use of net.sourceforge.tess4j.ITessAPI.TessResultIterator in project tess4j by nguyenq.
the class Tesseract method getWords.
/**
* Gets recognized words at specified page iterator level.
*
* @param bi input image
* @param pageIteratorLevel TessPageIteratorLevel enum
* @return list of <code>Word</code>
*/
@Override
public List<Word> getWords(BufferedImage bi, int pageIteratorLevel) {
this.init();
this.setTessVariables();
List<Word> words = new ArrayList<Word>();
try {
setImage(bi, null);
api.TessBaseAPIRecognize(handle, null);
TessResultIterator ri = api.TessBaseAPIGetIterator(handle);
TessPageIterator pi = api.TessResultIteratorGetPageIterator(ri);
api.TessPageIteratorBegin(pi);
do {
Pointer ptr = api.TessResultIteratorGetUTF8Text(ri, pageIteratorLevel);
String text = ptr.getString(0);
api.TessDeleteText(ptr);
float confidence = api.TessResultIteratorConfidence(ri, pageIteratorLevel);
IntBuffer leftB = IntBuffer.allocate(1);
IntBuffer topB = IntBuffer.allocate(1);
IntBuffer rightB = IntBuffer.allocate(1);
IntBuffer bottomB = IntBuffer.allocate(1);
api.TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB);
int left = leftB.get();
int top = topB.get();
int right = rightB.get();
int bottom = bottomB.get();
Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top));
words.add(word);
} while (api.TessPageIteratorNext(pi, pageIteratorLevel) == TRUE);
return words;
} catch (Exception e) {
return words;
} finally {
dispose();
}
}
Aggregations