Question

我正在将我的OCR应用程序从c ++转换为java。使用Tess4J我想得到每个单词的边界框。但是，显然TessResultIterator没有提供任何方法。所以我想，如果有可能以某种方式得到这些数据？

这是我目前的代码：

TessBaseAPI api = TessAPI1.TessBaseAPICreate();
TessAPI1.TessBaseAPIInit3(api, path, lang);
TessAPI1.TessBaseAPISetPageSegMode(api, TessAPI1.TessPageSegMode.PSM_AUTO);
TessAPI1.TessBaseAPISetImage(api, img, w, h, bpp, bpp*w);
TessAPI1.TessBaseAPIGetUTF8Text(api);
TessResultIterator it = TessAPI1.TessBaseAPIGetIterator(api);

在c ++中，我可以继续这样：

char* text = it->GetUTF8Text(tesseract::RIL_WORD); 
int left, top, right, bttm;
it->BoundingBox(tesseract::RIL_WORD, &left, &top, &right, &bttm);

Answer 1

您可以尝试以下代码段吗？我没有彻底测试它。

TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(api);
TessPageIterator pi = TessAPI1.TessResultIteratorGetPageIterator(ri);
String str = TessAPI1.TessResultIteratorGetUTF8Text(ri, TessPageIteratorLevel.RIL_WORD);
IntBuffer leftB = IntBuffer.allocate(1);
IntBuffer topB = IntBuffer.allocate(1);
IntBuffer rightB = IntBuffer.allocate(1);
IntBuffer bottomB = IntBuffer.allocate(1);
TessAPI1.TessPageIteratorBoundingBox(pi, TessPageIteratorLevel.RIL_WORD, leftB, topB, rightB, bottomB);
int left = leftB.get();
int top = topB.get();
int right = rightB.get();
int bottom = bottomB.get();

Answer 2

    logger.info("TessBaseAPIGetIterator");
    File tiff = new File(testResourcesDataPath, "eurotext.tif");
    BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF
    ByteBuffer buf = ImageIOHelper.convertImageData(image);
    int bpp = image.getColorModel().getPixelSize();
    int bytespp = bpp / 8;
    int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0);
    TessAPI1.TessBaseAPIInit3(handle, datapath, language);
    TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO);
    TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl);
    ETEXT_DESC monitor = new ETEXT_DESC();
    ITessAPI.TimeVal timeout = new ITessAPI.TimeVal();
    timeout.tv_sec = new NativeLong(0L); // time > 0 causes blank ouput
    monitor.end_time = timeout;
    ProgressMonitor pmo = new ProgressMonitor(monitor);
    pmo.start();
    TessAPI1.TessBaseAPIRecognize(handle, monitor);
    logger.info("Message: " + pmo.getMessage());
    TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle);
    TessPageIterator pi = TessAPI1.TessResultIteratorGetPageIterator(ri);
    TessAPI1.TessPageIteratorBegin(pi);
    logger.info("Bounding boxes:\nchar(s) left top right bottom confidence font-attributes");
    int level = TessPageIteratorLevel.RIL_WORD;

    // int height = image.getHeight();
    do {
        Pointer ptr = TessAPI1.TessResultIteratorGetUTF8Text(ri, level);
        String word = ptr.getString(0);
        TessAPI1.TessDeleteText(ptr);
        float confidence = TessAPI1.TessResultIteratorConfidence(ri, level);
        IntBuffer leftB = IntBuffer.allocate(1);
        IntBuffer topB = IntBuffer.allocate(1);
        IntBuffer rightB = IntBuffer.allocate(1);
        IntBuffer bottomB = IntBuffer.allocate(1);
        TessAPI1.TessPageIteratorBoundingBox(pi, level, leftB, topB, rightB, bottomB);
        int left = leftB.get();
        int top = topB.get();
        int right = rightB.get();
        int bottom = bottomB.get();
        System.out.print(String.format("%s %d %d %d %d %f", word, left, top, right, bottom, confidence));
        // logger.info(String.format("%s %d %d %d %d", str, left, height - bottom, right, height - top)); //
        // training box coordinates

        IntBuffer boldB = IntBuffer.allocate(1);
        IntBuffer italicB = IntBuffer.allocate(1);
        IntBuffer underlinedB = IntBuffer.allocate(1);
        IntBuffer monospaceB = IntBuffer.allocate(1);
        IntBuffer serifB = IntBuffer.allocate(1);
        IntBuffer smallcapsB = IntBuffer.allocate(1);
        IntBuffer pointSizeB = IntBuffer.allocate(1);
        IntBuffer fontIdB = IntBuffer.allocate(1);
        String fontName = TessAPI1.TessResultIteratorWordFontAttributes(ri, boldB, italicB, underlinedB,
                monospaceB, serifB, smallcapsB, pointSizeB, fontIdB);
        boolean bold = boldB.get() == TRUE;
        boolean italic = italicB.get() == TRUE;
        boolean underlined = underlinedB.get() == TRUE;
        boolean monospace = monospaceB.get() == TRUE;
        boolean serif = serifB.get() == TRUE;
        boolean smallcaps = smallcapsB.get() == TRUE;
        int pointSize = pointSizeB.get();
        int fontId = fontIdB.get();
        logger.info(String.format("  font: %s, size: %d, font id: %d, bold: %b,"
                + " italic: %b, underlined: %b, monospace: %b, serif: %b, smallcap: %b", fontName, pointSize,
                fontId, bold, italic, underlined, monospace, serif, smallcaps));
    } while (TessAPI1.TessPageIteratorNext(pi, level) == TRUE);

    assertTrue(true);

Tess4J：如何使用ResultIterator？

2 个答案: