如何在C#中使用MODI(Microsoft Office Document Imaging)进行串行OCR

时间:2012-06-14 14:39:46

标签: c# error-handling ms-office ocr modi

我将文档扫描为.jpg图片放在文件夹中,我想在C#中为该文件夹中的每个文档连续进行OCR。 到目前为止,我做到了这一点:

public string CheckFilesAndDoOCR(string directoryPath)
{
    directoryPath = Environment.SpecialFolder.MyPictures + "\\OCRTempPictures\\";
    IEnumerator files = Directory.GetFiles(directoryPath).GetEnumerator();
    string TheTxt = "";

    while (files.MoveNext())
    {
        // FileInfo
        FileInfo nfo = new FileInfo(Convert.ToString(files.Current));

        // Get new file name
        string fileName = AlltoJPG(nfo);

        // FileInfo (New File)
        FileInfo foo = new FileInfo(fileName);

        // Check for JPG File Format
        if (foo.Extension == ".jpg" || foo.Extension == ".JPG")
        // or // ImageFormat.Jpeg.ToString()
        {
            try
            {
                // OCR Operations...
                MODI.Document md = new MODI.Document();
                md.Create(foo.FullName);
                md.OCR(MODI.MiLANGUAGES.miLANG_ENGLISH, false, false); // OCR();
                MODI.Image image = (MODI.Image)md.Images[0];
                TheTxt = image.Layout.Text;
                md.Close(false);

                // Create text file with the same Image file name
                FileStream createFile = new FileStream(foo.DirectoryName + "\\" + foo.Name.Replace(foo.Extension,string.Empty) + ".txt", FileMode.CreateNew);

                // Save the image text in the text file
                StreamWriter writeFile = new StreamWriter(createFile);
                writeFile.Write(TheTxt);
                writeFile.Close();
            }
            catch (Exception ex)
            {
                // Expected errors
                string LogPath = System.Environment.SpecialFolder.MyPictures + "\\OCRTempPictures\\OCRInfo.txt";
                Logger(LogPath, "| Exception: Source[" + ex.Source + "] Message[" + ex.Message + "] InnerException[" + ex.InnerException + "] StackTrace[" + ex.StackTrace + "] | ");
                // MessageBox.Show(ex.Message, "OCR Exception", MessageBoxButtons.OK, MessageBoxIcon.Information);
            }
        }
    }
    return TheTxt;
}

但MODI会提供OCR running!Cant reach file.File is in use.错误..

视具体情况而定:

  • 如何避免这些错误?

  • 有没有办法停止OCR操作并耗尽所有正在使用的物品?

如果有人可以回答上述任何问题,我们将不胜感激。

2 个答案:

答案 0 :(得分:2)

这是完整的代码!感谢@Ramhound

下面的代码只指定一个装满图片的文件夹,并逐个进行OCR扫描。

    /// <summary>
    /// Gets all images inside a Folder
    /// and triggers OCR on each..
    /// </summary>
    /// <param name="directoryPath"> Path to Folder </param>
    /// <returns> Text </returns>        
    public string CheckFileAndDoOCR(string directoryPath)
    {
        string TheTxt = "";
        IEnumerator files = Directory.GetFiles(directoryPath).GetEnumerator();

        while (files.MoveNext())
        {
            // FileInfo
            FileInfo foo = new FileInfo(Convert.ToString(files.Current));

            // Check for JPG File Format
            if (foo.Extension == ".jpg" || foo.Extension == ".JPG")
            // or // ImageFormat.Jpeg.ToString()
            {
                // Start OCR Procedure
                TheTxt = DoOCR(foo.FullName);
                // Create TXT file next to ImageFile
                string txtFileName = foo.DirectoryName + "\\" + foo.Name.Replace(foo.Extension,"") + ".txt";
                FileStream createFile = new FileStream(txtFileName, FileMode.OpenOrCreate);
                // Save the text in to TXT file
                StreamWriter writeFile = new StreamWriter(createFile);
                writeFile.Write(TheTxt);
                // Close
                writeFile.Close();
                createFile.Close();
            }

            // Delete used pictures (Optional)
            /*--------------------------------------------------------------------*/
            try 
            { foo.Delete(); }
            catch (Exception ex)
            { Logger(LogPath, "| Exception: Source[" + ex.Source + "] Message[" + ex.Message + 
                "] InnerException[" + ex.InnerException + "] StackTrace[" + ex.StackTrace + "] | "); }
            /*--------------------------------------------------------------------*/
        }
        return TheTxt;
    }
    // DoOCR
    // 
    /// <summary>
    /// Start an OCR scan on given ImageFile
    /// </summary>
    /// <param name="FullPath"> Path to ImageFile </param>
    /// <returns> Text </returns>
    public string DoOCR(string FullPath)
    {
        string txt;

        // OCR Operations...
        MODI.Document md = new MODI.Document(); // Create MODI.Document
        md.Create(FullPath); // Fill MODI.Document with my file
        // Showprogress of OCR
        md.OnOCRProgress += new MODI._IDocumentEvents_OnOCRProgressEventHandler(this.ShowProgress);
        // Begin OCR
        md.OCR(MODI.MiLANGUAGES.miLANG_ENGLISH, false, false); // OCR();
        // Image from file
        MODI.Image image = (MODI.Image)md.Images[0];
        txt = image.Layout.Text;
        // Optionally you can get only first word by using word.Text
        /// Words from Image :
        // MODI.Word word = image.Layout.Words[0];
        /// Text from first Word :
        // txt = word.Text;

        // Close OCR
        word = null;
        image = null;
        md.Close(false);
        md = null;

        // Finalize
        GC.Collect();
        GC.WaitForPendingFinalizers();

        // Return Text
        return txt;
    }

答案 1 :(得分:1)

这是因为Doc1.OCR()检查多页tiff文件如果只插入单页文件,那么它会显示错误尝试使用多页tiff文件