显示图片的例子:
#include <cv.h>
#include <highgui.h>
using namespace std;
int main()
{
IplImage * test;
test = cvLoadImage("D:\\cvImg\\1024.jpg");
cvNamedWindow("test_demo", 1);
cvShowImage("test_demo", test);
cvWaitKey(0);
cvDestroyWindow("test_demo");
cvReleaseImage(&test);
return 0;
}
图像相似度ORB算法
#define _CRT_SECURE_NO_DEPRECATE
#include <stdio.h>
#include <string.h>
#include <time.h>
#include <io.h>
#include <stdlib.h>
#include <direct.h>
#include <vector>
#include <string>
#include <iostream>
#include <iterator>
#include <core/core.hpp>
#include <features2d/features2d.hpp>
#include <highgui/highgui.hpp>
#include <nonfree/nonfree.hpp>
#include <features2d/features2d.hpp>
#include <legacy/legacy.hpp>
using namespace std;
using namespace cv;
//OpenCV图像相似度ORB算法(图像特征比对) http://jingyan.baidu.com/article/6f2f55a185efa1b5b93e6c1d.html
int getORB(char * imagePatha, char * imagePathb) {
double t;
t = getTickCount();
Mat img_1 = imread(imagePatha);
Mat img_2 = imread(imagePathb);
if (!img_1.data || !img_2.data) {
cout << "error reading images " << endl; return -1;
}
ORB orb;
vector<KeyPoint> keyPoints_1, keyPoints_2;
Mat descriptors_1, descriptors_2;
orb(img_1, Mat(), keyPoints_1, descriptors_1);
orb(img_2, Mat(), keyPoints_2, descriptors_2);
BruteForceMatcher<HammingLUT> matcher;
vector<DMatch> matches;
matcher.match(descriptors_1, descriptors_2, matches);
double max_dist = 0; double min_dist = 100;
for (int i = 0; i < descriptors_1.rows; i++) {
double dist = matches[i].distance;
if (dist < min_dist) min_dist = dist;
if (dist > max_dist) max_dist = dist;
}
printf("-- Max dist : %f \n", max_dist);
printf("-- Min dist : %f \n", min_dist);
std::vector< DMatch > good_matches;
for (int i = 0; i < descriptors_1.rows; i++) {
if (matches[i].distance < 0.6*max_dist) {
good_matches.push_back(matches[i]);
}
}
t = getTickCount() - t;
t = t * 1000 / getTickFrequency();
Mat img_matches;
drawMatches(img_1, keyPoints_1, img_2, keyPoints_2, good_matches, img_matches,
Scalar::all(-1), Scalar::all(-1), vector<char>(),
DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
imshow("Match", img_matches);
printf("%f ms\n", t);
cvWaitKey(0);
return 0;
}
int main(int argc, char* argv[])
{
//getORB("D:\\cvImg\\1023.jpg", "D:\\cvImg\\1025.jpg");
getORB("D:\\cvImg\\1023.jpg", "D:\\cvImg\\1026.jpg");
cout << "ok" << endl;
return 0;
}
Google图像对比基本算法
<pre name="code" class="cpp">#include <cv.h>
#include <highgui.h>
#include <stdlib.h>
//http://www.sharejs.com/codes/cpp/8012 Google图像对比基本算法
//计算图像感知hash值。详情看:http://blog.csdn.net/lhfslhfs/article/details/9157845
int64 CalcImagePerceptualHashKey(const IplImage* pImage)
{
IplImage* pTheImage8X8 = cvCreateImage(cvSize(8, 8), pImage->depth, pImage->nChannels);
IplImage* pGrayscaleImage = cvCreateImage(cvSize(8, 8), 8, 1);
cvResize(pImage, pTheImage8X8, CV_INTER_AREA);
cvConvertImage(pTheImage8X8, pGrayscaleImage);
cvReleaseImage(&pTheImage8X8);
//计算平均值
float fElementMean = 0;
for (int y = 0; y < 8; ++y)
{
for (int x = 0; x < 8; ++x)
{
unsigned char& cElem = *(unsigned char*)(pGrayscaleImage->imageData + x + y * pGrayscaleImage->widthStep);
cElem = (unsigned char)(cElem / (float)255 * 64);
fElementMean += cElem;
}
}
fElementMean /= 64;
unsigned char cElementKey = 0;
int64 key = 0;
unsigned char* pKeyPtr = (unsigned char*)&key;
for (int y = 0; y < 8; ++y)
{
for (int x = 0; x < 8; ++x)
{
if (fElementMean > *(unsigned char*)(pGrayscaleImage->imageData + x + y * pGrayscaleImage->widthStep))
{
//小于平均值即为0。
cElementKey <<= 1;
}
else
{
//否则即为1
cElementKey <<= 1;
cElementKey |= 1;
}
}
pKeyPtr[y] = cElementKey;
}
cvReleaseImage(&pGrayscaleImage);
return key;
}
//比较2个key的相似度,结果以1为最相似,0为不相似。
float CompareImageKeySimilarity(int64 key1, int64 key2)
{
int64 keyResult = key1 ^ key2;
int nOneCount = 0;
int i = 64;
while (i--)
{
if ((keyResult & 1) == 1)
nOneCount++;
keyResult >>= 1;
}
printf("nOneCount = %dn", nOneCount);
return nOneCount == 0 ? 1 : (64 - nOneCount) / (float)64;
}
int main(int argc, char* argv[])
{
IplImage* pSrc1 = cvLoadImage("D:\\cvImg\\1023.jpg");
IplImage* pSrc2 = cvLoadImage("D:\\cvImg\\1026.jpg");
int64 key1 = CalcImagePerceptualHashKey(pSrc1);
int64 key2 = CalcImagePerceptualHashKey(pSrc2);
printf("\nkey1=0x%llX,key2 = 0x%llX, Similarity = %.2fn", key1, key2, CompareImageKeySimilarity(key1, key2));
return 0;
}
模板匹配:
<pre name="code" class="cpp">/**
* @file MatchTemplate_Demo.cpp
* @brief Sample code to use the function MatchTemplate
* @author OpenCV team
*/
//#include <opencv2/imgcodecs.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
/// Global Variables
Mat img; Mat templ; Mat result;
const char* image_window = "Source Image";
const char* result_window = "Result window";
int match_method;
int max_Trackbar = 5;
/// Function Headers
void MatchingMethod(int, void*);
/**
* @function main
*/
int main(int, char** argv)
{
/// Load image and template
img = imread(argv[1], 1);
templ = imread(argv[2], 1);
/// Create windows
namedWindow(image_window, WINDOW_AUTOSIZE);
namedWindow(result_window, WINDOW_AUTOSIZE);
/// Create Trackbar
const char* trackbar_label = "Method: \n 0: SQDIFF \n 1: SQDIFF NORMED \n 2: TM CCORR \n 3: TM CCORR NORMED \n 4: TM COEFF \n 5: TM COEFF NORMED";
createTrackbar(trackbar_label, image_window, &match_method, max_Trackbar, MatchingMethod);
MatchingMethod(0, 0);
waitKey(0);
return 0;
}
/**
* @function MatchingMethod
* @brief Trackbar callback
*/
void MatchingMethod(int, void*)
{
/// Source image to display
Mat img_display;
img.copyTo(img_display);
/// Create the result matrix
int result_cols = img.cols - templ.cols + 1;
int result_rows = img.rows - templ.rows + 1;
result.create(result_rows, result_cols, CV_32FC1);
/// Do the Matching and Normalize
matchTemplate(img, templ, result, match_method);
normalize(result, result, 0, 1, NORM_MINMAX, -1, Mat());
/// Localizing the best match with minMaxLoc
double minVal; double maxVal; Point minLoc; Point maxLoc;
Point matchLoc;
minMaxLoc(result, &minVal, &maxVal, &minLoc, &maxLoc, Mat());
/// For SQDIFF and SQDIFF_NORMED, the best matches are lower values. For all the other methods, the higher the better
if (match_method == TM_SQDIFF || match_method == TM_SQDIFF_NORMED)
{
matchLoc = minLoc;
}
else
{
matchLoc = maxLoc;
}
/// Show me what you got
rectangle(img_display, matchLoc, Point(matchLoc.x + templ.cols, matchLoc.y + templ.rows), Scalar::all(0), 2, 8, 0);
rectangle(result, matchLoc, Point(matchLoc.x + templ.cols, matchLoc.y + templ.rows), Scalar::all(0), 2, 8, 0);
imshow(image_window, img_display);
imshow(result_window, result);
return;
}
相似性对比
#include <opencv\cv.h>
#include <opencv\highgui.h>
#include <opencv\cxcore.h>
#include <stdlib.h>
#include <stdio.h>
/*
*函数功能:获取输入图像 的轮廓
*
*输入:
*srcIn : 单通道图像
*
*返回:
*CvSeq* : 存储轮廓信息
*
*/
CvSeq* getImageContour(IplImage* srcIn) {
IplImage* src;
src = cvCreateImage(cvGetSize(srcIn), 8, 1);
//拷贝图像
cvCopy(srcIn, src);
//创建空间
CvMemStorage* mem = cvCreateMemStorage(0);
//结构体 (mem和seq属于同一个地址<当释放的时候只要释放一个就行了>)
CvSeq* seq;
if (!mem) {
printf("mem is null");
}
//二值化图像
cvThreshold(src, src, 100, 255, 0);
//计算图像轮廓 计算后的轮廓信息不能释放 在后面需要用到
cvFindContours(src, mem, &seq, sizeof(CvContour), CV_RETR_CCOMP);
//释放图像空间
cvReleaseImage(&src);
//返回轮廓信息
return seq;
}
int main(int argc, char* argv[]) {
//加载图像1
IplImage* src1 = cvLoadImage("D:\\cvImg\\1022.jpg", CV_LOAD_IMAGE_GRAYSCALE);
//获取图像1的轮廓
CvSeq* contour1;
contour1 = getImageContour(src1);
//加载图像2
IplImage* src2 = cvLoadImage("D:\\cvImg\\1025.jpg", CV_LOAD_IMAGE_GRAYSCALE);
//获取图像2的轮廓
CvSeq* contour2;
contour2 = getImageContour(src2);
//进行比对 -- 比较这两个轮廓所对应的HU矩的距离 有多远
double result;
//cvMatchShapes函数参数(轮廓1,轮廓2,方法)
//计算第一个轮廓的普通矩和中心距 , 然后计算这个矩形的HU矩(HU距的7个数值保存在ma的数组里)
//的哥个轮廓同上(HU距保存在mb中)
//然后比较这两个HU距的相似性
//方法参数有3个 参数分别是1,2,3 三种计算方法
result = cvMatchShapes(contour1, contour2, 1);
//输出结果 结果越小 相似度越高
printf("result is %f \n", result);
//释放轮廓存储空间
cvReleaseMemStorage(&contour1->storage);
cvReleaseMemStorage(&contour2->storage);
//释放图像空间
cvReleaseImage(&src1);
cvReleaseImage(&src2);
return 0;
}
附上相关链接:
http://jingyan.baidu.com/article/75ab0bcbee4b47d6864db2fc.html