// Returns an Imagedata containing the image of the given box,
// and ground truth boxes/truth text if available in the input.
// The image is not normalized in any way.
ImageData* Tesseract::GetLineData(const TBOX& line_box,
const GenericVector<TBOX>& boxes,
const GenericVector<STRING>& texts,
int start_box, int end_box,
const BLOCK& block) {
TBOX revised_box;
ImageData* image_data = GetRectImage(line_box, block, kImagePadding,
&revised_box);
if (image_data == NULL) return NULL;
image_data->set_page_number(applybox_page);
// Copy the boxes and shift them so they are relative to the image.
FCOORD block_rotation(block.re_rotation().x(), -block.re_rotation().y());
ICOORD shift = -revised_box.botleft();
GenericVector<TBOX> line_boxes;
GenericVector<STRING> line_texts;
for (int b = start_box; b < end_box; ++b) {
TBOX box = boxes[b];
box.rotate(block_rotation);
box.move(shift);
line_boxes.push_back(box);
line_texts.push_back(texts[b]);
}
GenericVector<int> page_numbers;
page_numbers.init_to_size(line_boxes.size(), applybox_page);
image_data->AddBoxes(line_boxes, line_texts, page_numbers);
return image_data;
}
// Recognizes a word or group of words, converting to WERD_RES in *words.
// Analogous to classify_word_pass1, but can handle a group of words as well.
void Tesseract::LSTMRecognizeWord(const BLOCK& block, ROW *row, WERD_RES *word,
PointerVector<WERD_RES>* words) {
TBOX word_box = word->word->bounding_box();
// Get the word image - no frills.
if (tessedit_pageseg_mode == PSM_SINGLE_WORD ||
tessedit_pageseg_mode == PSM_RAW_LINE) {
// In single word mode, use the whole image without any other row/word
// interpretation.
word_box = TBOX(0, 0, ImageWidth(), ImageHeight());
} else {
float baseline = row->base_line((word_box.left() + word_box.right()) / 2);
if (baseline + row->descenders() < word_box.bottom())
word_box.set_bottom(baseline + row->descenders());
if (baseline + row->x_height() + row->ascenders() > word_box.top())
word_box.set_top(baseline + row->x_height() + row->ascenders());
}
ImageData* im_data = GetRectImage(word_box, block, kImagePadding, &word_box);
if (im_data == NULL) return;
lstm_recognizer_->RecognizeLine(*im_data, true, classify_debug_level > 0,
kWorstDictCertainty / kCertaintyScale,
lstm_use_matrix, &unicharset, word_box, 2.0,
false, words);
delete im_data;
SearchWords(words);
}
IplImage* LPRotateFromRect(const IplImage* src_lpr,CvRect rect,int color)
{
double angle;
IplImage* src,*gray,*bw,*dst;
gray = cvCreateImage(cvSize(rect.width,rect.height),IPL_DEPTH_8U,1);
bw = cvCreateImage(cvSize(rect.width,rect.height),IPL_DEPTH_8U,1);
dst = cvCreateImage(cvSize(rect.width,rect.height),src_lpr->depth,src_lpr->nChannels);
src = GetRectImage(src_lpr,rect);
cvConvertImage(src,gray,CV_BGR2GRAY);
AdjustContrast(gray,gray,100);
ThresholdPartIter(gray,bw,color,3);
// cvShowImage("img_bw",bw);
cvWaitKey(0);
angle = img_rotate_angle(src);
rotate_img(src,dst,angle);
cvReleaseImage(&src);
cvReleaseImage(&gray);
cvReleaseImage(&bw);
return dst;
}