現在很多場景需要使用的數字識別，比如銀行卡識別，以及車牌識別等，在AI領域有很多影像識別演算法，大多是居于opencv 或者谷歌開源的tesseract 識別.
由于公司業務需要，需要開發一個客戶端程式，同時需要在xp這種老古董的機子上運行，故研究了如下幾個數字識別方案：
ocr 識別的不同選擇方案
- tesseract
- 放棄：谷歌的開源tesseract ocr識別目前最新版本不支持xp系統
- 云端ocr 識別介面(不適用)
- 費用比較貴：
- 場景不同，我們的需求是可能毫秒級別就需要呼叫一次ocr 識別
- opencv
- 概念:OpenCV是一個基于BSD許可（開源）發行的跨平臺計算機視覺庫，可以運行在Linux、Windows、Android和Mac OS作業系統上，它輕量級而且高效——由一系列 C 函式和少量 C++ 類構成，同時提供了Python、Ruby、MATLAB等語言的介面，實作了影像處理和計算機視覺方面的很多通用演算法，
以上幾種ocr 識別比較，最后選擇了opencv 的方式進行ocr 數字識別,下面講解通過ocr識別的基本流程和演算法.
opencv 數字識別流程及演算法決議
要通過opencv 進行數字識別離不開訓練庫的支持，需要對目標圖片進行大量的訓練，才能做到精準的識別出目標數字;下面我會分別講解圖片訓練的程序及識別的程序.
opencv 識別演算法原理
- 比如下面一張圖片，需要從中識別出正確的數字，需要對圖片進行灰度、二值化、腐蝕、膨脹、尋找數字輪廓、切割等一系列操作.
原圖
灰度化圖
二值化圖
尋找輪廓
識別后的結果圖
以上就是簡單的圖片進行灰度化、二值化、尋找數字輪廓得到的識別結果(這是基于我之前訓練過的數字模型下得到的識別結果)
有些圖片比較賦值，比如存在背景斜杠等的圖片則需要一定的腐蝕或者膨脹等處理，才能尋找到正確的數字輪廓.
上面的說到我這里使用的是opencv 影像處理庫進行的ocr 識別，那我這里簡單介紹下C# 怎么使用opencv 影像處理看;
為了在xp上能夠運行 我這里通過nuget 包參考了 OpenCvSharp-AnyCPU 第三方庫,它使用的是opencv 2410 版本,你們如果不考慮xp系統的情況下開源使用最新的版本，最新版本支持了更多的識別演算法.
右擊你的個人專案，選擇“管理Nuget程式包”，在包管理器頁面中，點擊“瀏覽”選項，然后在搜索框中鍵入“OpenCvSharp-AnyCPU”，選擇最頂端的正確專案，并在右側詳情頁中點擊“安裝”，等待安裝完成即可，
以上的核心代碼如下:
private void runSimpleOCR(string pathName)
{
//構造opcvOcr 庫，這里的是我單獨對opencv 庫進行的一次封裝,加載訓練庫模板
var opencvOcr = new OpencvOcr($"{path}Template\\Traindata.xml", opencvOcrConfig: new OCR.Model.OpencvOcrConfig()
{
ErodeLevel = 2.5,
ThresholdType = OpenCvSharp.ThresholdType.Binary,
ZoomLevel = 2,
});
var img = new Bitmap(this.txbFilaName.Text);
var mat = img.ToMat();
//核心識別方法
var str = opencvOcr.GetText(mat, isDebug: true);
this.labContent.Content = str;
}
opencvOcr 的核心代碼如下
#region Constructor
const double Thresh = 80;
const double ThresholdMaxVal = 255;
const int _minHeight = 35;
bool _isDebug = false;
CvKNearest _cvKNearest = null;
OpencvOcrConfig _config = new OpencvOcrConfig() { ZoomLevel = 2, ErodeLevel = 3 };
#endregion
/// <summary>
/// 建構式
/// </summary>
/// <param name="path">訓練庫完整路徑</param>
/// <param name="opencvOcrConfig">OCR相關配置資訊</param>
public OpencvOcr(string path, OpencvOcrConfig opencvOcrConfig = null)
{
if (string.IsNullOrEmpty(path))
throw new ArgumentNullException("path is not null");
if (opencvOcrConfig != null)
_config = opencvOcrConfig;
this.LoadKnearest(path);
}
/// <summary>
/// 加載Knn 訓練庫模型
/// </summary>
/// <param name="dataPathFile"></param>
/// <returns></returns>
private CvKNearest LoadKnearest(string dataPathFile)
{
if (_cvKNearest == null)
{
using (var fs = new FileStorage(dataPathFile, FileStorageMode.Read))
{
var samples = fs["samples"].ReadMat();
var responses = fs["responses"].ReadMat();
this._cvKNearest = new CvKNearest();
this._cvKNearest.Train(samples, responses);
}
}
return _cvKNearest;
}
/// <summary>
/// OCR 識別,僅僅只能識別單行數字
/// </summary>
/// <param name="kNearest">訓練庫</param>
/// <param name="path">要識別的圖片路徑</param>
public override string GetText(Mat src, bool isDebug = false)
{
this._isDebug = isDebug;
#region 圖片處理
var respMat = MatProcessing(src, isDebug);
if (respMat == null)
return "";
#endregion
#region 查找輪廓
var sortRect = FindContours(respMat.FindContoursMat);
#endregion
return GetText(sortRect, respMat.ResourcMat, respMat.RoiResultMat);
}
/// <summary>
/// 查找輪廓
/// </summary>
/// <param name="src"></param>
/// <returns></returns>
private List<Rect> FindContours(Mat src)
{
try
{
#region 查找輪廓
Point[][] contours;
HierarchyIndex[] hierarchyIndexes;
Cv2.FindContours(
src,
out contours,
out hierarchyIndexes,
mode: OpenCvSharp.ContourRetrieval.External,
method: OpenCvSharp.ContourChain.ApproxSimple);
if (contours.Length == 0)
throw new NotSupportedException("Couldn't find any object in the image.");
#endregion
#region 單行排序（目前僅僅支持單行文字,多行文字順序可能不對，按照x坐標進行排序）
var sortRect = GetSortRect(contours, hierarchyIndexes);
sortRect = sortRect.OrderBy(item => item.X).ToList();
#endregion
return sortRect;
}
catch { }
return null;
}
/// <summary>
/// 獲得切割后的數量串列
/// </summary>
/// <param name="contours"></param>
/// <param name="hierarchyIndex"></param>
/// <returns></returns>
private List<Rect> GetSortRect(Point[][] contours, HierarchyIndex[] hierarchyIndex)
{
var sortRect = new List<Rect>();
var _contourIndex = 0;
while ((_contourIndex >= 0))
{
var contour = contours[_contourIndex];
var boundingRect = Cv2.BoundingRect(contour); //Find bounding rect for each contour
sortRect.Add(boundingRect);
_contourIndex = hierarchyIndex[_contourIndex].Next;
}
return sortRect;
}
/// <summary>
/// 是否放大
/// </summary>
/// <param name="src"></param>
/// <returns></returns>
private bool IsZoom(Mat src)
{
if (src.Height <= _minHeight)
return true;
return false;
}
private List<EnumMatAlgorithmType> GetAlgoritmList(Mat src)
{
var result = new List<EnumMatAlgorithmType>();
var algorithm = this._config.Algorithm;
#region 自定義的演算法
try
{
if (algorithm.Contains("|"))
{
result = algorithm.Split('|').ToList()
.Select(item => (EnumMatAlgorithmType)Convert.ToInt32(item))
.ToList();
if (!IsZoom(src))
result.Remove(EnumMatAlgorithmType.Zoom);
return result;
}
}
catch { }
#endregion
#region 默認演算法
if (IsZoom(src))
{
result.Add(EnumMatAlgorithmType.Zoom);
}
if (this._config.ThresholdType == ThresholdType.Binary)
{
//result.Add(EnumMatAlgorithmType.Blur);
result.Add(EnumMatAlgorithmType.Gray);
result.Add(EnumMatAlgorithmType.Thresh);
if (this._config.DilateLevel > 0)
result.Add(EnumMatAlgorithmType.Dilate);
result.Add(EnumMatAlgorithmType.Erode);
return result;
}
//result.Add(EnumMatAlgorithmType.Blur);
result.Add(EnumMatAlgorithmType.Gray);
result.Add(EnumMatAlgorithmType.Thresh);
if (this._config.DilateLevel > 0)
result.Add(EnumMatAlgorithmType.Dilate);
result.Add(EnumMatAlgorithmType.Erode);
return result;
#endregion
}
/// <summary>
/// 對查找的輪廓資料進行訓練模型匹配，這里使用的是KNN 匹配演算法
/// </summary>
private string GetText(List<Rect> sortRect, Mat source, Mat roiSource)
{
var response = "";
try
{
if ((sortRect?.Count ?? 0) <= 0)
return response;
var contourIndex = 0;
using (var dst = new Mat(source.Rows, source.Cols, MatType.CV_8UC3, Scalar.All(0)))
{
sortRect.ForEach(boundingRect =>
{
try
{
#region 繪制矩形
if (this._isDebug)
{
Cv2.Rectangle(source, new Point(boundingRect.X, boundingRect.Y),
new Point(boundingRect.X + boundingRect.Width, boundingRect.Y + boundingRect.Height),
new Scalar(0, 0, 255), 1);
Cv2.Rectangle(roiSource, new Point(boundingRect.X, boundingRect.Y),
new Point(boundingRect.X + boundingRect.Width, boundingRect.Y + boundingRect.Height),
new Scalar(0, 0, 255), 1);
}
#endregion
#region 單個ROI
var roi = roiSource.GetROI(boundingRect); //Crop the image
roi = roi.Compress();
var result = roi.ConvertFloat();
#endregion
#region KNN 匹配
var results = new Mat();
var neighborResponses = new Mat();
var dists = new Mat();
var detectedClass = (int)this._cvKNearest.FindNearest(result, 1, results, neighborResponses, dists);
var resultText = detectedClass.ToString(CultureInfo.InvariantCulture);
#endregion
#region 匹配
var isDraw = false;
if (detectedClass >= 0)
{
response += detectedClass.ToString();
isDraw = true;
}
if (detectedClass == -1 && !response.Contains("."))
{
response += ".";
resultText = ".";
isDraw = true;
}
#endregion
#region 繪制及輸出切割資訊庫
try
{
//if (this._isDebug)
//{
Write(contourIndex, detectedClass, roi);
//}
}
catch { }
if (this._isDebug && isDraw)
{
Cv2.PutText(dst, resultText, new Point(boundingRect.X, boundingRect.Y + boundingRect.Height), 0, 1, new Scalar(0, 255, 0), 2);
}
#endregion
result?.Dispose();
results?.Dispose();
neighborResponses?.Dispose();
dists?.Dispose();
contourIndex++;
}
catch (Exception ex)
{
TextHelper.Error("GetText ex", ex);
}
});
#region 除錯模式顯示程序
source.IsDebugShow("Segmented Source", this._isDebug);
dst.IsDebugShow("Detected", this._isDebug);
dst.IsDebugWaitKey(this._isDebug);
dst.IsDebugImWrite("dest.jpg", this._isDebug);
#endregion
}
}
catch
{
throw;
}
finally
{
source?.Dispose();
roiSource?.Dispose();
}
return response;
}
/// <summary>
/// 圖片處理演算法
/// </summary>
/// <param name="src"></param>
/// <param name="isDebug"></param>
/// <returns></returns>
public ImageProcessModel MatProcessing(Mat src, bool isDebug = false)
{
src.IsDebugShow("原圖", isDebug);
var list = GetAlgoritmList(src);
var resultMat = new Mat();
src.CopyTo(resultMat);
var isZoom = IsZoom(src);
list?.ForEach(item =>
{
switch (item)
{
case EnumMatAlgorithmType.Dilate:
resultMat = resultMat.ToDilate(Convert.ToInt32(this._config.DilateLevel));
resultMat.IsDebugShow(EnumMatAlgorithmType.Dilate.GetDescription(), isDebug);
break;
case EnumMatAlgorithmType.Erode:
var eroderLevel = isZoom ? this._config.ErodeLevel * this._config.ZoomLevel : this._config.ErodeLevel;
resultMat = resultMat.ToErode(eroderLevel);
resultMat.IsDebugShow(EnumMatAlgorithmType.Erode.GetDescription(), isDebug);
break;
case EnumMatAlgorithmType.Gray:
resultMat = resultMat.ToGrey();
resultMat.IsDebugShow(EnumMatAlgorithmType.Gray.GetDescription(), isDebug);
break;
case EnumMatAlgorithmType.Thresh:
var thresholdValue = https://www.cnblogs.com/dearroy/p/this._config.ThresholdValue <= 0 ? resultMat.GetMeanThreshold() : this._config.ThresholdValue;
resultMat = resultMat.ToThreshold(thresholdValue, thresholdType: this._config.ThresholdType);
resultMat.IsDebugShow(EnumMatAlgorithmType.Thresh.GetDescription(), isDebug);
break;
case EnumMatAlgorithmType.Zoom:
resultMat = resultMat.ToZoom(this._config.ZoomLevel);
src = resultMat;
resultMat.IsDebugShow(EnumMatAlgorithmType.Zoom.GetDescription(), isDebug);
break;
case EnumMatAlgorithmType.Blur:
resultMat = resultMat.ToBlur();
src = resultMat;
resultMat.IsDebugShow(EnumMatAlgorithmType.Blur.GetDescription(), isDebug);
break;
}
});
var oldThreshImage = new Mat();
resultMat.CopyTo(oldThreshImage);
return new ImageProcessModel()
{
ResourcMat = src,
FindContoursMat = oldThreshImage,
RoiResultMat = resultMat
};
}
opencv 圖片處理開放出去的配置物件物體如下：
public class OpencvOcrConfig
{
/// <summary>
/// 放大程度級別 默認2
/// </summary>
public double ZoomLevel { set; get; }
/// <summary>
/// 腐蝕級別 默認2.5
/// </summary>
public double ErodeLevel { set; get; }
/// <summary>
/// 膨脹
/// </summary>
public double DilateLevel { set; get; }
/// <summary>
/// 閥值
/// </summary>
public double ThresholdValue { set; get; }
/// <summary>
/// 圖片處理演算法,用逗號隔開
/// </summary>
public string Algorithm { set; get; }
/// <summary>
/// 二值化方式
/// </summary>
public ThresholdType ThresholdType { set; get; } = ThresholdType.BinaryInv;
/// <summary>
/// 通道模式
/// </summary>
public OcrChannelTypeEnums ChannelType { set; get; } = OcrChannelTypeEnums.BlackBox;
}
opencv 圖片處理演算法擴展方法如下：
public static partial class OpenCvExtensions
{
private const int Thresh = 200;
private const int ThresholdMaxVal = 255;
/// <summary>
/// Bitmap Convert Mat
/// </summary>
/// <param name="bitmap"></param>
/// <returns></returns>
public static Mat ToMat(this System.Drawing.Bitmap bitmap)
{
return OpenCvSharp.Extensions.BitmapConverter.ToMat(bitmap);
}
/// <summary>
/// Bitmap Convert Mat
/// </summary>
/// <param name="bitmap"></param>
/// <returns></returns>
public static System.Drawing.Bitmap ToBitmap(this Mat mat)
{
return OpenCvSharp.Extensions.BitmapConverter.ToBitmap(mat);
}
public static bool MatIsEqual(this Mat mat1, Mat mat2)
{
try
{
if (mat1.Empty() && mat2.Empty())
{
return true;
}
if (mat1.Cols != mat2.Cols || mat1.Rows != mat2.Rows || mat1.Dims() != mat2.Dims() ||
mat1.Channels() != mat2.Channels())
{
return false;
}
if (mat1.Size() != mat2.Size() || mat1.Type() != mat2.Type())
{
return false;
}
var nrOfElements1 = mat1.Total() * mat1.ElemSize();
if (nrOfElements1 != mat2.Total() * mat2.ElemSize())
return false;
return MatPixelEqual(mat1, mat2);
}
catch (Exception ex)
{
TextHelper.Error("MatIsEqual 例外", ex);
return true;
}
}
/// <summary>
/// 灰度
/// </summary>
/// <param name="mat"></param>
/// <returns></returns>
public static Mat ToGrey(this Mat mat)
{
try
{
Mat grey = new Mat();
Cv2.CvtColor(mat, grey, OpenCvSharp.ColorConversion.BgraToGray);
return grey;
}
catch
{
return mat;
}
}
/// <summary>
/// 二值化
/// </summary>
/// <param name="data"></param>
/// <returns></returns>
public static Mat ToThreshold(this Mat data, double threshValue = https://www.cnblogs.com/dearroy/p/0, ThresholdType thresholdType = ThresholdType.BinaryInv)
{
Mat threshold = new Mat();
if (threshValue == 0)
threshValue = Thresh;
Cv2.Threshold(data, threshold, threshValue, ThresholdMaxVal, thresholdType);
if (threshold.IsBinaryInv())
{
Cv2.Threshold(threshold, threshold, threshValue, ThresholdMaxVal, ThresholdType.BinaryInv);
}
//Mat threshold = new Mat();
//if (threshValue == 0)
// threshValue = Thresh;
//Cv2.AdaptiveThreshold(data, threshold, ThresholdMaxVal,AdaptiveThresholdType.MeanC, thresholdType,3,0);
//if (threshold.IsBinaryInv())
//{
// Cv2.AdaptiveThreshold(threshold, threshold, ThresholdMaxVal, AdaptiveThresholdType.MeanC, ThresholdType.BinaryInv,3, 0);
//}
//Cv2.AdaptiveThreshold()
// Threshold to find contour
//var threshold = data.Threshold(80, 255, ThresholdType.BinaryInv);
//Cv2.Threshold(data, threshold, Thresh, ThresholdMaxVal, ThresholdType.BinaryInv); // Threshold to find contour
//Cv2.AdaptiveThreshold(data, threshold, 255, AdaptiveThresholdType.MeanC, ThresholdType.BinaryInv, 11, 2);
//Cv2.Threshold(data, data, Thresh, ThresholdMaxVal, OpenCvSharp.ThresholdType.BinaryInv); // Threshold to find contour
//Cv2.AdaptiveThreshold(data, threshold, ThresholdMaxVal, AdaptiveThresholdType.GaussianC, OpenCvSharp.ThresholdType.Binary, 3, 0); // Threshold to find contour
//Cv2.AdaptiveThreshold(data, threshold, 255, AdaptiveThresholdType.MeanC, ThresholdType.Binary, 3, 0);
//CvInvoke.AdaptiveThreshold(data, data, 255, Emgu.CV.CvEnum.AdaptiveThresholdType.GaussianC, Emgu.CV.CvEnum.ThresholdType.Binary, 3, 0);
return threshold;
//var mat = data.Threshold(100, 255,ThresholdType.Binary);
//return mat;
}
///
/// 是否除錯顯示
///
///
///
///
public static void IsDebugShow(this Mat src, string name, bool isDebug = false)
{
if (!isDebug)
return;
Cv2.ImShow(name, src);
}
public static void IsDebugWaitKey(this Mat src, bool isDebug = false)
{
if (!isDebug)
return;
Cv2.WaitKey();
}
public static void IsDebugImWrite(this Mat src, string path, bool isDebug = false)
{
if (!isDebug)
return;
try
{
Cv2.ImWrite(path, src);
}
catch { }
}
///
/// Mat 轉成另外一種存盤矩陣方式
///
///
///
/// 腐蝕
///
///
///
/// 膨脹
///
///
///
/// mat 轉Roi
///
///
///
///
/// 獲取平均閥值
///
///
///
/// 獲得二值化閥值
///
///
///
/// 放大
///
///
///
///
/// 均值濾波
///
///
/// (row, col); //獲對應矩陣坐標的取像素
byte pAre = are.At(row, col);
if (p != pAre)
return false;
}
}
return true;
}
public static int GetSumPixelCount(this Mat threshold)
{
var width = threshold.Width;
var height = threshold.Height;
var sum = width * height;
var value = 0;
for (int row = 0; row < height; row++)
{
for (int col = 0; col < width; col++)
{
byte p = threshold.At(row, col); //獲對應矩陣坐標的取像素
value++;
}
}
return value;
}
public static int GetPixelCount(this Mat threshold, System.Drawing.Color color)
{
var width = threshold.Width;
var height = threshold.Height;
var sum = width * height;
var value = 0;
for (int row = 0; row < height; row++)
{
for (int col = 0; col < width; col++)
{
byte p = threshold.At(row, col); //獲對應矩陣坐標的取像素
if (Convert.ToInt32(p) == color.R)
{
value++;
}
}
}
return value;
}
///
/// 是否需要二值化反轉
///
///
///
/// 是否需要腐蝕
///
///
///
/// 獲得白色像素占比
///
///
///
/// 根據模板查找目標圖片的在原圖示中的開始位置坐標
///
///
///
///
/// 以上代碼中開源對圖片進行輪廓切割，同時會生成切割后的圖片代碼如下
#region 繪制及輸出切割資訊庫
try
{
Write(contourIndex, detectedClass, roi);
}
catch { }
#endregion
private void Write(int contourIndex, int detectedClass, Mat roi)
{
Task.Factory.StartNew(() =>
{
try
{
var templatePath = $"{AppDomain.CurrentDomain.BaseDirectory}template";
FileHelper.CreateDirectory(templatePath);
var templatePathFile = $"{templatePath}/{contourIndex}_{detectedClass.ToString()}.png";
Cv2.ImWrite(templatePathFile, roi);
if (!roi.IsDisposed)
{
roi.Dispose();
}
}
catch {}
});
}
切割后的圖片如下：
這里我已經對數字進行切割好了，接下來就是需要對0-9 這些數字進行分類(建立檔案夾進行數字歸類)，如下：
圖中的每一個分類都是我事先切割好的數字圖片,圖中有-1 和-2 這兩個特殊分類，-1 里面我是放的是“.”好的分類，用于訓練“.”的圖片，這樣就可以識別出小數點的數字支持.
-2 這個分類主要是其他一些無關緊要的圖片，也就是不是數字和點的都歸為這一類中.
現在訓練庫分類已經建立好了，接下來我們需要對這些分類數字進行歸一化處理，生成訓練模型. 代碼如下：
private void Button_Click_1(object sender, RoutedEventArgs e)
{
var opencvOcr = new OpencvOcr($"{path}Template\\Traindata.xml", opencvOcrConfig: null);
opencvOcr.Save($"{path}Template\\NumberWrite", outputPath: $"{path}Template\\Traindata.xml");
MessageBox.Show("生成訓練庫成功");
//var img = new Bitmap(this.txbFilaName.Text);
//var str = opencvOcr.GetText(img.ToMat(), isDebug: true);
//this.labContent.Content = str;
}
/// <summary>
/// 保存訓練模型
/// </summary>
/// <param name="dataPath"></param>
/// <param name="trainExt"></param>
/// <param name="dataPathFile"></param>
public void Save(string dataPath, string trainExt = "*.png", string outputPath = "")
{
if (string.IsNullOrEmpty(outputPath))
throw new ArgumentNullException("save dataPath is not null");
var trainingImages = this.ReadTrainingImages(dataPath, trainExt);
var samples = GetSamples(trainingImages);
var response = GetResponse(trainingImages);
//寫入到訓練庫中
using (var fs = new FileStorage(outputPath, FileStorageMode.WriteText))
{
fs.Write("samples", samples);
fs.Write("responses", response);
}
}
/// <summary>
/// 根據目錄加載檔案
/// </summary>
/// <param name="path"></param>
/// <param name="ext"></param>
/// <returns></returns>
private IList<ImageInfo> ReadTrainingImages(string path, string ext)
{
var images = new List<ImageInfo>();
var imageId = 1;
foreach (var dir in new DirectoryInfo(path).GetDirectories())
{
var groupId = int.Parse(dir.Name);
foreach (var imageFile in dir.GetFiles(ext))
{
var srcMat = new Mat(imageFile.FullName, OpenCvSharp.LoadMode.GrayScale);
var image = srcMat.ConvertFloat();
if (image == null)
{
continue;
}
images.Add(new ImageInfo
{
Image = image,
ImageId = imageId++,
ImageGroupId = groupId
});
}
}
return images;
}
/// <summary>
/// Mat 轉成另外一種存盤矩陣方式
/// </summary>
/// <param name="roi"></param>
/// <returns></returns>
public static Mat ConvertFloat(this Mat roi)
{
var resizedImage = new Mat();
var resizedImageFloat = new Mat();
Cv2.Resize(roi, resizedImage, new Size(10, 10)); //resize to 10X10
resizedImage.ConvertTo(resizedImageFloat, MatType.CV_32FC1); //convert to float
var result = resizedImageFloat.Reshape(1, 1);
return result;
}
/// <summary>
/// 獲取Samples
/// </summary>
/// <param name="trainingImages"></param>
/// <returns></returns>
private Mat GetSamples(IList<ImageInfo> trainingImages)
{
var samples = new Mat();
foreach (var trainingImage in trainingImages)
{
samples.PushBack(trainingImage.Image);
}
return samples;
}
private Mat GetResponse(IList<ImageInfo> trainingImages)
{
var labels = trainingImages.Select(x => x.ImageGroupId).ToArray();
var responses = new Mat(labels.Length, 1, MatType.CV_32SC1, labels);
var tmp = responses.Reshape(1, 1); //make continuous
var responseFloat = new Mat();
tmp.ConvertTo(responseFloat, MatType.CV_32FC1); // Convert to float
return responses;
}
到這里ocr 訓練模型以及建立好了，會在目錄中生成一個Traindata.xml 的訓練模型庫,我們來打開這個訓練模型庫檔案探索它的神秘的容顏.
到這里opencv + 數字識別分享已經完成，它的神秘面紗也就到此結束了
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/63574.html
標籤：其他