：", "【效果图窗口】", &BrightValue, 200, ContrastAndBright);
	//调用回调函数
	ContrastAndBright(ContrastValue, 0);
	ContrastAndBright(BrightValue, 0);
	//等待用户按键，起到暂停的作用
	waitKey();
	return 0;
}

三、

对于下面这幅图像，编程实现染色体计数，并附简要处理流程说明。

#include <opencv2/opencv.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
#include <vector>
using namespace std;
using namespace cv;
int main(int argc, char **argv)
{
	Mat gray, src, dst;
	//打开图像
	src = imread("image.png");
	if (src.empty())
	{
		cout << "打开图像失败！" << endl;
		return -1;
	}
	cout << "rows = " << src.rows << endl;
	cout << "cols = " << src.cols << endl;
	//转换为灰度图
	cvtColor(src, gray, CV_BGR2GRAY);
	//中值滤波
	medianBlur(gray, gray, 7);
	//图像二值化
	threshold(gray, dst, 170, 255, THRESH_BINARY);
	//腐蚀,默认内核3*3
	erode(dst, dst, Mat());
	//erode(dst, dst, Mat());

	Mat canny_output;
	vector<vector<Point> > contours;
	vector<Vec4i> hierarchy;
	//画轮廓线
	Canny(dst, canny_output, 100, 100 * 2, 3);
	imwrite("data.png", dst);

	//检测轮廓
	findContours(dst, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
	cout << "一共检测到染色体数目：" << contours.size() - 1 << endl;
	/*
	for (int i = 0; i < contours.size(); i++)
	{
		for (int j = 0; j < contours[i].size(); j++)
		{
			cout << contours[i][j] << " ";
		}
		cout << ";" << endl;
	}
	*/

	//显示图片
	imshow("src", src);
	imshow("canny_output", canny_output);

	//将图片保存到文件
	imwrite("dst.png", canny_output);
	//等待用户输入
	waitKey();
	return 0;
}

//高斯滤波
//GaussianBlur(gray, gray, Size(5, 5), 0, 0);

//双边滤波
//bilateralFilter(gray, gray, 5, 10.0, 2.0);

//中值滤波
//medianBlur(gray, gray, 3);

四、

对MNIST手写数字数据库（可在网上搜索下载），编程实现来提取其链码。

#include <opencv2/opencv.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
#include <vector>
#include <string>
#include <fstream>

using namespace std;
using namespace cv;

//格式转换
int ReverseInt(int i)
{
	unsigned char ch1, ch2, ch3, ch4;
	ch1 = i & 255;
	ch2 = (i >> 8) & 255;
	ch3 = (i >> 16) & 255;
	ch4 = (i >> 24) & 255;
	return((int)ch1 << 24) + ((int)ch2 << 16) + ((int)ch3 << 8) + ch4;
}

/**
*  将Mnist数据库读取到OpenCV::Mat格式中
*  格式：
*  magic number
*  number of images
*  rows
*  cols
*  a very very long vector contains all digits
*/
void read_Mnist(string filename, vector<Mat> &vec)
{
	ifstream file(filename, ios::binary);
	if (file.is_open())
	{
		int magic_number = 0;
		int number_of_images = 0;
		int n_rows = 0;
		int n_cols = 0;
		file.read((char*)&magic_number, sizeof(magic_number));
		magic_number = ReverseInt(magic_number);

		file.read((char*)&number_of_images, sizeof(number_of_images));
		number_of_images = ReverseInt(number_of_images);

		file.read((char*)&n_rows, sizeof(n_rows));
		n_rows = ReverseInt(n_rows);

		file.read((char*)&n_cols, sizeof(n_cols));
		n_cols = ReverseInt(n_cols);

		for (int i = 0; i < number_of_images; ++i)
		{
			cv::Mat tp = Mat::zeros(n_rows, n_cols, CV_8UC1);
			for (int r = 0; r < n_rows; ++r)
			{
				for (int c = 0; c < n_cols; ++c)
				{
					unsigned char temp = 0;
					file.read((char*)&temp, sizeof(temp));
					tp.at<uchar>(r, c) = (int)temp;
				}
			}
			vec.push_back(tp);
		}
	}//if
}

int main(int argc, char **argv)
{
	int count = 1;
	//存储Mnist字库
	vector<Mat> vec;
	//将Mnist字库读取到vector中
	read_Mnist("t10k-images.idx3-ubyte", vec);
	cout << "共含有：" << vec.size() << "幅图片" << endl;

	for (auto iter = vec.begin(); iter != vec.end(); iter++)
	{
		cout << "第" << count++ << "幅图片..." << endl;
		//显示Mnist字库
		imshow("Mnist", *iter);
		vector<vector<Point> > contours;

		//读取轮廓
		findContours(*iter, contours, CV_RETR_EXTERNAL, CV_CHAIN_CODE);
		//输出链码
		for (int i = 0; i < contours.size(); i++)
		{
			for (int j = 0; j < contours[i].size(); j++)
			{
				cout << contours[i][j];
			}
			cout << endl;
		}
		contours.clear();
		waitKey(1000);
	}
	waitKey();
	return 0;
}

详细说明：

http://download.csdn.net/detail/lgh1992314/9733718