前言

学习了很长一段时间了，需要沉淀下，而最好的办法就是做一个东西来应用学习的东西，同时也是一个学习的过程。

PS：这篇小文是毕业之前和同学做的一个小项目，所以写的比较匆忙，代码也是直接粘贴的，基于qt开发的C++代码，不能保证没有错误，请慎重。不希望对你产生误导，有任何问题可以联系我，一起探讨下。最后，我现在已经没有搞嵌入式方面的开发了。

概述    

OpenCV的全称是：Open Source Computer Vision Library。OpenCV是一个基于（开源）发行的跨平台计算机视觉库，可以运行在Linux、Windows和Mac OS操作系统上。它轻量级而且高效——由一系列 C 函数和少量 C++ 类构成，同时提供了Python、Ruby、MATLAB等语言的接口，实现了图像处理和计算机视觉方面的很多通用算法。

来自百度的解释，之所以选择opencv是因为：首先向学习一个新的东西来看看自己的学习接受能力，然后是感觉opencv很酷，处理图片真实说一不二的（你可以理解为处理图片很方便）。

车牌识别系统重点在于车牌的识别，还有后台的处理。要使它成为一个系统，缺一不可。

大致上分为三个部分：信息采集和传输，接收图片并识别客户端请求，信息的存储和查询

1.信息采集和传输

这里我们采用的是 网上买的小摄像头+网上的开源项目mjpg-stream

对于mjpg-stream的使用，网上已经有很多博客了，你可以找到很多。

mjpg-stream 不仅能调用摄像头拍摄照片还可以作为服务器发送图片数据，所以我这里直接使用它作为服务器发送给我自己写的客户端数据。

2.接收图片并进行图片识别和显示

这里就需要用到opencv来进行处理了。

大致上车牌识别分为：车牌提取，字符提取，字符识别

车牌提取：需要调用opencv里面图片处理的几个函数接口：

灰度处理-》竖向边缘检测（因为车牌大部分竖向的）-》二值化处理-》形态学处理-》车牌截取

  1.  string read_plate(string path)
  2.  {
  3.       /*加载图片*/
  4.       const char* imagename = path.c_str();
  5.       IplImage * img = cvLoadImage(imagename);
  6.       if(!img)
  7.       {
  8.              exit();
  9.       }
  10.  
  11.       if( !img->imageData ) // 检查是否正确载入图像
  12.             exit();
  13.  
  14.       cvNamedWindow("image", CV_WINDOW_AUTOSIZE); //创建窗口
  15.      // cvShowImage("image", img); //显示图像
  16.      /*灰度化处理*/
  17.       IplImage* img1 = cvCreateImage(cvGetSize(img), IPL_DEPTH_8U, );//创建目标图像
  18.       cvCvtColor(img,img1,CV_BGR2GRAY);//cvCvtColor(src,des,CV_BGR2GRAY)
  19.       cvNamedWindow("gray_image",CV_WINDOW_AUTOSIZE);//创建显示目标的窗口
  20.  
  21.      // cvShowImage("gray_image",img1);//显示灰度图像
  22.      /*滤波处理*/
  23.       IplImage* temp = cvCreateImage(cvGetSize(img1), IPL_DEPTH_8U, );//创建目标图像
  24.       cvSmooth(img1,temp,CV_GAUSSIAN,,);//高斯模糊
  25.      // cvShowImage("guolv_image",temp);//显示过滤图
  26.  
  27.       /*竖向边缘检测  竖向只是参数的改变*/
  28.       IplImage * sobel=cvCreateImage(cvGetSize(temp),IPL_DEPTH_16S,);
  29.       IplImage *sobelimg=cvCreateImage(cvGetSize(temp),IPL_DEPTH_8U,);
  30.       cvSobel(temp,sobel,,,);
  31.       cvConvertScaleAbs(sobel,sobelimg, 0.00390625,);
  32.      // cvShowImage("灰度图像Sobel变换",sobelimg);
  33.  
  34.      /*二值化处理*/
  35.       IplImage *two=cvCreateImage(cvGetSize(temp),IPL_DEPTH_8U,);
  36.       cvThreshold(sobelimg, two, , , CV_THRESH_BINARY| CV_THRESH_OTSU);
  37.      // cvShowImage("two",two);
  38.  
  39.       /*形态学处理  腐蚀膨胀*/
  40.       IplImage *closeimg=cvCreateImage(cvGetSize(temp),IPL_DEPTH_8U,);
  41.       IplConvKernel* kernal=cvCreateStructuringElementEx(,, , , CV_SHAPE_RECT);
  42.       cvDilate(two, closeimg, kernal, );
  43.       cvErode(closeimg, closeimg, kernal, );
  44.       cvDilate(closeimg, closeimg, kernal, );
  45.       kernal = cvCreateStructuringElementEx(, , , , CV_SHAPE_RECT);
  46.       cvErode(closeimg, closeimg, kernal, );
  47.       cvDilate(closeimg, closeimg, kernal, );
  48.       //cvShowImage("closeimg",closeimg);
  49.  
  50.       /*筛选最大的那块矩形*/
  51.       IplImage* copy = cvCloneImage(closeimg);
  52.       IplImage* dst  =   cvCloneImage(img);
  53.       CvMemStorage* storage = cvCreateMemStorage();
  54.       CvSeq* contours;
  55.       CvRect rect,max;
  56.       int count=;
  57.       double wide=,height=;
  58.        count= cvFindContours (copy, storage, &contours, sizeof(CvContour), CV_RETR_LIST, CV_CHAIN_APPROX_NONE);
  59.        for (;contours != NULL; contours = contours->h_next)
  60.        {
  61.             rect = cvBoundingRect(contours);
  62.             if(rect.width > (rect.height*))
  63.             {
  64.                 if(rect.height>height && rect.width>wide)
  65.                 {
  66.                      max = rect;
  67.                      height = rect.height;
  68.                      wide = rect.width;
  69.  
  70.                 }
  71.             }
  72.        }
  73.        cvSetImageROI(dst,cvRect(max.x+,max.y+,max.width-,max.height-));
  74.        cvShowImage("choose",dst);     
  75.  
  76.  }

plate shot

代码中对截取车牌进行了操作

下面是字符的识别：字符识别有很多方法，但是都是算法的，我研究的不是很深，选取了最简单的一种，自己做字符库，然后比对。

  1.  //车牌识别
  2.  #include "char.h"
  3.  
  4.  //中文字模   注意绝对路径= =
  5.  const char *mb_ku_zw[] = {
  6.      "/home/panhao/QtProject/MyANPR/char_img/zw1.bmp","/home/panhao/QtProject/MyANPR/char_img/zw2.bmp","/home/panhao/QtProject/MyANPR/char_img/zw3.bmp",
  7.      "/home/panhao/QtProject/MyANPR/char_img/zw4.bmp","/home/panhao/QtProject/MyANPR/char_img/zw5.bmp",
  8.      "/home/panhao/QtProject/MyANPR/char_img/zw6.bmp","/home/panhao/QtProject/MyANPR/char_img/zw7.bmp","/home/panhao/QtProject/MyANPR/char_img/zw8.bmp",
  9.      "/home/panhao/QtProject/MyANPR/char_img/zw9.bmp","/home/panhao/QtProject/MyANPR/char_img/zw10.bmp","/home/panhao/QtProject/MyANPR/char_img/zw11.bmp",
  10.      "/home/panhao/QtProject/MyANPR/char_img/zw12.bmp","/home/panhao/QtProject/MyANPR/char_img/zw13.bmp","/home/panhao/QtProject/MyANPR/char_img/zw14.bmp",
  11.      "/home/panhao/QtProject/MyANPR/char_img/zw15.bmp","/home/panhao/QtProject/MyANPR/char_img/zw16.bmp","/home/panhao/QtProject/MyANPR/char_img/zw17.bmp",
  12.      "/home/panhao/QtProject/MyANPR/char_img/zw18.bmp","/home/panhao/QtProject/MyANPR/char_img/zw19.bmp","/home/panhao/QtProject/MyANPR/char_img/zw20.bmp",
  13.      "/home/panhao/QtProject/MyANPR/char_img/zw21.bmp","/home/panhao/QtProject/MyANPR/char_img/zw22.bmp","/home/panhao/QtProject/MyANPR/char_img/zw23.bmp",
  14.      "/home/panhao/QtProject/MyANPR/char_img/zw24.bmp","/home/panhao/QtProject/MyANPR/char_img/zw25.bmp","/home/panhao/QtProject/MyANPR/char_img/zw26.bmp",
  15.      "/home/panhao/QtProject/MyANPR/char_img/zw27.bmp","/home/panhao/QtProject/MyANPR/char_img/zw28.bmp","/home/panhao/QtProject/MyANPR/char_img/zw29.bmp",
  16.      "/home/panhao/QtProject/MyANPR/char_img/zw30.bmp","/home/panhao/QtProject/MyANPR/char_img/zw31.bmp",
  17.  };
  18.  const char *mb_ku_zf[] ={
  19.      "/home/panhao/QtProject/MyANPR/char_img/A.bmp","/home/panhao/QtProject/MyANPR/char_img/B.bmp",
  20.      "/home/panhao/QtProject/MyANPR/char_img/C.bmp","/home/panhao/QtProject/MyANPR/char_img/D.bmp",
  21.      "/home/panhao/QtProject/MyANPR/char_img/E.bmp","/home/panhao/QtProject/MyANPR/char_img/F.bmp",
  22.      "/home/panhao/QtProject/MyANPR/char_img/G.bmp","/home/panhao/QtProject/MyANPR/char_img/H.bmp",
  23.      "/home/panhao/QtProject/MyANPR/char_img/J.bmp","/home/panhao/QtProject/MyANPR/char_img/K.bmp",
  24.      "/home/panhao/QtProject/MyANPR/char_img/L.bmp","/home/panhao/QtProject/MyANPR/char_img/M.bmp",
  25.      "/home/panhao/QtProject/MyANPR/char_img/N.bmp","/home/panhao/QtProject/MyANPR/char_img/P.bmp",
  26.      "/home/panhao/QtProject/MyANPR/char_img/Q.bmp","/home/panhao/QtProject/MyANPR/char_img/R.bmp",
  27.      "/home/panhao/QtProject/MyANPR/char_img/S.bmp","/home/panhao/QtProject/MyANPR/char_img/T.bmp",
  28.      "/home/panhao/QtProject/MyANPR/char_img/U.bmp","/home/panhao/QtProject/MyANPR/char_img/V.bmp",
  29.      "/home/panhao/QtProject/MyANPR/char_img/W.bmp","/home/panhao/QtProject/MyANPR/char_img/X.bmp",
  30.      "/home/panhao/QtProject/MyANPR/char_img/Y.bmp","/home/panhao/QtProject/MyANPR/char_img/Z.bmp",
  31.  };
  32.  const char *mb_ku_sz[] ={
  33.      "/home/panhao/QtProject/MyANPR/char_img/0.bmp","/home/panhao/QtProject/MyANPR/char_img/1.bmp","/home/panhao/QtProject/MyANPR/char_img/2.bmp",
  34.      "/home/panhao/QtProject/MyANPR/char_img/3.bmp","/home/panhao/QtProject/MyANPR/char_img/4.bmp","/home/panhao/QtProject/MyANPR/char_img/5.bmp",
  35.      "/home/panhao/QtProject/MyANPR/char_img/6.bmp","/home/panhao/QtProject/MyANPR/char_img/7.bmp","/home/panhao/QtProject/MyANPR/char_img/8.bmp",
  36.      "/home/panhao/QtProject/MyANPR/char_img/9.bmp",
  37.  };
  38.  const char *mb_ku_sf[] = {
  39.      "/home/panhao/QtProject/MyANPR/char_img/0.bmp","/home/panhao/QtProject/MyANPR/char_img/1.bmp","/home/panhao/QtProject/MyANPR/char_img/2.bmp",
  40.      "/home/panhao/QtProject/MyANPR/char_img/3.bmp","/home/panhao/QtProject/MyANPR/char_img/4.bmp","/home/panhao/QtProject/MyANPR/char_img/5.bmp",
  41.      "/home/panhao/QtProject/MyANPR/char_img/6.bmp","/home/panhao/QtProject/MyANPR/char_img/7.bmp","/home/panhao/QtProject/MyANPR/char_img/8.bmp",
  42.      "/home/panhao/QtProject/MyANPR/char_img/9.bmp","/home/panhao/QtProject/MyANPR/char_img/A.bmp","/home/panhao/QtProject/MyANPR/char_img/B.bmp",
  43.      "/home/panhao/QtProject/MyANPR/char_img/C.bmp","/home/panhao/QtProject/MyANPR/char_img/D.bmp","/home/panhao/QtProject/MyANPR/char_img/E.bmp",
  44.      "/home/panhao/QtProject/MyANPR/char_img/F.bmp","/home/panhao/QtProject/MyANPR/char_img/G.bmp","/home/panhao/QtProject/MyANPR/char_img/H.bmp",
  45.      "/home/panhao/QtProject/MyANPR/char_img/J.bmp","/home/panhao/QtProject/MyANPR/char_img/K.bmp","/home/panhao/QtProject/MyANPR/char_img/L.bmp",
  46.      "/home/panhao/QtProject/MyANPR/char_img/M.bmp","/home/panhao/QtProject/MyANPR/char_img/N.bmp","/home/panhao/QtProject/MyANPR/char_img/P.bmp",
  47.      "/home/panhao/QtProject/MyANPR/char_img/Q.bmp","/home/panhao/QtProject/MyANPR/char_img/R.bmp","/home/panhao/QtProject/MyANPR/char_img/S.bmp",
  48.      "/home/panhao/QtProject/MyANPR/char_img/T.bmp","/home/panhao/QtProject/MyANPR/char_img/U.bmp","/home/panhao/QtProject/MyANPR/char_img/V.bmp",
  49.      "/home/panhao/QtProject/MyANPR/char_img/W.bmp","/home/panhao/QtProject/MyANPR/char_img/X.bmp","/home/panhao/QtProject/MyANPR/char_img/Y.bmp",
  50.      "/home/panhao/QtProject/MyANPR/char_img/Z.bmp",
  51.  
  52.  };
  53.  
  54.  string shibie(char *imgpath)
  55.  {
  56.      IplImage *pSrcImage = cvLoadImage(imgpath, );       //定位后车牌路径
  57.      IplImage *pGrayImage = NULL;
  58.      IplImage *pBinaryImage = NULL;
  59.      IplImage *ty_cpimg = NULL;
  60.      // 转为灰度图
  61.      pGrayImage =  cvCreateImage(cvGetSize(pSrcImage), IPL_DEPTH_8U, );
  62.      cvCvtColor(pSrcImage, pGrayImage, CV_BGR2GRAY);
  63.      // 创建二值图
  64.      pBinaryImage = cvCreateImage(cvGetSize(pGrayImage), IPL_DEPTH_8U, );
  65.      //转为二值图，自适二值化CV_THRESH_OTSU
  66.      cvThreshold(pGrayImage, pBinaryImage, , , CV_THRESH_BINARY | CV_THRESH_OTSU);
  67.  
  68.      cvNamedWindow("input",);
  69.      cvShowImage("input",pBinaryImage);
  70.  
  71.      //识别铆钉
  72.      const int height_md_yz = pBinaryImage->height / ;        //y轴方向的阈值
  73.      const int width_md_yz  = pBinaryImage->width;              //x轴方向的阈值
  74.      IplImage* cyp = cvCloneImage( pBinaryImage );
  75.      int width_md = ;
  76.      int height_md  = ;
  77.      int count_bd = ;
  78.      uchar count_bd_str[width_md_yz];
  79.      for(count_bd = ; count_bd < width_md_yz; count_bd++)
  80.          count_bd_str[count_bd] = ;
  81.      uchar *pt = (uchar *)cyp->imageData;
  82.      const uchar step = cyp->widthStep;
  83.  
  84.      //扫描白点并记录
  85.      for(width_md  =  ; width_md < width_md_yz; width_md++)
  86.      {
  87.          for(height_md =  ; height_md < height_md_yz; height_md++)
  88.          {
  89.              if(pt[height_md*step + width_md])
  90.                  count_bd_str[width_md]++;
  91.          }
  92.      }
  93.  
  94.      int width_bf   = ;
  95.      int width_ls   = ;
  96.      for(width_md  =  ; width_md < width_md_yz; width_md++)
  97.      {
  98.          if(count_bd_str[width_md] > height_md_yz/)
  99.              if(width_md < width_md_yz-)
  100.                  if(count_bd_str[++width_md]> height_md_yz/)
  101.                  {
  102.                      if(!width_bf)
  103.                      {
  104.                          if(width_md > width_md_yz*0.2)
  105.                              width_bf = width_md;
  106.                      }
  107.                      else if(width_md - width_bf > width_md_yz/)
  108.                      {
  109.                          if(width_md > width_md_yz*0.6)
  110.                              width_ls = width_md;
  111.                      }
  112.                  }
  113.      }
  114.      //如果判断是柳钉则使用柳钉计算比例定位
  115.      if(width_md_yz*0.4 < (width_ls - width_bf) && (width_ls - width_bf) < width_md_yz*0.6)
  116.      {
  117.          float img_bl = ((float)(width_ls - width_bf))/;
  118.          int width_left_new = width_bf - (int)(img_bl*);
  119.          int width_right_new = width_ls + (int)(img_bl*);
  120.          if(width_left_new<)width_left_new=;
  121.          if(width_right_new>pBinaryImage->width)width_right_new=pBinaryImage->width;
  122.          int height_top_new = ;
  123.          int height_down_new = pBinaryImage->height;
  124.          const uchar height_yz_x = pBinaryImage->height/;
  125.          uchar count_bd_x_str[height_yz_x];
  126.          for(count_bd = ; count_bd < height_yz_x; count_bd++)             //数组清零
  127.              count_bd_x_str[count_bd] = ;
  128.          for(int height_ydw = ; height_ydw < height_yz_x; height_ydw++)
  129.          {
  130.              for(width_md  =  ; width_md < width_md_yz; width_md++)
  131.              {
  132.                  if(pt[height_ydw*step + width_md])
  133.                      count_bd_x_str[height_ydw]++;
  134.              }
  135.          }
  136.          for(int height_ydw = ; height_ydw < height_yz_x; height_ydw++)
  137.          {
  138.              if(count_bd_x_str[height_ydw] < (int)(pBinaryImage->width*/))    //切割条件->白点个数 阈值
  139.                  height_top_new = height_ydw;
  140.          }
  141.  
  142.          for(count_bd = ; count_bd < height_yz_x; count_bd++)
  143.              count_bd_x_str[count_bd] = ;
  144.          for(int height_ydw = ; height_ydw < height_yz_x; height_ydw++)
  145.          {
  146.              for(width_md  =  ; width_md < width_md_yz; width_md++)
  147.              {
  148.                  if(pt[(pBinaryImage->height - height_ydw)*step + width_md])
  149.                      count_bd_x_str[height_ydw]++;
  150.              }
  151.          }
  152.          for(int height_ydw = ; height_ydw < height_yz_x; height_ydw++)
  153.          {
  154.              if(count_bd_x_str[height_ydw] < (int)(pBinaryImage->width*/))
  155.                  height_down_new = pBinaryImage->height - height_ydw;
  156.          }
  157.  
  158.          IplImage* cyp_ptx = cvCloneImage( pBinaryImage );
  159.          CvRect ptx;
  160.          ptx.x = width_left_new;
  161.          ptx.y = height_top_new;
  162.          ptx.height = height_down_new - height_top_new;
  163.          ptx.width  = width_right_new - width_left_new;
  164.          cvSetImageROI(cyp_ptx, ptx);
  165.          cvSaveImage("/home/panhao/QtProject/MyANPR/img/cyp_ptx.jpg", cyp_ptx);
  166.          ty_cpimg = cvCloneImage(cyp_ptx);
  167.          cvResetImageROI(cyp_ptx);
  168.      }
  169.      //如果无法识别铆钉，那就先投影切割后按比例切割字符
  170.      else
  171.      {
  172.          int width_left_new_y = ;
  173.          int width_right_new_y = pBinaryImage->width;
  174.          int height_top_new_y = ;
  175.          int height_down_new_y = pBinaryImage->height;
  176.          const uchar height_yz_y = pBinaryImage->height/;
  177.          const uchar width_yz_y = pBinaryImage->width/;    //阈值 请修改
  178.          uchar width_bd_ptr_y[width_yz_y];
  179.          uchar height_bd_ptr_y[height_yz_y];
  180.          for(count_bd = ; count_bd < width_yz_y; count_bd++)
  181.              width_bd_ptr_y[count_bd] = ;
  182.          for(count_bd = ; count_bd < height_yz_y; count_bd++)
  183.              height_bd_ptr_y[count_bd] = ;
  184.          for(int width_yd_y = ; width_yd_y < width_yz_y; width_yd_y++)
  185.              for(int height_yd_y = ; height_yd_y < pBinaryImage->height; height_yd_y++)
  186.              {
  187.                  if(pt[height_yd_y*step + width_yd_y])
  188.                      width_bd_ptr_y[width_yd_y]++;
  189.              }
  190.          for(int width_yd_y = ; width_yd_y < width_yz_y; width_yd_y++)
  191.          {
  192.              if(width_bd_ptr_y[width_yd_y] < (int)(pBinaryImage->height*/))
  193.                  width_left_new_y = width_yd_y;
  194.  //            int x = width_bd_ptr_y[width_yd_y];
  195.          }
  196.          for(count_bd = ; count_bd < width_yz_y; count_bd++)
  197.              width_bd_ptr_y[count_bd] = ;
  198.          for(int width_yd_y = ; width_yd_y < width_yz_y; width_yd_y++)
  199.              for(int height_yd_y = ; height_yd_y < pBinaryImage->height; height_yd_y++)
  200.              {
  201.                  if(pt[height_yd_y*step + pBinaryImage->width - width_yd_y])
  202.                      width_bd_ptr_y[width_yd_y]++;
  203.              }
  204.          for(int width_yd_y = ; width_yd_y < width_yz_y; width_yd_y++)
  205.          {
  206.              if(width_bd_ptr_y[width_yd_y] < (int)(pBinaryImage->height*/))
  207.                  width_right_new_y =pBinaryImage->width - width_yd_y;
  208.          }
  209.  
  210.          for(int height_yd_y = ; height_yd_y < height_yz_y; height_yd_y++)
  211.              for(int width_yd_y = ; width_yd_y < pBinaryImage->width; width_yd_y++)
  212.              {
  213.                  if(pt[height_yd_y*step + width_yd_y])
  214.                      height_bd_ptr_y[height_yd_y]++;
  215.              }
  216.          for(int height_yd_y = ; height_yd_y < height_yz_y; height_yd_y++)
  217.          {
  218.              if(height_bd_ptr_y[height_yd_y] < (int)(pBinaryImage->width*/))
  219.                  height_top_new_y = height_yd_y;
  220.          }
  221.          for(count_bd = ; count_bd < height_yz_y; count_bd++)
  222.              height_bd_ptr_y[count_bd] = ;
  223.          for(int height_yd_y = ; height_yd_y < height_yz_y; height_yd_y++)
  224.              for(int width_yd_y = ; width_yd_y < pBinaryImage->width; width_yd_y++)
  225.              {
  226.                  if(pt[(pBinaryImage->height - height_yd_y)*step + width_yd_y])
  227.                      height_bd_ptr_y[height_yd_y]++;
  228.              }
  229.          for(int height_yd_y = ; height_yd_y < height_yz_y; height_yd_y++)
  230.          {
  231.              if(height_bd_ptr_y[height_yd_y] < (int)(pBinaryImage->width*/))    //上下切
  232.                  height_down_new_y = pBinaryImage->height - height_yd_y;
  233.          }
  234.          IplImage* cyp_ptx = cvCloneImage( pBinaryImage );
  235.          CvRect ptx;
  236.          ptx.x = width_left_new_y;
  237.          ptx.y = height_top_new_y;
  238.          ptx.height = height_down_new_y - height_top_new_y;
  239.          ptx.width  = width_right_new_y - width_left_new_y;
  240.          cvSetImageROI(cyp_ptx, ptx);
  241.          cvSaveImage("/home/panhao/QtProject/MyANPR/img/cyp_ptx_y.jpg", cyp_ptx);        //保存查看投影切割的结果
  242.          ty_cpimg = cvCloneImage(cyp_ptx);
  243.          cvResetImageROI(cyp_ptx);
  244.      }
  245.  
  246.      //图片统一尺寸180x40  开始字符切割(字符切割使用的是最最简单的按比例切割，效果不是很理想，如果要高识别率，需要对字符进行上下左右的投影切割，然后再进行归一化，这样可以提高识别率)
  247.      IplImage *img_ty = NULL;
  248.      CvSize dst_cvsize;
  249.      dst_cvsize.height = ;
  250.      dst_cvsize.width = ;
  251.      img_ty = cvCreateImage(dst_cvsize, ty_cpimg->depth, ty_cpimg->nChannels);
  252.      cvResize(ty_cpimg, img_ty, CV_INTER_LINEAR);         //二线性插值法会出现灰度
  253.      ty_cpimg = cvCloneImage( img_ty );
  254.      cvThreshold(ty_cpimg, img_ty, , , CV_THRESH_BINARY | CV_THRESH_OTSU);   //再次二值化
  255.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/img_ty.jpg", img_ty);
  256.      dst_cvsize.height = ;
  257.      dst_cvsize.width = ;
  258.      IplImage *pic1 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  259.      IplImage *pic2 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  260.      IplImage *pic3 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  261.      IplImage *pic4 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  262.      IplImage *pic5 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  263.      IplImage *pic6 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  264.      IplImage *pic7 = cvCreateImage(dst_cvsize, img_ty->depth, img_ty->nChannels);
  265.      IplImage* copy_zf = NULL;
  266.      copy_zf = cvCloneImage( img_ty );
  267.      CvRect ptx;
  268.      ptx.x = ;
  269.      ptx.y = ;
  270.      ptx.height = ;
  271.      ptx.width  = ;
  272.      cvSetImageROI(copy_zf, ptx);
  273.      cvCopy(copy_zf, pic1);
  274.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf1.jpg", pic1);                        //注意绝对路径 出错请debug
  275.      pic1 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf1.jpg", );                    //注意 这两句必须要，否则后面结果就不对
  276.  
  277.      copy_zf = cvCloneImage( img_ty );
  278.      ptx.x = +;
  279.      ptx.y = ;
  280.      ptx.height = ;
  281.      ptx.width  = ;
  282.      cvSetImageROI(copy_zf, ptx);
  283.      cvCopy(copy_zf, pic2);
  284.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf2.jpg", pic2);
  285.      pic2 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf2.jpg", );
  286.  
  287.      copy_zf = cvCloneImage( img_ty );
  288.      ptx.x = +++;
  289.      ptx.y = ;
  290.      ptx.height = ;
  291.      ptx.width  = ;
  292.      cvSetImageROI(copy_zf, ptx);
  293.      cvCopy(copy_zf, pic3);
  294.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf3.jpg", pic3);
  295.      pic3 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf3.jpg", );
  296.  
  297.      copy_zf = cvCloneImage( img_ty );
  298.      ptx.x = +++++;
  299.      ptx.y = ;
  300.      ptx.height = ;
  301.      ptx.width  = ;
  302.      cvSetImageROI(copy_zf, ptx);
  303.      cvCopy(copy_zf, pic4);
  304.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf4.jpg", pic4);
  305.      pic4 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf4.jpg", );
  306.  
  307.      copy_zf = cvCloneImage( img_ty );
  308.      ptx.x = +++++++;
  309.      ptx.y = ;
  310.      ptx.height = ;
  311.      ptx.width  = ;
  312.      cvSetImageROI(copy_zf, ptx);
  313.      cvCopy(copy_zf, pic5);
  314.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf5.jpg", pic5);
  315.      pic5 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf5.jpg", );
  316.  
  317.      copy_zf = cvCloneImage( img_ty );
  318.      ptx.x = +++++++++;
  319.      ptx.y = ;
  320.      ptx.height = ;
  321.      ptx.width  = ;
  322.      cvSetImageROI(copy_zf, ptx);
  323.      cvCopy(copy_zf, pic6);
  324.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf6.jpg", pic6);
  325.      pic6 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf6.jpg", );
  326.  
  327.      copy_zf = cvCloneImage( img_ty );
  328.      ptx.x = +++++++++++;
  329.      ptx.y = ;
  330.      ptx.height = ;
  331.      ptx.width  = ;
  332.      cvSetImageROI(copy_zf, ptx);
  333.      cvCopy(copy_zf, pic7);
  334.      cvSaveImage("/home/panhao/QtProject/MyANPR/img/copy_zf7.jpg", pic7);
  335.      pic7 = cvLoadImage("/home/panhao/QtProject/MyANPR/img/copy_zf7.jpg", );
  336.  
  337.      //字符识别(使用模版逐点比对式，相似点*100/总点数=成功率)
  338.      string wz_1 = db_successlv_1(pic1);                     //车牌第一个字符   以下以此类推   做返回值string中若有中文会有乱码
  339.      string wz_2 = db_successlv_2(pic2);
  340.      string wz_3 = db_successlv_3(pic3);
  341.      string wz_4 = db_successlv_3(pic4);
  342.      string wz_5 = db_successlv_4_7(pic5);
  343.      string wz_6 = db_successlv_4_7(pic6);
  344.      string wz_7 = db_successlv_4_7(pic7);
  345.      string finish = wz_1 + wz_2 + wz_3 + wz_4 + wz_5 + wz_6 + wz_7;    //最后结果
  346.      //cout << "finish:"<<finish << endl;
  347.      //printf("endl\n");
  348.  
  349.      cvReleaseImage(&pic1);
  350.      cvReleaseImage(&pic2);
  351.      cvReleaseImage(&pic3);
  352.      cvReleaseImage(&pic4);
  353.      cvReleaseImage(&pic5);
  354.      cvReleaseImage(&pic6);
  355.      cvReleaseImage(&pic7);
  356.      cvReleaseImage(&copy_zf);
  357.      cvReleaseImage(&img_ty);
  358.      cvReleaseImage(&ty_cpimg);
  359.      cvReleaseImage(&pSrcImage);
  360.      cvReleaseImage(&pGrayImage);
  361.      cvReleaseImage(&pBinaryImage);
  362.      cvReleaseImage(&cyp);
  363.  
  364.      return finish;
  365.  }
  366.  
  367.  int sb_count_bd(IplImage *img)
  368.  {
  369.      int count = ;
  370.      uchar *pt = (uchar *)img->imageData;
  371.      const uchar step = img->widthStep;
  372.      for(int w = ; w < img->width; w++)
  373.          for(int h = ; h < img->height; h++)
  374.              if(pt[h*step + w])
  375.                  count += w*h;
  376.      return count;
  377.  }
  378.  
  379.  string db_successlv_3(IplImage *cs)
  380.  {
  381.      uchar *pt_cs = (uchar *)cs->imageData;
  382.      uchar i = ;
  383.      uchar max = ;
  384.      uchar max_backup = ;
  385.      uchar zf  = ;
  386.      string fhz = "\0";
  387.      for(i = ; i < ; i++)
  388.      {
  389.          IplImage *mb = cvLoadImage(mb_ku_sf[i], );
  390.          uchar cgl = ;
  391.  
  392.          int cg_count = ;
  393.          int bd_count = ;
  394.          uchar *pt_mb = (uchar *)mb->imageData;
  395.          const uchar step_cs = cs->widthStep;
  396.          const uchar step_mb = mb->widthStep;
  397.          for(int w = ; w < cs->width; w++)
  398.              for(int h = ; h < cs->height; h++)
  399.              {
  400.                  if((pt_cs[h*step_cs + w] == pt_mb[h*step_mb + w]))
  401.                      cg_count++;
  402.                  if(pt_mb[h*step_mb + w])
  403.                      bd_count++;
  404.              }
  405.          cvReleaseImage(&mb);
  406.              cgl = (uchar)(((float)cg_count/(cs->height*cs->width))*);
  407.          max = max<cgl? cgl : max;
  408.          if(max != max_backup)
  409.              zf = i;
  410.          max_backup = max;
  411.      }
  412.      switch(zf)
  413.      {
  414.      case : fhz = "";break; case : fhz = "";break; case : fhz = "";break; case : fhz = "";break;
  415.      case : fhz = "";break; case : fhz = "";break; case : fhz = "";break; case : fhz = "";break;
  416.      case : fhz = "";break; case : fhz = "";break; case : fhz = "A";break; case : fhz = "B";break;
  417.      case : fhz = "C";break; case : fhz = "D";break; case : fhz = "E";break; case : fhz = "F";break;
  418.      case : fhz = "G";break; case : fhz = "H";break; case : fhz = "J";break; case : fhz = "K";break;
  419.      case : fhz = "L";break; case : fhz = "M";break; case : fhz = "N";break; case : fhz = "P";break;
  420.      case : fhz = "Q";break; case : fhz = "R";break; case : fhz = "S";break; case : fhz = "T";break;
  421.      case : fhz = "U";break; case : fhz = "V";break; case : fhz = "W";break; case : fhz = "X";break;
  422.      case : fhz = "Y";break; case : fhz = "Z";break;
  423.      }
  424.      return (fhz);
  425.  }
  426.  
  427.  string db_successlv_1(IplImage *cs)
  428.  {
  429.      string fhz = "\0";
  430.      uchar *pt_cs = (uchar *)cs->imageData;
  431.      uchar i = ;
  432.      uchar max = ;
  433.      uchar max_backup = ;
  434.      uchar zf  = ;
  435.      for(i = ; i < ; i++)
  436.      {
  437.          IplImage *mb = cvLoadImage(mb_ku_zw[i], );
  438.          uchar cgl = ;
  439.  
  440.          int cg_count = ;
  441.          int bd_count = ;
  442.          uchar *pt_mb = (uchar *)mb->imageData;
  443.          const uchar step_cs = cs->widthStep;
  444.          const uchar step_mb = mb->widthStep;
  445.          for(int w = ; w < cs->width; w++)
  446.              for(int h = ; h < cs->height; h++)
  447.              {
  448.                  if((pt_cs[h*step_cs + w] == pt_mb[h*step_mb + w]))
  449.                      cg_count++;
  450.                  if(pt_mb[h*step_mb + w])
  451.                      bd_count++;
  452.              }
  453.          cvReleaseImage(&mb);
  454.              cgl = (uchar)(((float)cg_count/(cs->height*cs->width))*);
  455.          max = max<cgl? cgl : max;
  456.          if(max != max_backup)
  457.              zf = i;
  458.          max_backup = max;
  459.          //printf("zf=%d\n",(int)zf);
  460.      }
  461.  
  462.      switch(zf)
  463.      {
  464.      case : fhz = "藏";break; case : fhz = "川";break; case : fhz = "鄂";break; case : fhz = "甘";break;
  465.      case : fhz = "赣";break; case : fhz = "贵";break; case : fhz = "桂";break; case : fhz = "黑";break;
  466.      case : fhz = "沪";break; case : fhz = "吉";break; case : fhz = "冀";break; case : fhz = "津";break;
  467.      case : fhz = "晋";break; case : fhz = "京";break; case : fhz = "辽";break; case : fhz = "鲁";break;
  468.      case : fhz = "蒙";break; case : fhz = "闽";break; case : fhz = "宁";break; case : fhz = "青";break;
  469.      case : fhz = "琼";break; case : fhz = "陕";break; case : fhz = "苏";break; case : fhz = "皖";break;
  470.      case : fhz = "湘";break; case : fhz = "新";break; case : fhz = "渝";break; case : fhz = "豫";break;
  471.      case : fhz = "粤";break; case : fhz = "云";break; case : fhz = "浙";break;
  472.      }
  473.      //cout << "return"<<endl;
  474.      return (fhz);
  475.  }
  476.  
  477.  string db_successlv_2(IplImage *cs)
  478.  {
  479.      string fhz = "\0";
  480.      uchar *pt_cs = (uchar *)cs->imageData;
  481.      uchar i = ;
  482.      uchar max = ;
  483.      uchar max_backup = ;
  484.      uchar zf  = ;
  485.      for(i = ; i < ; i++)
  486.      {
  487.          IplImage *mb = cvLoadImage(mb_ku_zf[i], );
  488.          uchar cgl = ;
  489.  
  490.          int cg_count = ;
  491.          int bd_count = ;
  492.          uchar *pt_mb = (uchar *)mb->imageData;
  493.          const uchar step_cs = cs->widthStep;
  494.          const uchar step_mb = mb->widthStep;
  495.          for(int w = ; w < cs->width; w++)
  496.              for(int h = ; h < cs->height; h++)
  497.              {
  498.                  if((pt_cs[h*step_cs + w] == pt_mb[h*step_mb + w]))
  499.                      cg_count++;
  500.                  if(pt_mb[h*step_mb + w])
  501.                      bd_count++;
  502.              }
  503.          cvReleaseImage(&mb);
  504.              cgl = (uchar)(((float)cg_count/(cs->height*cs->width))*);
  505.          max = max<cgl? cgl : max;
  506.          if(max != max_backup)
  507.              zf = i;
  508.          max_backup = max;
  509.          //printf("wz_2  i=%d,zf=%d,max=%d\n",(int)i,(int)zf,(int)max);
  510.      }
  511.      switch(zf)
  512.      {
  513.      case : fhz = "A";break; case : fhz = "B";break;
  514.      case : fhz = "C";break; case : fhz = "D";break; case : fhz = "E";break; case : fhz = "F";break;
  515.      case : fhz = "G";break; case : fhz = "H";break; case : fhz = "J";break; case : fhz = "K";break;
  516.      case : fhz = "L";break; case : fhz = "M";break; case : fhz = "N";break; case : fhz = "P";break;
  517.      case : fhz = "Q";break; case : fhz = "R";break; case : fhz = "S";break; case : fhz = "T";break;
  518.      case : fhz = "U";break; case : fhz = "V";break; case : fhz = "W";break; case : fhz = "X";break;
  519.      case : fhz = "Y";break; case : fhz = "Z";break;
  520.      }
  521.      return (fhz);
  522.  }
  523.  
  524.  string db_successlv_4_7(IplImage *cs)
  525.  {
  526.      string fhz = "\0";
  527.      uchar *pt_cs = (uchar *)cs->imageData;
  528.      uchar i = ;
  529.      uchar max = ;
  530.      uchar max_backup = ;
  531.      uchar zf  = ;
  532.      for(i = ; i < ; i++)
  533.      {
  534.          IplImage *mb = cvLoadImage(mb_ku_sz[i], );
  535.          uchar cgl = ;
  536.  
  537.          int cg_count = ;
  538.          int bd_count = ;
  539.          uchar *pt_mb = (uchar *)mb->imageData;
  540.          const uchar step_cs = cs->widthStep;
  541.          const uchar step_mb = mb->widthStep;
  542.          for(int w = ; w < cs->width; w++)
  543.              for(int h = ; h < cs->height; h++)
  544.              {
  545.                  if((pt_cs[h*step_cs + w] == pt_mb[h*step_mb + w]))
  546.                      cg_count++;
  547.                  if(pt_mb[h*step_mb + w])
  548.                      bd_count++;
  549.              }
  550.          cvReleaseImage(&mb);
  551.              cgl = (uchar)(((float)cg_count/(cs->height*cs->width))*);
  552.          max = max<cgl? cgl : max;
  553.          if(max != max_backup)
  554.              zf = i;
  555.          max_backup = max;
  556.      }
  557.      switch(zf)
  558.      {
  559.      case : fhz = "";break; case : fhz = "";break; case : fhz = "";break; case : fhz = "";break;
  560.      case : fhz = "";break; case : fhz = "";break; case : fhz = "";break; case : fhz = "";break;
  561.      case : fhz = "";break; case : fhz = "";break;
  562.      }
  563.      return (fhz);
  564.  }

char

前面的路径中就是字符库的图片路径。

最后可以得到车牌号码的 字符串，接下来就是后台的处理。

3.对进出用户的信息存储和读取。

这里我们使用的是Qt界面程序语言编写的客户端。

这里是真正的发挥空间，可以使用得来的数据进行存储，还有手机客户端给用户信息。

 

 

基于opencv的车牌识别系统的更多相关文章

  1. python基于OpenCV的人脸识别系统

    想获得所有的代码,请下载(来自我的CSDN): https://download.csdn.net/download/qq_40875849/11292912 主函数: from recognitio ...

  2. EasyPR--中文开源车牌识别系统 开发详解（1）

    在上篇文档中作者已经简单的介绍了EasyPR,现在在本文档中详细的介绍EasyPR的开发过程. 正如淘宝诞生于一个购买来的LAMP系统,EasyPR也有它诞生的原型,起源于CSDN的taotao123 ...

  3. EasyPR--一个开源的中文车牌识别系统

    我正在做一个开源的中文车牌识别系统,Git地址为:https://github.com/liuruoze/EasyPR. 我给它取的名字为EasyPR,也就是Easy to do Plate Reco ...

  4. 基于 OpenCV 的人脸识别

    基于 OpenCV 的人脸识别 一点背景知识 OpenCV 是一个开源的计算机视觉和机器学习库.它包含成千上万优化过的算法,为各种计算机视觉应用提供了一个通用工具包.根据这个项目的关于页面,OpenC ...

  5. 数字图像处理：基于MATLAB的车牌识别项目 标签： 图像处理matlab算法 2017-06-24 09:17 98人阅读 评论(0)

    学过了数字图像处理,就进行一个综合性强的小项目来巩固一下知识吧.前阵子编写调试了一套基于MATLAB的车牌识别的项目的代码.今天又重新改进了一下代码,识别的效果好一点了,也精简了一些代码.这里没有使用 ...

  6. 基于ARM的车牌识别技术研究与实现

    在云盘里包含了我本科毕业设计的全部资料和代码.主要涉及下面摘要中的几个部分.虽然系统无法实用,但是适合机器视觉和嵌入式方向的入门.希望能对有志从事相关方向的朋友有所帮助.本人现在在深圳从事机器视觉算法 ...

  7. 【计算机视觉】基于OpenCV的人脸识别

    一点背景知识 OpenCV 是一个开源的计算机视觉和机器学习库.它包含成千上万优化过的算法,为各种计算机视觉应用提供了一个通用工具包.根据这个项目的关于页面,OpenCV 已被广泛运用在各种项目上,从 ...

  8. java基于OpenCV的人脸识别

    基于Java简单的人脸和人眼识别程序 使用这个程序之前必须先安装配置OpenCV详细教程见:https://www.cnblogs.com/prodigal-son/p/12768948.html 注 ...

  9. 毕业设计 python opencv实现车牌识别 界面

    主要代码参考https://blog.csdn.net/wzh191920/article/details/79589506 GitHub:https://github.com/yinghualuow ...

随机推荐

  1. Gradle之恋－任务1

    任务作为Gradle的核心功能模块,而且Gradle的任务还可以具有自己的属性和方法,大大扩展了Ant任务的功能.由于任务相关内容比较多,分为两篇来探讨,本篇主要涉及到:任务的定义.任务的属性.任务的 ...

  2. Oracle Developer Data Modeler项目实践 (转)

    http://www.Oracle.com/webfolder/technetwork/tutorials/obe/db/sqldevdm/r30/datamodel2moddm/datamodel2 ...

  3. Struts2中Action配置的三种方式

    <!-- 方案一:一个action对应一个方法; --> <action name="add" class="com.gxxy.struts.kp03_ ...

  4. 3713: [PA2014]Iloczyn

    3713: [PA2014]Iloczyn Time Limit: 1 Sec  Memory Limit: 128 MBSubmit: 327  Solved: 181[Submit][Status ...

  5. 1657: [Usaco2006 Mar]Mooo 奶牛的歌声

    1657: [Usaco2006 Mar]Mooo 奶牛的歌声 Time Limit: 5 Sec  Memory Limit: 64 MBSubmit: 526  Solved: 365[Submi ...

  6. C++ Primer 5 CH2 变量和基本类型

    C++ 是一种静态数据类型语言,它的类型检查发生在编译时.因此,编译器需要知道每一个变量对应的数据类型. 2.1 基本内置类型 算术类型 C++ 标准并没有规定带符号类型应如何表示,但是约定了在表示范 ...

  7. MySQL基准测试（benchmark）

    基准测试是唯一方便有效的.可以学习系统在给定的工作负载下会发生什么的方法.基准测试可以观察系统在不同压力下的行为,评估系统的容量,掌握哪些是重要的变化,或者观察系统如何处理不同的数据. 验证基于系统的 ...

  8. cobbler自动安装系统

    一.简介 Cobbler是一个快速网络安装linux的服务,而且在经过调整也可以支持网络安装windows.该工具使用python开发,小巧轻便(才15k行python代码),使用简单的命令即可完成P ...

  9. 2017-3-20 HTML 基础知识

    HTML的定义:HTML是一门编程语言的名字:超文本标记语言(Hyper Text Mark-up Language ),就是超越了文字的范畴,除了文字还可以有图片.视频.音频.动画.特效.表格.链接 ...

  10. elasticsearch 索引 red 状态恢复 green

    方案一 找到状态为 red 的索引 curl -X GET "http://172.xxx.xxx.174:9288/_cat/indices?v=" red open index ...