java - 未进入 tessract 方法 doOCR(File imageFile) 内部-6ren

java - 未进入 tessract 方法 doOCR(File imageFile) 内部

转载作者：行者123 更新时间：2023-12-01 14:09:56

我创建了一个小型控制台应用程序来对 .tiff 图像文件执行 OCR，我使用 tess4j 完成了此操作。

public class JavaApplication10 {

/**
 * @param args the command line arguments
 */
public static void main(String[] args) 
{
    File imageFile = new File("C:\\Users\\Manesh\\Desktop\\license_plate.tiff");

    Tesseract instance = Tesseract.getInstance();  // JNA Interface Mapping

    // Tesseract1 instance = new Tesseract1(); // JNA Direct Mapping
    try 
    {
        String result = instance.doOCR(imageFile); //Empty result
        System.out.println("hahahaha");
        System.out.println("The result is: " + result);
    }
    catch (TesseractException e) 
    {
        System.out.println("error:" + e);
    }
  }
}

当我查看 Tesseract 类的代码并插入几个 System.out.println 时，我没有在结果中获得任何值，这些值也没有在控制台中打印。我的 Tesseract 代码如下。

public class Tesseract 
{

private static Tesseract instance;
private final static Rectangle EMPTY_RECTANGLE = new Rectangle();
private String language = "eng";
private String datapath = "tessdata";
private int psm = TessAPI.TessPageSegMode.PSM_AUTO;
private boolean hocr;
private int pageNum;
private int ocrEngineMode = TessAPI.TessOcrEngineMode.OEM_DEFAULT;
private Properties prop = new Properties();
public final static String htmlBeginTag =
        "<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\""
        + " \"http://www.w3.org/TR/html4/loose.dtd\">\n"
        + "<html>\n<head>\n<title></title>\n"
        + "<meta http-equiv=\"Content-Type\" content=\"text/html;"
        + "charset=utf-8\" />\n<meta name='ocr-system' content='tesseract'/>\n"
        + "</head>\n<body>\n";
public final static String htmlEndTag = "</body>\n</html>\n";
private Tesseract() 
{
    System.setProperty("jna.encoding", "UTF8");
}
public static synchronized Tesseract getInstance() 
{
    if (instance == null) 
    {
        instance = new Tesseract();
    }

    return instance;
}
public void setDatapath(String datapath) 
{
    this.datapath = datapath;
}
public void setLanguage(String language) 
{
    this.language = language;
}
public void setOcrEngineMode(int ocrEngineMode) 
{
    this.ocrEngineMode = ocrEngineMode;
}

public void setPageSegMode(int mode) 
{
    this.psm = mode;
}

public void setHocr(boolean hocr) 
{
    this.hocr = hocr;
    prop.setProperty("tessedit_create_hocr", hocr ? "1" : "0");
}

public void setTessVariable(String key, String value) 
{
    prop.setProperty(key, value);
}

public String doOCR(File imageFile) throws TesseractException 
{
    System.out.println("hiiiiiii "); //not getting printed
    return doOCR(imageFile, null);
}


public String doOCR(File imageFile, Rectangle rect) throws TesseractException 
{
    try 
    {
     System.out.println("be: "); //not getting printed
     return doOCR(ImageIOHelper.getIIOImageList(imageFile), rect);
    } 
    catch (IOException ioe) 
    {
        throw new TesseractException(ioe);
    }
}

public String doOCR(BufferedImage bi) throws TesseractException 
{
    return doOCR(bi, null);
}


public String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException 
{
    IIOImage oimage = new IIOImage(bi, null, null);
    List<IIOImage> imageList = new ArrayList<IIOImage>();
    imageList.add(oimage);
    return doOCR(imageList, rect);
}

public String doOCR(List<IIOImage> imageList, Rectangle rect) throws TesseractException 
{
    StringBuilder sb = new StringBuilder();
    pageNum = 0;

    for (IIOImage oimage : imageList) 
    {
        pageNum++;
        try 
        {
            ByteBuffer buf = ImageIOHelper.getImageByteBuffer(oimage);
            RenderedImage ri = oimage.getRenderedImage();
            String pageText = doOCR(ri.getWidth(), ri.getHeight(), buf, rect,     ri.getColorModel().getPixelSize());
            sb.append(pageText);
        } 
        catch (IOException ioe) 
        {
            //skip the problematic image
            System.err.println(ioe.getMessage());
        }
    }

    if (hocr) 
    {
        sb.insert(0, htmlBeginTag).append(htmlEndTag);
    }
    return sb.toString();
}


public String doOCR(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) throws TesseractException 
{
    TessAPI api = TessAPI.INSTANCE;
    TessAPI.TessBaseAPI handle = api.TessBaseAPICreate();
    api.TessBaseAPIInit2(handle, datapath, language, ocrEngineMode);
    api.TessBaseAPISetPageSegMode(handle, psm);

    Enumeration em = prop.propertyNames();
    while (em.hasMoreElements()) 
    {
        String key = (String) em.nextElement();
        api.TessBaseAPISetVariable(handle, key, prop.getProperty(key));
    }

    int bytespp = bpp / 8;
    int bytespl = (int) Math.ceil(xsize * bpp / 8.0);
    api.TessBaseAPISetImage(handle, buf, xsize, ysize, bytespp, bytespl);

    if (rect != null && !rect.equals(EMPTY_RECTANGLE)) 
    {
        api.TessBaseAPISetRectangle(handle, rect.x, rect.y, rect.width, rect.height);
    }

    Pointer utf8Text = hocr ? api.TessBaseAPIGetHOCRText(handle, pageNum - 1) : api.TessBaseAPIGetUTF8Text(handle);
    String str = utf8Text.getString(0);
    api.TessDeleteText(utf8Text);
    api.TessBaseAPIDelete(handle);

    return str;
}
}

我是第一次使用 tesseract，请告诉我我做错了什么。

最佳答案

对于 Tesseract，你必须传递你想要进行 OCR 的确切图像，例如，假设你正在读取玩家的宝箱号码，如果你传递宝箱号码的裁剪和灰度图像，它只会读取文本，就好像您传递整个图像一样，它不会读取。您可以使用以下方法来执行此操作。

String doOCR(BufferedImage img, Rectangle rect);

好吧，我直接传递裁剪后的图像，所以我没有使用上面的方法，我的代码现在看起来像这个仪式。

public class JavaApplication10 {

/**
 * @param args the command line arguments
 */
public static void main(String[] args) 
{
    try 
    {           
        File imageFile = new File("C:\\Users\\Manesh\\Desktop\\116.jpg"); //This is a cropped image of a chest number.
        BufferedImage img =  ImageIO.read(imageFile);
        //BufferedImageOp grayscaleConv =  new ColorConvertOp(colorFrame.getColorModel().getColorSpace(), grayscaleConv.filter(colorFrame, grayFrame);
        Tesseract instance = Tesseract.getInstance();  // JNA Interface Mapping
        ColorSpace cs = ColorSpace.getInstance(ColorSpace.CS_GRAY);  
        ColorConvertOp op = new ColorConvertOp(cs, null);
        op.filter(img, img); // gray scaling the image
        // Tesseract1 instance = new Tesseract1(); // JNA Direct Mapping
        try 
        {   
            String result = instance.doOCR(img);
            System.out.println("hahahaha");
            System.out.println("The result is: " + result);
        }
        catch (TesseractException e) 
        {
            System.out.println("error:" + e);
        }
    }
    catch (IOException ex) 
    {
        Logger.getLogger(JavaApplication10.class.getName()).log(Level.SEVERE, null, ex);
    }
  }
}