![]() ![]() Get the given level kind of components (block, textline, word etc.) as a leptonica-style Boxa, Pixa pair, in reading order. If text_only is true, then only text components are returned. If raw_image is true, then portions of the original image are extracted instead of the thresholded image and padded with raw_padding. If blockids is not NULL, the paragraph-id of each component with its block is also returned as an array of one element per component. If blockids is not NULL, the block-id of each component is also returned as an array of one element per component. The following methods break TesseractRect into pieces, so you can get hold of the thresholded image, get the text in different formats, get bounding boxes, confidences etc. Tesseract::TessBaseAPI::DeleteBlockList (BLOCK_LIST *block_list) Tesseract::TessBaseAPI::FindLinesCreateBlockList () Tesseract::TessBaseAPI::GetBlockTextOrientations (int **block_orientation, bool **vertical_writing) Tesseract::TessBaseAPI::set_min_orientation_margin (double margin) Tesseract::TessBaseAPI::GetCubeRecoContext () const Tesseract::TessBaseAPI::InitTruthCallback (TruthCallback *cb) Tesseract::TessBaseAPI::tesseract () const Tesseract::TessBaseAPI::NormalizeTBLOB ( TBLOB *tblob, ROW *row, bool numeric_mode) Tesseract::TessBaseAPI::MakeTBLOB (Pix *pix) Tesseract::TessBaseAPI::MakeTessOCRRow (float baseline, float xheight, float descender, float ascender) Tesseract::TessBaseAPI::NumDawgs () const Tesseract::TessBaseAPI::GetDawg (int i) const Tesseract::TessBaseAPI::GetUnichar (int unichar_id) Tesseract::TessBaseAPI::RunAdaptiveClassifier ( TBLOB *blob, int num_max_matches, int *unichar_ids, float *ratings, int *num_matches_returned) Tesseract::TessBaseAPI::FindRowForBox (BLOCK_LIST *blocks, int left, int top, int right, int bottom) Tesseract::TessBaseAPI::GetFeaturesForBlob ( TBLOB *blob, INT_FEATURE_STRUCT *int_features, int *num_features, int *feature_outline_index) Tesseract::TessBaseAPI::DetectOS ( OSResults *) Tesseract::TessBaseAPI::SetFillLatticeFunc (FillLatticeFunc f) Tesseract::TessBaseAPI::SetProbabilityInContextFunc (ProbabilityInContextFunc f) Tesseract::TessBaseAPI::SetDictFunc (DictFunc f) Tesseract::TessBaseAPI::GetTextDirection (int *out_offset, float *out_slope) Tesseract::TessBaseAPI::IsValidCharacter (const char *utf8_character) Tesseract::TessBaseAPI::IsValidWord (const char *word) Tesseract::TessBaseAPI::ClearPersistentCache () Tesseract::TessBaseAPI::AdaptToWordStr (PageSegMode mode, const char *wordstr) Tesseract::TessBaseAPI::AllWordConfidences () Tesseract::TessBaseAPI::GetBoxText (int page_number) Tesseract::TessBaseAPI::GetHOCRText (int page_number) Tesseract::TessBaseAPI::GetMutableIterator () Tesseract::TessBaseAPI::ProcessPage (Pix *pix, int page_index, const char *filename, const char *retry_config, int timeout_millisec, TessResultRenderer *renderer) Tesseract::TessBaseAPI::ProcessPagesInternal (const char *filename, const char *retry_config, int timeout_millisec, TessResultRenderer *renderer) Tesseract::TessBaseAPI::ProcessPages (const char *filename, const char *retry_config, int timeout_millisec, TessResultRenderer *renderer) Tesseract::TessBaseAPI::RecognizeForChopTest ( ETEXT_DESC *monitor) Tesseract::TessBaseAPI::Recognize ( ETEXT_DESC *monitor) Tesseract::TessBaseAPI::AnalyseLayout (bool merge_similar_words) Tesseract::TessBaseAPI::DumpPGM (const char *filename) Tesseract::TessBaseAPI::GetThresholdedImageScaleFactor () const Tesseract::TessBaseAPI::GetComponentImages (const PageIteratorLevel level, const bool text_only, Pixa **pixa, int **blockids) Tesseract::TessBaseAPI::GetComponentImages (const PageIteratorLevel level, const bool text_only, const bool raw_image, const int raw_padding, Pixa **pixa, int **blockids, int **paraids) Tesseract::TessBaseAPI::GetConnectedComponents (Pixa **cc) Tesseract::TessBaseAPI::GetWords (Pixa **pixa) Tesseract::TessBaseAPI::GetStrips (Pixa **pixa, int **blockids) Tesseract::TessBaseAPI::GetTextlines (Pixa **pixa, int **blockids) Tesseract::TessBaseAPI::GetTextlines (const bool raw_image, const int raw_padding, Pixa **pixa, int **blockids, int **paraids) ![]() Tesseract::TessBaseAPI::GetRegions (Pixa **pixa) Tesseract::TessBaseAPI::GetThresholdedImage () Tesseract::TessBaseAPI::SetThresholder (ImageThresholder *thresholder) Tesseract::TessBaseAPI::SetRectangle (int left, int top, int width, int height) Tesseract::TessBaseAPI::SetSourceResolution (int ppi) Tesseract::TessBaseAPI::SetImage (Pix *pix) Tesseract::TessBaseAPI::SetImage (const unsigned char *imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line) ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |