C# Sdcb.OpenVINO.PaddleOCR 离线使用-CSDN博客

本文链接：https://blog.csdn.net/ldg200731589/article/details/134443054

1.使用NuGet 下载安装

OpenCvSharp4
OpenCVSharp4.runtime.win
Sdcb.OpenVINO
Sdcb.OpenVINO.runtime.win-x64
Sdcb.OpenVINO.PaddleOCR
Sdcb.OpenVINO.PaddleOCR.Models.Online

2.编写使用代码

我这个方法是传入图片的字节数据

 public class VinoOcrHandler
 {
     public static async Task<string> handlerImgAsync(byte[] sampleImageData)
     {

         Settings.GlobalModelDirectory = ".\\Models";
       
         FullOcrModel model = await OnlineFullModels.ChineseV3.DownloadAsync();            
      

         using (PaddleOcrAll all = new PaddleOcrAll(model)
         {
             AllowRotateDetection = true, /* 允许识别有角度的文字 */
             Enable180Classification = false, /* 允许识别旋转角度大于90度的文字 */
         })
         {
             // Load local file by following code:
             // using (Mat src2 = Cv2.ImRead(@"C:\test.jpg"))
             using (Mat src = Cv2.ImDecode(sampleImageData, ImreadModes.Color))
             {
                 PaddleOcrResult result = all.Run(src);
                 //Console.WriteLine("Detected all texts: \n" + result.Text);
                 return result.Text;
             }
         }
     }

 }

Settings.GlobalModelDirectory = ".\\Models";

非常重要，在初次使用时，会将支持文件下载到这个目录，在发布的时候需要把这个目录拷贝到对应的目录下