OpenCV学习笔记（十七）模板匹配

来源：互联网发布：淘宝查号网站编辑：程序博客网时间：2024/05/01 19:06

我的目的就是选取图像中的指示灯，识别那种功能的指示灯亮了，进而知道那种功能打开了。

模板匹配：

模板匹配是傻瓜似的识别，从一副图像中寻找与模板图像相似部分的技术。模板匹配由matchTemplate()函数完成。

介绍两个函数，matchTemplate()和minMaxLoc()函数：

void matchTemplate(InputArray image, InputArray temp, OutputArray result, int method)

image – Image where the search is running. It must be 8-bit or 32-bit floating-point.
templ – Searched template. It must be not greater than the source image and have the same data type.
result – Map of comparison results. It must be single-channel 32-bit floating-point. If image is $W \times H$ and templ is $w \times h$ , thenresult is $(W-w+1) \times (H-h+1)$ .
method – Parameter specifying the comparison method (see below).

method：CV_TM_SQDIFF_NORMED，CV_TM_CCORR，CV_TM_CCORR_NORMED，CV_TM_CCOEFF，CV_TM_CCOEFF_NORMED

查找数组中的全局最小值和最大值：minMaxLoc()函数

void minMaxLoc(InputArray src, double* minVal, double* maxVal=0, Point* minLoc=0, Point* maxLoc=0, InputArray mask=noArray())

src – Source single-channel array.
minVal – Pointer to the returned minimum value. NULL is used if not required.
maxVal – Pointer to the returned maximum value. NULL is used if not required.
minLoc – Pointer to the returned minimum location (in 2D case). NULL is used if not required.
maxLoc – Pointer to the returned maximum location (in 2D case). NULL is used if not required.
mask – Optional mask used to select a sub-array.

程序实现：

#include <opencv2/highgui/highgui.hpp>#include <opencv2/imgproc/imgproc.hpp>using namespace cv;#define WINDOW_NAME1 "【原始图片】"Mat g_srcImage, g_templateImage, g_resultImage;int g_nMatchMethod=3;//int g_nMaxTrackbarNum = 5;void on_Matching(int, void*);int main(){g_srcImage = imread("D:\\Projects\\1.jpg");g_templateImage = imread("D:\\Projects\\11.jpg");namedWindow(WINDOW_NAME1, CV_WINDOW_AUTOSIZE);/*createTrackbar("方法", WINDOW_NAME1, &g_nMatchMethod, g_nMaxTrackbarNum, on_Matching);*/on_Matching(0, 0);waitKey(0);return 0;}void on_Matching(int, void*){Mat srcImage;g_srcImage.copyTo(srcImage);//初始化用于结果输出的矩阵int resultImage_cols = g_srcImage.cols - g_templateImage.cols + 1;int resultImage_rows = g_srcImage.rows - g_templateImage.rows + 1;g_resultImage.create(resultImage_cols, resultImage_rows, CV_32FC1);//进行匹配和标准化matchTemplate(g_srcImage, g_templateImage, g_resultImage, g_nMatchMethod);normalize(g_resultImage, g_resultImage, 0, 1, NORM_MINMAX, -1, Mat());//通过哦函数minMaxLoc定位最匹配位置double minValue, maxValue;Point minLocation, maxLocation;Point matchLocation;minMaxLoc(g_resultImage, &minValue, &maxValue, &minLocation, &maxLocation, Mat());//对于方法SQDIFF和SQDIFF_NORMED，越小的数值有着更高的匹配结果，而其余的方法，数值越大匹配效果越好if (g_nMatchMethod == CV_TM_CCORR_NORMED){maxLocation.x = maxLocation.x + 48;maxLocation.y = maxLocation.y + 2;matchLocation = maxLocation;}//绘制出矩形，并显示最终结果rectangle(srcImage, matchLocation, Point(matchLocation.x + g_templateImage.cols - 10, matchLocation.y + g_templateImage.rows - 10),Scalar(255, 255, 255), 1, 8, 0);imshow(WINDOW_NAME1, srcImage);}

模板图像：

原图像：

效果图：

使用模板匹配是选取了就是合位的指示灯，需要的不断的调整，实用性差，选取不准确，又难以多个选取。

0 0