基于OpenCV的车牌识别（一整套）

#include "carID_Detection.h" void RgbConvToGray(const Mat& inputImage,Mat & outpuImage) //g = 0.3R+0.59G+0.11B { outpuImage = Mat(inputImage.rows ,inputImage.cols ,CV_8UC1); for (int i = 0 ;i<inputImage.rows ;++ i) { uchar *ptrGray = outpuImage.ptr<uchar>(i); const Vec3b * ptrRgb = inputImage.ptr<Vec3b>(i); for (int j = 0 ;j<inputImage.cols ;++ j) { ptrGray[j] = 0.3*ptrRgb[j][2]+0.59*ptrRgb[j][1]+0.11*ptrRgb[j][0]; } } } void posDetect_closeImg(Mat &inputImage , vector <RotatedRect> & rects ) //初步找到候选区域 rects { Mat img_canny; Canny(inputImage, img_canny, 150, 220); Mat img_threshold; threshold(img_canny , img_threshold,0,255 , CV_THRESH_OTSU+CV_THRESH_BINARY); //otsu算法自动获得阈值 Mat element = getStructuringElement(MORPH_RECT ,Size(15 ,3)); //闭形态学的结构元素 morphologyEx(img_threshold ,img_threshold,CV_MOP_CLOSE,element); //形态学处理 //寻找车牌区域的轮廓 vector< vector <Point> > contours; findContours(img_threshold ,contours,CV_RETR_EXTERNAL, CV_CHAIN_APPROX_NONE);//只检测外轮廓 //对候选的轮廓进行进一步筛选 vector< vector <Point> > ::iterator itc = contours.begin(); while( itc != contours.end()) { RotatedRect mr = minAreaRect(Mat( *itc )); //返回每个轮廓的最小有界矩形区域 if(!verifySizes_closeImg(mr)) //判断矩形轮廓是否符合要求 { itc = contours.erase(itc); } else { rects.push_back(mr); ++itc; } } } bool verifySizes_closeImg(const RotatedRect & candidate) { float error = 0.4; const float aspect = 44/14; //长宽比 int min = 100*aspect*100; //最小区域 int max = 180*aspect*180; //最大区域 float rmin = aspect - aspect*error; //考虑误差后的最小长宽比 float rmax = aspect + aspect*error; //考虑误差后的最大长宽比 int area = candidate.size.height * candidate.size.width; float r = (float)candidate.size.width/(float)candidate.size.height; if(r <1) r = 1/r; if( (area < min || area > max) || (r< rmin || r > rmax) ) return false; else return true; } void posDetect(Mat &inputImage , vector <RotatedRect> & rects ) //初步找到候选区域 rects { Mat img_sobel; Sobel(inputImage , img_sobel , CV_8U, 1,0,3,1,0); Mat img_threshold; threshold(img_sobel , img_threshold,0,255 , CV_THRESH_OTSU+CV_THRESH_BINARY); //otsu算法自动获得阈值 Mat element = getStructuringElement(MORPH_RECT ,Size(15 ,3)); //闭形态学的结构元素 morphologyEx(img_threshold ,img_threshold,CV_MOP_CLOSE,element); //寻找车牌区域的轮廓 vector< vector <Point> > contours; findContours(img_threshold ,contours,CV_RETR_EXTERNAL, CV_CHAIN_APPROX_NONE);//只检测外轮廓 //对候选的轮廓进行进一步筛选 vector< vector <Point> > ::iterator itc = contours.begin(); while( itc != contours.end()) { RotatedRect mr = minAreaRect(Mat( *itc )); //返回每个轮廓的最小有界矩形区域 if(!verifySizes(mr)) //判断矩形轮廓是否符合要求 { itc = contours.erase(itc); } else { rects.push_back(mr); ++itc; } } } bool verifySizes(const RotatedRect & candidate) { float error = 0.4; const float aspect = 44/14; //长宽比 int min = 20*aspect*20; //最小区域 int max = 180*aspect*180; //最大区域 float rmin = aspect - 2*aspect*error; //考虑误差后的最小长宽比 float rmax = aspect + 2*aspect*error; //考虑误差后的最大长宽比 int area = candidate.size.height * candidate.size.width; float r = (float)candidate.size.width/(float)candidate.size.height; if(r <1) r = 1/r; if( (area < min || area > max) || (r< rmin || r > rmax) ) //满足该条件才认为该candidate为车牌区域 return false; else return true; } void optimPosDetect(vector <RotatedRect> & rects_sImg , vector <RotatedRect> & rects_grayImg, vector <RotatedRect> & rects_closeImg,vector <RotatedRect> & rects_optimal ) { for (int i=0;i<rects_sImg.size() ;++ i) { for (int j=0;j<rects_grayImg.size() ; ++j) { if (calOverlap(rects_sImg[i].boundingRect() , rects_grayImg[j].boundingRect()) > 0.2) { if(rects_sImg[i].boundingRect().width * rects_sImg[i].boundingRect().height >= rects_grayImg[j].boundingRect().width * rects_grayImg[j].boundingRect().height) rects_optimal.push_back(rects_sImg[i]); else rects_optimal.push_back(rects_grayImg[j]); } } } if (rects_closeImg.size()<2 ) //只考虑1个，为了速度 { for (int i =0;i < rects_optimal.size();++ i ) for (int j =0;j < rects_closeImg.size();++ j) { if (( calOverlap(rects_optimal[i].boundingRect() , rects_closeImg[j].boundingRect()) < 0.2 && calOverlap(rects_optimal[i].boundingRect() , rects_closeImg[j].boundingRect()) > 0.05)) { rects_optimal.push_back(rects_closeImg[j]); } } } } float calOverlap(const Rect& box1,const Rect& box2) { if (box1.x > box2.x+box2.width) { return 0.0; } if (box1.y > box2.y+box2.height) { return 0.0; } if (box1.x+box1.width < box2.x) { return 0.0; } if (box1.y+box1.height < box2.y) { return 0.0; } float colInt = min(box1.x+box1.width,box2.x+box2.width) - max(box1.x, box2.x); float rowInt = min(box1.y+box1.height,box2.y+box2.height) - max(box1.y,box2.y); float intersection = colInt * rowInt; float area1 = box1.width*box1.height; float area2 = box2.width*box2.height; return intersection / (area1 + area2 - intersection); } void normalPosArea(Mat &intputImg, vector<RotatedRect> &rects_optimal, vector <Mat>& output_area ) { float r,angle; for (int i = 0 ;i< rects_optimal.size() ; ++i) { //旋转区域 angle = rects_optimal[i].angle; r = (float)rects_optimal[i].size.width / (float) (float)rects_optimal[i].size.height; if(r<1) angle = 90 + angle; Mat rotmat = getRotationMatrix2D(rects_optimal[i].center , angle,1);//获得变形矩阵对象 Mat img_rotated; warpAffine(intputImg ,img_rotated,rotmat, intputImg.size(),CV_INTER_CUBIC); //裁剪图像 Size rect_size = rects_optimal[i].size; if(r<1) swap(rect_size.width, rect_size.height); Mat img_crop; getRectSubPix(img_rotated ,rect_size,rects_optimal[i].center , img_crop ); //用光照直方图调整所有裁剪得到的图像，使具有相同宽度和高度，适用于训练和分类 Mat resultResized; resultResized.create(33,144,CV_8UC3); resize(img_crop , resultResized,resultResized.size() , 0,0,INTER_CUBIC); Mat grayResult; RgbConvToGray(resultResized ,grayResult); //blur(grayResult ,grayResult,Size(3,3)); equalizeHist(grayResult,grayResult); output_area.push_back(grayResult); } } void svm_train(CvSVM & svmClassifier) { FileStorage fs; fs.open("SVM.xml" , FileStorage::READ); Mat SVM_TrainningData; Mat SVM_Classes; fs["TrainingData"] >>SVM_TrainningData; fs["classes"] >>SVM_Classes; CvSVMParams SVM_params; SVM_params.kernel_type = CvSVM::LINEAR; svmClassifier.train(SVM_TrainningData,SVM_Classes ,Mat(),Mat(),SVM_params); //SVM训练模型 fs.release(); } void char_segment(const Mat & inputImg,vector <Mat>& dst_mat)//得到20*20的标准字符分割图像 { Mat img_threshold; threshold(inputImg ,img_threshold , 180,255 ,CV_THRESH_BINARY ); Mat img_contours; img_threshold.copyTo(img_contours); vector < vector <Point> > contours; findContours(img_contours ,contours,CV_RETR_EXTERNAL,CV_CHAIN_APPROX_NONE); vector< vector <Point> > ::iterator itc = contours.begin(); vector<RotatedRect> char_rects; while( itc != contours.end()) { RotatedRect minArea = minAreaRect(Mat( *itc )); //返回每个轮廓的最小有界矩形区域 Point2f vertices[4]; minArea.points(vertices); if(!char_verifySizes(minArea)) //判断矩形轮廓是否符合要求 { itc = contours.erase(itc); } else { ++itc; char_rects.push_back(minArea); } } char_sort(char_rects); //对字符排序 vector <Mat> char_mat; for (int i = 0; i<char_rects.size() ;++i ) { char_mat.push_back( Mat(img_threshold,char_rects[i].boundingRect())) ; } Mat train_mat(2,