/**
* Gets recognized text.
*
* @return the recognized text
*/
private String getOCRText() {
Pointer utf8Text =
hocr ? api.TessBaseAPIGetHOCRText(handle, pageNum - 1) : api.TessBaseAPIGetUTF8Text(handle);
String str = utf8Text.getString(0);
api.TessDeleteText(utf8Text);
return str;
}
/** Initializes Tesseract engine. */
private void init() {
pageNum = 0;
api = TessAPI.INSTANCE;
handle = api.TessBaseAPICreate();
api.TessBaseAPIInit2(handle, datapath, language, ocrEngineMode);
api.TessBaseAPISetPageSegMode(handle, psm);
}
/**
* Sets image to be processed.
*
* @param xsize width of image
* @param ysize height of image
* @param buf pixel data
* @param rect the bounding rectangle defines the region of the image to be recognized. A
* rectangle of zero dimension or <code>null</code> indicates the whole image.
* @param bpp bits per pixel, represents the bit depth of the image, with 1 for binary bitmap, 8
* for gray, and 24 for color RGB.
*/
private void setImage(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) {
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.isEmpty()) {
api.TessBaseAPISetRectangle(handle, rect.x, rect.y, rect.width, rect.height);
}
}
/** Sets Tesseract's internal parameters. */
private void setTessVariables() {
Enumeration<?> em = prop.propertyNames();
while (em.hasMoreElements()) {
String key = (String) em.nextElement();
api.TessBaseAPISetVariable(handle, key, prop.getProperty(key));
}
}
/** Releases all of the native resources used by this instance. */
private void dispose() {
api.TessBaseAPIDelete(handle);
}