//预测图片类型是否正确
public static PlateCategory Test(Mat matTest)
{
try
{
if (IsReady == false || svm == null)
{
throw new Exception("训练数据为空，请重新训练?车牌类型识别或加载数据");
}
PlateCategory result = PlateCategory.非车牌;
if (IsReady == false || svm == null)
{
return(result);
}
//￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥
Mat matTestGray = matTest.CvtColor(ColorConversionCodes.BGR2GRAY);
//之后记得改为0-255
Mat matTestDst = matTestGray.Threshold(0, 225, ThresholdTypes.Otsu | ThresholdTypes.Binary);
float[] descriptor = ComputeHogDescriptors(matTestDst);
Mat testDescriptor = Mat.Zeros(1, descriptor.Length, MatType.CV_32FC1);
for (int index = 0; index < descriptor.Length; index++)
{
testDescriptor.Set <float>(0, index, descriptor[index]);
}
float predict = svm.Predict(testDescriptor);
result = (PlateCategory)((int)predict);
return(result);
}
catch (Exception ex)
{
throw ex;
}
}
//测试
public static PlateCategory Test(Mat matTest)
{
try
{
if (IsReady == false || svm == null)
{
throw new Exception("训练数据为空，请重新训练⻋牌类型识别或加载数据");
}
PlateCategory result = PlateCategory.非车牌;
if (IsReady == false || svm == null)
{
return(result);
}
float[] descriptor = ComputeHogDescriptors(matTest);
Mat testDescriptor = TypeConvert.Float2Mat(descriptor);
float predict = svm.Predict(testDescriptor);
result = (PlateCategory)((int)predict);
return(result);
}
catch (Exception ex)
{
throw ex;
}
}
// 字符保存
public static void SaveCharSample(Mat charMat, PlateCategory plateCate, string libPath, string shortFileNameNoExt)
{
string fileName = string.Format(@"{0}\Mychars\{1}\{2}.jpg", libPath, plateCate, shortFileNameNoExt);
charMat = charMat.Resize(WIN_SIZE);
charMat.SaveImage(fileName);
}
// 保存图片样本
public static void SavePlateSample(Mat matPlate, PlateCategory plateCategory, string libPath, string shortFileNameNoExt)
{
DateTime now = DateTime.Now;
string fileName = string.Format(@"{0}\plates\{1}\{2}.jpg", libPath, plateCategory,
shortFileNameNoExt);
matPlate.SaveImage(fileName);
}
public PlateImage(string fileName, string name, PlateCategory plateCategory, OpenCvSharp.Size
matSize)
{
this.FileName = fileName;
this.Name = name;
this.PlateCategory = plateCategory;
this.MatSize = matSize;
}
//保存图片样本
public static void SavePlateSample(Mat matPlate, PlateCategory plateCategory, string libPath)
{
DateTime now = DateTime.Now;
string name = string.Format("{0}-{1:00}-{2:00}-{3:00}-{4:00}-{5:00}-{6:000000}",
now.Year, now.Month, now.Day, now.Hour, now.Minute, now.Second,
random.Next(100000));
string fileName = string.Format(@"{0}\plates\{1}\{2}.jpg", libPath, plateCategory, name);
matPlate.SaveImage(fileName);
}
public PlateInfo(PlateCategory plateCategory,
Rect originalRect, Mat originalMat,
List <CharInfo> charInfos,
PlateLocateMethod plateLocateMethod)
{
this.PlateCategory = plateCategory;
this.OriginalRect = originalRect;
this.OriginalMat = originalMat;
this.CharInfos = charInfos;
this.PlateLocateMethod = plateLocateMethod;
}
public static PlateCategory Test(Mat matPlate)
{
float[] hog = GetHog(matPlate);
Mat matTest = new Mat(1, hog.Length, MatType.CV_32FC1);
for (int i = 0; i < hog.Length; i++)
{
matTest.Set <float>(0, i, hog[i]);
}
PlateCategory result = (PlateCategory)((int)svm.Predict(matTest));
return(result);
}
private void tvTest_AfterSelect(object sender, TreeViewEventArgs e)
{
if (e.Node.Level == 0)
{
return;
}
string fileName = e.Node.Tag as string;
if (fileName == null)
{
return;
}
Mat matPreview = Cv2.ImRead(fileName);
this.picImage.Image = matPreview.ToBitmap();
PlateCategory category = Plate_SVM.Test(matPreview);
this.txtinfo.AppendText(string.Format("\r\n预测结果：{0}\r\n", category));
}
public static List <PlateCategory> TestList(List <Mat> matPlateList)
{
List <PlateCategory> resultList = new List <PlateCategory>();
PlateCategory result = 0;
foreach (var matPlate in matPlateList)
{
float[] hog = GetHog(matPlate);
Mat matTest = new Mat(1, hog.Length, MatType.CV_32FC1);
for (int i = 0; i < hog.Length; i++)
{
matTest.Set <float>(0, i, hog[i]);
}
result = (PlateCategory)((int)svm.Predict(matTest));
resultList.Add(result);
}
return(resultList);
}
public static List <PlateInfo> RecogPlateAndChar(Mat matSource)
{
List <PlateInfo> PlateInfoList = PlateRecognition_V3.Recognite(matSource);
if (PlateInfoList.Count == 0)
{
PlateCategory PlateCategory = PlateCategory.非车牌;
Rect OriginalRect = new Rect();
Mat OriginalMatnew = new Mat();
PlateLocateMethod PlateLocateMethod = PlateLocateMethod.未知;
List <CharInfo> CharInfos = null;
PlateInfo noPlateInfo = new PlateInfo(PlateCategory, OriginalRect, OriginalMatnew, CharInfos, PlateLocateMethod);
PlateInfoList.Add(noPlateInfo);
return(PlateInfoList);
}
else
{
return(PlateInfoList);
}
}
/// <summary>
/// 开始训练
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void btnStart_Click(object sender, EventArgs e)
{
if (this.samplePath == "")
{
return;
}
List <PlateInfo> plateSamples = new List <PlateInfo>();
string[] subDirectories = Directory.GetDirectories(this.samplePath);
for (int index = 0; index < subDirectories.Length; index++)
{
string subDirectory = subDirectories[index];
string shortDirectory = subDirectory.Substring(subDirectory.LastIndexOf(@"\") + 1);
PlateCategory category = (PlateCategory)Enum.Parse(typeof(PlateCategory), shortDirectory);
string[] fileNames = Directory.GetFiles(subDirectory, "*.jpg");
for (int i = 0; i < fileNames.Length; i++)
{
string fileName = fileNames[i];
this.txtinfo.AppendText(string.Format("{0} 类型：{1}\r\n", fileName, category));
Mat matPlate = Cv2.ImRead(fileName);
PlateInfo plateInfo = new PlateInfo();
plateInfo.PlateMat = matPlate;
plateInfo.Category = category;
plateSamples.Add(plateInfo);
}
}
//将样本的元数据转化为SVM的样品数据和标签数据
Mat trainData = new Mat();
Mat trainLabel = new Mat(plateSamples.Count, 1, MatType.CV_32SC1);
for (int index = 0; index < plateSamples.Count; index++)
{
PlateInfo plateInfo = plateSamples[index];
float[] hog = Plate_SVM.GetHog(plateInfo.PlateMat);
if (index == 0)
{
trainData = Mat.Zeros(plateSamples.Count, hog.Length, MatType.CV_32FC1);
}
for (int colIndex = 0; colIndex < hog.Length; colIndex++)
{
trainData.Set <float>(index, colIndex, hog[colIndex]);
}
trainLabel.Set <int>(index, 0, (int)plateInfo.Category);
this.txtinfo.AppendText(hog.Length.ToString() + "\r\n");
}
Plate_SVM.Train(trainData, trainLabel);
this.txtinfo.AppendText("训练已完成\r\n");
}
public static List <PlateInfo> LocatePlatesForAutoSample(Mat matSource,
out Mat matProcess,
int blur_Size = 5,
int sobel_Scale = 1,
int sobel_Delta = 0,
int sobel_X_Weight = 1,
int sobel_Y_Weight = 0,
int morph_Size_Width = 17,
int morph_Size_Height = 3,
int minWidth = 60, int maxWidth = 180,
int minHeight = 18, int maxHeight = 80,
float minRatio = 0.15f, float maxRatio = 0.70f)
{
List <PlateInfo> plateInfos = new List <PlateInfo>();
Mat gray = null;
Mat blur = null;
if (matSource.Empty() || matSource.Rows == 0 || matSource.Cols == 0)
{
matProcess = new Mat(0, 0, MatType.CV_8UC1);
return(plateInfos);
}
//灰度图
gray = matSource.CvtColor(ColorConversionCodes.BGR2GRAY);
//高斯模糊图
blur = gray.GaussianBlur(new OpenCvSharp.Size(blur_Size, blur_Size), 0, 0, BorderTypes.Default);
//HSV图
Mat hsv = matSource.CvtColor(ColorConversionCodes.BGR2HSV);
//将HSV图分成H、S、V通道图
Mat[] hsvSplits = hsv.Split();
hsvSplits[2] = hsvSplits[2].EqualizeHist();
Mat hsvEqualizeHist = new Mat();
//合并通道图
Cv2.Merge(hsvSplits, hsvEqualizeHist);
//提取蓝色
Scalar blueStart = new Scalar(100, 70, 70);
Scalar blueEnd = new Scalar(140, 255, 255);
Mat blue = hsvEqualizeHist.InRange(blueStart, blueEnd);
//提取黄色
Scalar yellowStart = new Scalar(15, 70, 70);
Scalar yellowEnd = new Scalar(40, 255, 255);
Mat yellow = hsvEqualizeHist.InRange(yellowStart, yellowEnd);
Mat add = blue + yellow;
//二值化
Mat threshold = add.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
Mat element = Cv2.GetStructuringElement(MorphShapes.Rect,
new OpenCvSharp.Size(morph_Size_Width, morph_Size_Height));
//闭操作
Mat threshold_Close = threshold.MorphologyEx(MorphTypes.Close, element);
Mat element_Erode = Cv2.GetStructuringElement(MorphShapes.Rect, new OpenCvSharp.Size(3,
3));
Mat threshold_Erode = threshold_Close.Erode(element_Erode);
matProcess = threshold_Erode;
OpenCvSharp.Point[][] contours = null;
HierarchyIndex[] hierarchys = null;
Cv2.FindContours(threshold_Erode, out contours, out hierarchys,
RetrievalModes.External, ContourApproximationModes.ApproxNone);
int isPlateCount = 0;
for (int index = 0; index < contours.Length; index++)
{
RotatedRect rotatedRect = Cv2.MinAreaRect(contours[index]);
Rect rectROI = Cv2.BoundingRect(contours[index]);
if (VerifyPlateSize(rectROI.Size,
minWidth,
maxWidth,
minHeight,
maxHeight,
minRatio,
maxRatio))
{
Mat matROI = matSource.SubMat(rectROI);
PlateCategory plateCategory = PlateCategory_SVM.Test(matROI);
if (plateCategory != PlateCategory.非车牌)
{
isPlateCount++;
}
PlateInfo plateInfo = new PlateInfo();
plateInfo.RotatedRect = rotatedRect;
plateInfo.OriginalRect = rectROI;
plateInfo.OriginalMat = matROI;
plateInfo.PlateCategory = plateCategory;
plateInfo.PlateLocateMethod = PlateLocateMethod.颜色法;
plateInfos.Add(plateInfo);
}
}
if (isPlateCount > 0)
{
return(plateInfos);
}
blur = matSource.GaussianBlur(new OpenCvSharp.Size(blur_Size, blur_Size), 0, 0,
BorderTypes.Default);
gray = blur.CvtColor(ColorConversionCodes.BGR2GRAY);
// 对图像进行Sobel 运算，得到的是图像的一阶水平方向导数。
// Generate grad_x and grad_y
MatType ddepth = MatType.CV_16S;
Mat grad_x = gray.Sobel(ddepth, 1, 0, 3, sobel_Scale, sobel_Delta, BorderTypes.Default);
Mat abs_grad_x = grad_x.ConvertScaleAbs();
Mat grad_y = gray.Sobel(ddepth, 0, 1, 3, sobel_Scale, sobel_Delta, BorderTypes.Default);
Mat abs_grad_y = grad_y.ConvertScaleAbs();
Mat grad = new Mat();
Cv2.AddWeighted(abs_grad_x, sobel_X_Weight, abs_grad_y, sobel_Y_Weight, 0, grad);
// 对图像进行二值化。将灰度图像（每个像素点有256 个取值可能）转化为二值图像（每个像素点仅有1 和0 两个取值可能）。
threshold = grad.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
// 使用闭操作。对图像进?行行闭操作以后，可以看到车牌区域被连接成一个矩形装的区域。
element = Cv2.GetStructuringElement(MorphShapes.Rect,
new OpenCvSharp.Size(morph_Size_Width,
morph_Size_Height));
threshold_Close = threshold.MorphologyEx(MorphTypes.Close, element);
element_Erode = Cv2.GetStructuringElement(MorphShapes.Rect, new OpenCvSharp.Size(5, 5));
threshold_Erode = threshold_Close.Erode(element_Erode);
matProcess = threshold_Erode;
// Find 轮廓 of possibles plates 求轮廓。求出图中所有的轮廓。这个算法会把全图的轮廓都计算出来，因此要进? 行行筛选。
contours = null;
hierarchys = null;
Cv2.FindContours(threshold_Erode, out contours, out hierarchys,
RetrievalModes.External, ContourApproximationModes.ApproxNone);
// 筛选。对轮廓求最?小外接矩形，然后验证，不不满?足条件的淘汰。
for (int index = 0; index < contours.Length; index++)
{
Rect rectROI = Cv2.BoundingRect(contours[index]);
if (VerifyPlateSize(rectROI.Size,
minWidth,
maxWidth,
minHeight,
maxHeight,
minRatio,
maxRatio))
{
RotatedRect rotatedRect = Cv2.MinAreaRect(contours[index]);
Mat matROI = matSource.SubMat(rectROI);
PlateCategory plateCategory = PlateCategory_SVM.Test(matROI);
PlateInfo plateInfo = new PlateInfo();
plateInfo.RotatedRect = rotatedRect;
plateInfo.OriginalRect = rectROI;
plateInfo.OriginalMat = matROI;
plateInfo.PlateCategory = plateCategory;
plateInfo.PlateLocateMethod = PlateLocateMethod.Sobel法;
plateInfos.Add(plateInfo);
}
}
return(plateInfos);
}
private static List <PlateInfo> LocatePlatesBySobel(Mat matSource,
int blur_Size = 5,
int sobel_Scale = 1,
int sobel_Delta = 0,
int sobel_X_Weight = 1,
int sobel_Y_Weight = 0,
int morph_Size_Width = 17,
int morph_Size_Height = 3,
int minWidth = 60, int maxWidth = 180,
int minHeight = 18, int maxHeight = 80,
float minRatio = 0.15f, float maxRatio = 0.70f)
{
List <PlateInfo> plateInfos = new List <PlateInfo>();
if (matSource.Empty())
{
return(plateInfos);
}
Mat blur = null;
Mat gray = null;
blur = matSource.GaussianBlur(new OpenCvSharp.Size(blur_Size, blur_Size), 0, 0,
BorderTypes.Default);
gray = blur.CvtColor(ColorConversionCodes.BGR2GRAY);
// 对图像进行Sobel 运算，得到的是图像的一阶水平方向导数。
// Generate grad_x and grad_y
MatType ddepth = MatType.CV_16S;
Mat grad_x = gray.Sobel(ddepth, 1, 0, 3, sobel_Scale, sobel_Delta, BorderTypes.Default);
Mat abs_grad_x = grad_x.ConvertScaleAbs();
Mat grad_y = gray.Sobel(ddepth, 0, 1, 3, sobel_Scale, sobel_Delta, BorderTypes.Default);
Mat abs_grad_y = grad_y.ConvertScaleAbs();
Mat grad = new Mat();
Cv2.AddWeighted(abs_grad_x, sobel_X_Weight, abs_grad_y, sobel_Y_Weight, 0, grad);
// 对图像进行二值化。将灰度图像（每个像素点有256 个取值可能）转化为二值图像（每个像素点仅有1 和0 两个取值可能）。
Mat threshold = grad.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
// 使用闭操作。对图像进行闭操作以后，可以看到车牌区域被连接成一个矩形装的区域。
Mat element = Cv2.GetStructuringElement(MorphShapes.Rect,
new OpenCvSharp.Size(morph_Size_Width,
morph_Size_Height));
Mat threshold_Close = threshold.MorphologyEx(MorphTypes.Close, element);
Mat element_Erode = Cv2.GetStructuringElement(MorphShapes.Rect, new OpenCvSharp.Size(5,
5));
Mat threshold_Erode = threshold_Close.Erode(element_Erode);
// Find 轮廓 of possibles plates 求轮廓。求出图中所有的轮廓。这个算法会把全图的轮廓都计算出来，因此要进行筛选。
OpenCvSharp.Point[][] contours = null;
HierarchyIndex[] hierarchys = null;
Cv2.FindContours(threshold_Erode, out contours, out hierarchys,
RetrievalModes.External, ContourApproximationModes.ApproxNone);
// 筛选。对轮廓求最小外接矩形，然后验证，不满足条件的淘汰。
for (int index = 0; index < contours.Length; index++)
{
Rect rectROI = Cv2.BoundingRect(contours[index]);
if (VerifyPlateSize(rectROI.Size,
minWidth,
maxWidth,
minHeight,
maxHeight,
minRatio,
maxRatio))
{
Mat matROI = matSource.SubMat(rectROI);
PlateCategory plateCategory = PlateCategory_SVM.Test(matROI);
if (plateCategory == PlateCategory.非车牌)
{
continue;
}
PlateInfo plateInfo = new PlateInfo();
plateInfo.OriginalRect = rectROI;
plateInfo.OriginalMat = matROI;
plateInfo.PlateCategory = plateCategory;
plateInfo.PlateLocateMethod = PlateLocateMethod.Sobel法;
plateInfos.Add(plateInfo);
}
}
return(plateInfos);
}
//颜色法
private static List <PlateInfo> LocatePlatesByColor(Mat matSource,
int blur_Size = 5,
int morph_Size_Width = 17,
int morph_Size_Height = 3,
int minWidth = 60, int maxWidth = 180,
int minHeight = 18, int maxHeight = 80,
float minRatio = 0.15f, float maxRatio = 0.70f)
{
List <PlateInfo> plateInfos = new List <PlateInfo>();
if (matSource.Empty())
{
return(plateInfos);
}
Mat hsv = matSource.CvtColor(ColorConversionCodes.BGR2HSV);
Mat[] hsvSplits = hsv.Split();
hsvSplits[2] = hsvSplits[2].EqualizeHist();
Mat hsvEqualizeHist = new Mat();
Cv2.Merge(hsvSplits, hsvEqualizeHist);
Scalar blueStart = new Scalar(100, 70, 70);
Scalar blueEnd = new Scalar(140, 255, 255);
Mat blue = hsvEqualizeHist.InRange(blueStart, blueEnd);
Scalar yellowStart = new Scalar(15, 70, 70);
Scalar yellowEnd = new Scalar(40, 255, 255);
Mat yellow = hsvEqualizeHist.InRange(yellowStart, yellowEnd);
Mat add = blue + yellow;
Mat threshold = add.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
Mat element = Cv2.GetStructuringElement(MorphShapes.Rect,
new OpenCvSharp.Size(morph_Size_Width,
morph_Size_Height));
Mat threshold_Close = threshold.MorphologyEx(MorphTypes.Close, element);
Mat element_Erode = Cv2.GetStructuringElement(MorphShapes.Rect, new OpenCvSharp.Size(3,
3));
Mat threshold_Erode = threshold_Close.Erode(element_Erode);
OpenCvSharp.Point[][] contours = null;
HierarchyIndex[] hierarchys = null;
Cv2.FindContours(threshold_Erode, out contours, out hierarchys,
RetrievalModes.External, ContourApproximationModes.ApproxNone);
for (int index = 0; index < contours.Length; index++)
{
Rect rectROI = Cv2.BoundingRect(contours[index]);
if (VerifyPlateSize(rectROI.Size,
minWidth,
maxWidth,
minHeight,
maxHeight,
minRatio,
maxRatio))
{
Mat matROI = matSource.SubMat(rectROI);
PlateCategory plateCategory = PlateCategory_SVM.Test(matROI);
if (plateCategory == PlateCategory.非车牌)
{
continue;
}
PlateInfo plateInfo = new PlateInfo();
plateInfo.OriginalRect = rectROI;
plateInfo.OriginalMat = matROI;
plateInfo.PlateCategory = plateCategory;
plateInfo.PlateLocateMethod = PlateLocateMethod.颜色法;
plateInfos.Add(plateInfo);
}
}
return(plateInfos);
}
public static List <Mat> carCharSplit(Mat matPlate)
{
Mat hsvmat = matPlate.CvtColor(ColorConversionCodes.BGR2HSV);
Mat[] hsv = hsvmat.Split();
Mat h = hsv[0];
Mat s = hsv[1];
Mat v = hsv[2];
for (int i = 0; i < hsvmat.Rows; i++)
{
for (int j = 0; j < hsvmat.Cols; j++)
{
byte hvalue = h.At <byte>(i, j); //////////////////h通道/-/////////////////////
// Console.WriteLine(hvalue + ":h");
byte svalue = s.At <byte>(i, j); //////////////////s通道/-/////////////////////
byte vvalue = v.At <byte>(i, j); //////////////////v通道/-/////////////////////
// printf("x=%d,y=%d,HSV: H=%d,S=%d,V=%d\n",i,j,hvalue,svalue,vvalue);
if ((hvalue > 80 && hvalue < 130) && (svalue > 43 && svalue < 220) && (vvalue > 46 && vvalue < 255)) //hsv图像在蓝色区域里
{
//蓝色+1
bluenum++;
}
else if ((hvalue > 11 && hvalue < 34) && (svalue > 43 && svalue < 255) && (vvalue > 46 && vvalue < 255))//hsv在黄色区域里
{
//黄色+1
yellownum++;
}
else if ((hvalue > 0 && hvalue < 180) && (svalue > 0 && svalue < 255) && (vvalue > 0 && vvalue < 46))//hsv在黑色区域里
{
blacknum++;
//黑色+1
}
else if ((hvalue > 0 && hvalue < 180) && (svalue > 0 && svalue < 30) && (vvalue > 46 && vvalue < 220))//hsv在白色区域里
{
//白色+1
whitenum++;
}
else if ((hvalue > 60 && hvalue < 90) && (svalue > 43 && svalue < 255) && (vvalue > 46 && vvalue < 255))//hsv在绿色区域里
{
//绿色+1
greennum++;
}
else
{
//其他颜色
othernum++;
}
}
}
Console.WriteLine(greennum + ":绿色");
Console.WriteLine(hsvmat.Rows * hsvmat.Cols + ":总");
Console.WriteLine(yellownum + ":黄色");
Console.WriteLine(bluenum + ":蓝色");
// 灰度
matGray_car = matPlate.CvtColor(ColorConversionCodes.BGR2GRAY);
//二值化
Mat matshoid_th = matGray_car.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
matshoid = new Mat();
// 判断 取反 否
if (bluenum < yellownum && yellownum > greennum)
{
// 取反
matshoid = 255 - matshoid_th;
}
else if (bluenum > yellownum && bluenum > greennum)
{
matshoid = matGray_car.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
}
else if (greennum > yellownum && greennum > bluenum)
{
// 取反
matshoid = 255 - matshoid_th;
}
else
{
matshoid = matGray_car.Threshold(0, 255, ThresholdTypes.Otsu | ThresholdTypes.Binary);
}
// 车牌高度大于20的去除边框和柳钉
Mat clearBorder = new Mat();
Mat clearMoDing = new Mat();
if (matshoid.Height > 22)
{
// 去除边框
clearBorder = ClearBorder(matshoid);
// 去除柳钉
clearMoDing = ClearMaoding(matshoid, 4);
}
else if (matshoid.Height <= 22 && matshoid.Height > 20)
{
// 去除边框
clearBorder = ClearBorder(matshoid);
// 去除柳钉
clearMoDing = ClearMaoding(matshoid, 3);
}
else
{
clearMoDing = matshoid;
}
// 膨胀
Mat element = Cv2.GetStructuringElement(MorphShapes.Rect, new OpenCvSharp.Size(1, 1));
matDilate_car = clearMoDing.MorphologyEx(MorphTypes.Dilate, element);
//点的二维数组
OpenCvSharp.Point[][] contours = null;
HierarchyIndex[] hierarchyIndexs = null;
matDilate_car.FindContours(out contours, out hierarchyIndexs, RetrievalModes.External, ContourApproximationModes.ApproxSimple);
matWithFalg_car = matPlate.Clone();
matWithFalg_car.DrawContours(contours, -1, Scalar.Red);
matWithRects = matPlate.Clone();
// 创建集合 存储分割后的图片 -- 用于 识别
List <Mat> ListMat = new List <Mat>();
// 切割的矩形 图
List <Rect> ListRect = new List <Rect>();
for (int index = 0; index < contours.Length; index++)
{
Rect rect = Cv2.BoundingRect(contours[index]);
ListRect.Add(rect);
matWithRects.Rectangle(rect, Scalar.Red);
}
// 对分割的字符排序
SortRectsByLeft_ASC(ListRect);
foreach (var rect in ListRect)
{
Mat matchar = matPlate.SubMat(rect); // 切割矩形
Console.WriteLine("========= 宽:" + matchar.Width + " 高:" + matchar.Height);
// 判断 太小的不要
if (matchar.Width >= 3 && matchar.Height >= 10)
{
PlateCategory plateCate = Plate_SVM.Test(matchar);
ListMat.Add(matchar);
Console.WriteLine(ListMat.Count + " 个");
}
Console.WriteLine("========= 宽:" + rect.Width + " 高:" + rect.Height + " X:" + rect.X + " Y:" + rect.Y);
}
return(ListMat);
}