目录
背景
尝试一：整图OCR识别，然后正则匹配
尝试二：利用显著特征，直接传统方法定位，切出来识别
尝试三：yolov8训练一个统一社会信用代码、企业名称位置检测
编辑
效果
模型信息
项目
编辑
代码
下载
其他
背景
因项目需要，需要从营业执照中提取统一社会信用代码、企业名称。
尝试一：整图OCR识别，然后正则匹配
统一社会信用代码大多情况是18位数字加英文的组合，比较好正则匹配，名称结尾太多不好匹配，放弃。
尝试二：利用显著特征，直接传统方法定位，切出来识别
国徽就是个显著特征，利用国徽模板匹配，角度和位置就有了，然后用相对固定的比例系数乘以输入图片宽高，切出来后整个主要文字区域就有了，然后还是按比例从主区域中一块块的切，由于图片拍摄质量问题放弃。
尝试三：yolov8训练一个统一社会信用代码、企业名称位置检测
效果还不错，先检测出位置，再裁剪出图片OCR。
效果
模型信息
Model Properties
-------------------------
author：Ultralytics
task：detect
license：AGPL-3.0 https://ultralytics.com/license
version：8.0.184
stride：32
batch：1
imgsz：[640, 640]
names：{0: 'code', 1: 'name'}
---------------------------------------------------------------
Inputs
-------------------------
name：images
tensor：Float[1, 3, 640, 640]
---------------------------------------------------------------
Outputs
-------------------------
name：output0
tensor：Float[1, 6, 8400]
---------------------------------------------------------------
项目
VS2022+.net framework 4.8
OpenCvSharp 4.8
Microsoft.ML.OnnxRuntime 1.16.2
代码
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Windows.Forms;
namespace Onnx_Yolov8_Detect
{
public partial class frmMain : Form
{
public frmMain()
{
InitializeComponent();
}
string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
string image_path = "";
string startupPath;
string classer_path;
string model_path;
DateTime dt1 = DateTime.Now;
DateTime dt2 = DateTime.Now;
Mat image;
Mat result_image;
SessionOptions options;
InferenceSession onnx_session;
Tensor<float> input_tensor;
List<NamedOnnxValue> input_ontainer;
IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
DisposableNamedOnnxValue[] results_onnxvalue;
Tensor<float> result_tensors;
float[] result_array;
float[] factors = new float[2];
Result result;
DetectionResult result_pro;
StringBuilder sb = new StringBuilder();
private void button1_Click(object sender, EventArgs e)
{
OpenFileDialog ofd = new OpenFileDialog();
ofd.Filter = fileFilter;
if (ofd.ShowDialog() != DialogResult.OK) return;
pictureBox1.Image = null;
pictureBox2.Image = null;
textBox1.Text = "";
image_path = ofd.FileName;
pictureBox1.Image = new Bitmap(image_path);
image = new Mat(image_path);
}
private void Form1_Load(object sender, EventArgs e)
{
startupPath = Application.StartupPath + "\\model\\";
model_path = startupPath + "best.onnx";
classer_path = startupPath + "lable.txt";
// 创建输出会话
options = new SessionOptions();
options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
// 创建推理模型类，读取本地模型文件
onnx_session = new InferenceSession(model_path, options);
// 输入Tensor
input_tensor = new DenseTensor<float>(new[] { 1, 3, 640, 640 });
// 创建输入容器
input_ontainer = new List<NamedOnnxValue>();
}
private void button2_Click(object sender, EventArgs e)
{
if (image_path == "")
{
return;
}
textBox1.Text = "检测中，请稍等……";
pictureBox2.Image = null;
Application.DoEvents();
//图片缩放
image = new Mat(image_path);
int max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
Mat max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
Rect roi = new Rect(0, 0, image.Cols, image.Rows);
image.CopyTo(new Mat(max_image, roi));
factors[0] = factors[1] = (float)(max_image_length / 640.0);
//将图片转为RGB通道
Mat image_rgb = new Mat();
Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
Mat resize_image = new Mat();
Cv2.Resize(image_rgb, resize_image, new OpenCvSharp.Size(640, 640));
//输入Tensor
for (int y = 0; y < resize_image.Height; y++)
{
for (int x = 0; x < resize_image.Width; x++)
{
input_tensor[0, 0, y, x] = resize_image.At<Vec3b>(y, x)[0] / 255f;
input_tensor[0, 1, y, x] = resize_image.At<Vec3b>(y, x)[1] / 255f;
input_tensor[0, 2, y, x] = resize_image.At<Vec3b>(y, x)[2] / 255f;
}
}
//将 input_tensor 放入一个输入参数的容器，并指定名称
input_ontainer.Add(NamedOnnxValue.CreateFromTensor("images", input_tensor));
dt1 = DateTime.Now;
//运行 Inference 并获取结果
result_infer = onnx_session.Run(input_ontainer);
dt2 = DateTime.Now;
//将输出结果转为DisposableNamedOnnxValue数组
results_onnxvalue = result_infer.ToArray();
//读取第一个节点输出并转为Tensor数据
result_tensors = results_onnxvalue[0].AsTensor<float>();
result_array = result_tensors.ToArray();
resize_image.Dispose();
image_rgb.Dispose();
result_pro = new DetectionResult(classer_path, factors, 0.8f, 0.5f);
result = result_pro.process_result(result_array);
result_image = result_pro.draw_result(result, image.Clone());
if (!result_image.Empty())
{
pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
sb.Clear();
sb.AppendLine("推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms");
sb.AppendLine("------------------------------");
for (int i = 0; i < result.length; i++)
{
sb.AppendLine(string.Format("{0}：{1},({2},{3},{4},{5})"
, result.classes[i]
, result.scores[i].ToString("0.00")
, result.rects[i].TopLeft.X
, result.rects[i].TopLeft.Y
, result.rects[i].BottomRight.X
, result.rects[i].BottomRight.Y
));
}
textBox1.Text = sb.ToString();
}
else
{
textBox1.Text = "无信息";
}
}
private void pictureBox2_DoubleClick(object sender, EventArgs e)
{
Common.ShowNormalImg(pictureBox2.Image);
}
private void pictureBox1_DoubleClick(object sender, EventArgs e)
{
Common.ShowNormalImg(pictureBox1.Image);
}
}
}下载
源码下载
其他
OCR识别参考 C# OpenVINO 通用OCR识别 文字识别 中文识别 服务-CSDN博客
