opencv +数字识别
Posted dearroy
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了opencv +数字识别相关的知识，希望对你有一定的参考价值。
现在很多场景需要使用的数字识别，比如银行卡识别，以及车牌识别等，在AI领域有很多图像识别算法，大多是居于opencv 或者谷歌开源的tesseract 识别.
由于公司业务需要，需要开发一个客户端程序，同时需要在xp这种老古董的机子上运行，故研究了如下几个数字识别方案：
ocr 识别的不同选择方案
- tesseract
- 放弃：谷歌的开源tesseract ocr识别目前最新版本不支持xp系统
- 云端ocr 识别接口(不适用)
- 费用比较贵：
- 场景不同，我们的需求是可能毫秒级别就需要调用一次ocr 识别
- opencv
- 概念:OpenCV是一个基于BSD许可（开源）发行的跨平台计算机视觉库，可以运行在Linux、Windows、android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。
以上几种ocr 识别比较，最后选择了opencv 的方式进行ocr 数字识别,下面讲解通过ocr识别的基本流程和算法.
opencv 数字识别流程及算法解析
要通过opencv 进行数字识别离不开训练库的支持，需要对目标图片进行大量的训练，才能做到精准的识别出目标数字;下面我会分别讲解图片训练的过程及识别的过程.
opencv 识别算法原理
- 比如下面一张图片，需要从中识别出正确的数字，需要对图片进行灰度、二值化、腐蚀、膨胀、寻找数字轮廓、切割等一系列操作.
原图
灰度化图
二值化图
寻找轮廓
识别后的结果图
以上就是简单的图片进行灰度化、二值化、寻找数字轮廓得到的识别结果(这是基于我之前训练过的数字模型下得到的识别结果)
有些图片比较赋值，比如存在背景斜杠等的图片则需要一定的腐蚀或者膨胀等处理，才能寻找到正确的数字轮廓.
上面的说到我这里使用的是opencv 图像处理库进行的ocr 识别，那我这里简单介绍下C# 怎么使用opencv 图像处理看;
为了在xp上能够运行 我这里通过nuget 包引用了 OpenCvSharp-AnyCPU 第三方库,它使用的是opencv 2410 版本,你们如果不考虑xp系统的情况下开源使用最新的版本，最新版本支持了更多的识别算法.
右击你的个人项目，选择“管理Nuget程序包”。在包管理器页面中，点击“浏览”选项，然后在搜索框中键入“OpenCvSharp-AnyCPU”。选择最顶端的正确项目，并在右侧详情页中点击“安装”，等待安装完成即可。
以上的核心代码如下:
private void runSimpleOCR(string pathName)
{
//构造opcvOcr 库，这里的是我单独对opencv 库进行的一次封装,加载训练库模板
var opencvOcr = new OpencvOcr($"{path}TemplateTraindata.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();
//核心识别方法
var str = opencvOcr.GetText(mat, isDebug: true);
this.labContent.Content = str;
}
opencvOcr 的核心代码如下
#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>
/// 构造函数
/// </summary>
/// <param name="path">训练库完整路径</param>
/// <param name="opencvOcrConfig">OCR相关配置信息</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>
/// 加载Knn 训练库模型
/// </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 识别,仅仅只能识别单行数字
/// </summary>
/// <param name="kNearest">训练库</param>
/// <param name="path">要识别的图片路径</param>
public override string GetText(Mat src, bool isDebug = false)
{
this._isDebug = isDebug;
#region 图片处理
var respMat = MatProcessing(src, isDebug);
if (respMat == null)
return "";
#endregion
#region 查找轮廓
var sortRect = FindContours(respMat.FindContoursMat);
#endregion
return GetText(sortRect, respMat.ResourcMat, respMat.RoiResultMat);
}
/// <summary>
/// 查找轮廓
/// </summary>
/// <param name="src"></param>
/// <returns></returns>
private List<Rect> FindContours(Mat src)
{
try
{
#region 查找轮廓
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 单行排序（目前仅仅支持单行文字,多行文字顺序可能不对，按照x坐标进行排序）
var sortRect = GetSortRect(contours, hierarchyIndexes);
sortRect = sortRect.OrderBy(item => item.X).ToList();
#endregion
return sortRect;
}
catch { }
return null;
}
/// <summary>
/// 获得切割后的数量列表
/// </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 自定义的算法
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 默认算法
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>
/// 对查找的轮廓数据进行训练模型匹配，这里使用的是KNN 匹配算法
/// </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 绘制矩形
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 单个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 绘制及输出切割信息库
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 调试模式显示过程
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>
/// 图片处理算法
/// </summary>
/// <param name="src"></param>
/// <param name="isDebug"></param>
/// <returns></returns>
public ImageProcessModel MatProcessing(Mat src, bool isDebug = false)
{
src.IsDebugShow("原图", 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 = 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 图片处理开放出去的配置对象实体如下：
public class OpencvOcrConfig
{
/// <summary>
/// 放大程度级别 默认2
/// </summary>
public double ZoomLevel { set; get; }
/// <summary>
/// 腐蚀级别 默认2.5
/// </summary>
public double ErodeLevel { set; get; }
/// <summary>
/// 膨胀
/// </summary>
public double DilateLevel { set; get; }
/// <summary>
/// 阀值
/// </summary>
public double ThresholdValue { set; get; }
/// <summary>
/// 图片处理算法,用逗号隔开
/// </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 图片处理算法扩展方法如下：
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 异常", 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 = 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;
}
/// <summary>
/// 是否调试显示
/// </summary>
/// <param name="src"></param>
/// <param name="name"></param>
/// <param name="isDebug"></param>
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 { }
}
/// <summary>
/// Mat 转成另外一种存储矩阵方式
/// </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>
/// 腐蚀
/// </summary>
/// <param name="mat"></param>
/// <returns></returns>
public static Mat ToErode(this Mat mat, double level)
{
#region level 2.5时默认的,自动会判断是否需要腐蚀
if (level < 1)
{
return mat;
}
if (level == 2.5)
{
if (!mat.IsErode())
return mat;
}
#endregion
var erode = new Mat();
var copyMat = new Mat();
mat.CopyTo(copyMat);
Cv2.Erode(mat, erode, Cv2.GetStructuringElement(StructuringElementShape.Ellipse, new Size(level, level)));
return erode;
}
/// <summary>
/// 膨胀
/// </summary>
/// <param name="mat"></param>
/// <returns></returns>
public static Mat ToDilate(this Mat mat, int level)
{
if (level <= 0)
return mat;
var dilate = new Mat();
Cv2.Dilate(mat, dilate, Cv2.GetStructuringElement(StructuringElementShape.Ellipse, new Size(level, level)));
return dilate;
//return mat;
}
/// <summary>
/// mat 转Roi
/// </summary>
/// <param name="image"></param>
/// <param name="boundingRect"></param>
/// <returns></returns>
public static Mat GetROI(this Mat image, Rect boundingRect)
{
try
{
return new Mat(image, boundingRect); //Crop the image
}
catch
{
}
return null;
}
/// <summary>
/// 获取平均阀值
/// </summary>
/// <param name="mat"></param>
/// <returns></returns>
public static int GetMeanThreshold(this Mat mat)
{
var width = mat.Width;
var height = mat.Height;
var m = mat.Reshape(1, width * height);
return (int)m.Sum() / (width * height);
}
/// <summary>
/// 获得二值化阀值
/// </summary>
/// <param name="bitmap"></param>
/// <returns></returns>
public static int GetMeanThreshold(this System.Drawing.Bitmap bitmap)
{
using (var mat = bitmap.ToMat())
using (var grap = mat.ToGrey())
{
return grap.GetMeanThreshold();
}
}
public static bool IsErode(this System.Drawing.Bitmap bitmap)
{
using (var mat = bitmap.ToMat())
using (var grap = mat.ToGrey())
{
var thresholdValue = grap.GetMeanThreshold();
using (var threshold = grap.ToThreshold(thresholdValue, ThresholdType.BinaryInv))
{
return threshold.IsErode();
}
}
}
/// <summary>
/// 放大
/// </summary>
/// <param name="img"></param>
/// <param name="times"></param>
/// <returns></returns>
public static Mat ToZoom(this Mat img, double times)
{
if (times <= 0)
return img;
var width = img.Width * times;
var height = img.Height * times;
img = img.Resize(new Size(width, height), 0, 0, Interpolation.NearestNeighbor);
return img;
}
/// <summary>
/// 均值滤波
/// </summary>
/// <param name="img"></param>
/// <returns></returns>
public static Mat ToBlur(this Mat img)
{
return img.Blur(new Size(3, 3));
}
public static Mat Compress(this Mat img)
{
var width = 28.0 * img.Width / img.Height;
var fWidth = width / img.Width;
var fHeight = 28.0 / img.Height;
img = img.Resize(new Size(width, 28), fWidth, fHeight, Interpolation.NearestNeighbor);
return img;
}
public static bool MatPixelEqual(this Mat src, Mat are)
{
var width = src.Width;
var height = src.Height;
var sum = width * height;
for (int row = 0; row < height; row++)
{
for (int col = 0; col < width; col++)
{
byte p = src.At<byte>(row, col); //获对应矩阵坐标的取像素
byte pAre = are.At<byte>(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<byte>(row, col); //获对应矩阵坐标的取像素
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<byte>(row, col); //获对应矩阵坐标的取像素
if (Convert.ToInt32(p) == color.R)
{
value++;
}
}
}
return value;
}
/// <summary>
/// 是否需要二值化反转
/// </summary>
/// <param name="threshold"></param>
/// <returns></returns>
public static bool IsBinaryInv(this Mat threshold)
{
var width = threshold.Width;
var height = threshold.Height;
var sum = Convert.ToDouble(width * height);
var black = GetPixelCount(threshold, System.Drawing.Color.Black);
return (Convert.ToDouble(black) / sum) < 0.5;
}
/// <summary>
/// 是否需要腐蚀
/// </summary>
/// <param name="mat"></param>
/// <returns></returns>
public static bool IsErode(this Mat mat)
{
var percent = mat.GetPercent();
return percent >= 0.20;
}
/// <summary>
/// 获得白色像素占比
/// </summary>
/// <param name="threshold"></param>
/// <returns></returns>
public static double GetPercent(this Mat threshold)
{
var width = threshold.Width;
var height = threshold.Height;
var sum = Convert.ToDouble(width * height);
var white = GetPixelCount(threshold, System.Drawing.Color.White);
return (Convert.ToDouble(white) / sum);
}
/// <summary>
/// 根据模板查找目标图片的在原图标中的开始位置坐标
/// </summary>
/// <param name="source"></param>
/// <param name="template"></param>
/// <param name="matchTemplateMethod"></param>
/// <returns></returns>
public static Point FindTemplate(this Mat source, Mat template, MatchTemplateMethod matchTemplateMethod = MatchTemplateMethod.SqDiffNormed)
{
if (source == null)
return new OpenCvSharp.CPlusPlus.Point();
var result = new Mat();
Cv2.MatchTemplate(source, template, result, matchTemplateMethod);
Cv2.MinMaxLoc(result, out OpenCvSharp.CPlusPlus.Point minVal, out OpenCvSharp.CPlusPlus.Point maxVal);
var topLeft = new OpenCvSharp.CPlusPlus.Point();
if (matchTemplateMethod == MatchTemplateMethod.SqDiff || matchTemplateMethod == MatchTemplateMethod.SqDiffNormed)
{
topLeft = minVal;
}
else
{
topLeft = maxVal;
}
return topLeft;
}
}
以上代码中开源对图片进行轮廓切割，同时会生成切割后的图片代码如下
#region 绘制及输出切割信息库
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 = $"{templatePath}/{contourIndex}_{detectedClass.ToString()}.png";
Cv2.ImWrite(templatePathFile, roi);
if (!roi.IsDisposed)
{
roi.Dispose();
}
}
catch {}
});
}
切割后的图片如下：
这里我已经对数字进行切割好了，接下来就是需要对0-9 这些数字进行分类(建立文件夹进行数字归类)，如下：
图中的每一个分类都是我事先切割好的数字图片,图中有-1 和-2 这两个特殊分类，-1 里面我是放的是“.”好的分类，用于训练“.”的图片，这样就可以识别出小数点的数字支持.
-2 这个分类主要是其他一些无关紧要的图片，也就是不是数字和点的都归为这一类中.
现在训练库分类已经建立好了，接下来我们需要对这些分类数字进行归一化处理，生成训练模型. 代码如下：
private void Button_Click_1(object sender, RoutedEventArgs e)
{
var opencvOcr = new OpencvOcr($"{path}TemplateTraindata.xml", opencvOcrConfig: null);
opencvOcr.Save($"{path}TemplateNumberWrite", outputPath: $"{path}TemplateTraindata.xml");
MessageBox.Show("生成训练库成功");
//var img = new Bitmap(this.txbFilaName.Text);
//var str = opencvOcr.GetText(img.ToMat(), isDebug: true);
//this.labContent.Content = str;
}
/// <summary>
/// 保存训练模型
/// </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);
//写入到训练库中
using (var fs = new FileStorage(outputPath, FileStorageMode.WriteText))
{
fs.Write("samples", samples);
fs.Write("responses", response);
}
}
/// <summary>
/// 根据目录加载文件
/// </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 转成另外一种存储矩阵方式
/// </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>
/// 获取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;
}
到这里ocr 训练模型以及建立好了，会在目录中生成一个Traindata.xml 的训练模型库,我们来打开这个训练模型库文件探索它的神秘的容颜.
到这里opencv + 数字识别分享已经完成，它的神秘面纱也就到此结束了
以上是关于opencv +数字识别的主要内容，如果未能解决你的问题，请参考以下文章
在 Python 多处理进程中运行较慢的 OpenCV 代码片段
OpenCV-Python实战（番外篇）——利用 SVM 算法识别手写数字