Advanced API

Functions
bool	tesseract::TessBaseAPI::AdaptToWordStr (PageSegMode mode, const char *wordstr)
int *	tesseract::TessBaseAPI::AllWordConfidences ()
PageIterator *	tesseract::TessBaseAPI::AnalyseLayout ()
void	tesseract::TessBaseAPI::Clear ()
static void	tesseract::TessBaseAPI::DeleteBlockList (BLOCK_LIST *block_list)
bool	tesseract::TessBaseAPI::DetectOS (OSResults *)
void	tesseract::TessBaseAPI::DumpPGM (const char *filename)
void	tesseract::TessBaseAPI::End ()
BLOCK_LIST *	tesseract::TessBaseAPI::FindLinesCreateBlockList ()
static ROW *	tesseract::TessBaseAPI::FindRowForBox (BLOCK_LIST *blocks, int left, int top, int right, int bottom)
void	tesseract::TessBaseAPI::GetBlockTextOrientations (int **block_orientation, bool **vertical_writing)
char *	tesseract::TessBaseAPI::GetBoxText (int page_number)
Boxa *	tesseract::TessBaseAPI::GetComponentImages (PageIteratorLevel level, bool text_only, Pixa **pixa, int **blockids)
Boxa *	tesseract::TessBaseAPI::GetConnectedComponents (Pixa **cc)
CubeRecoContext *	tesseract::TessBaseAPI::GetCubeRecoContext () const
const Dawg *	tesseract::TessBaseAPI::GetDawg (int i) const
void	tesseract::TessBaseAPI::GetFeaturesForBlob (TBLOB *blob, const DENORM &denorm, INT_FEATURE_ARRAY int_features, int *num_features, int *FeatureOutlineIndex)
char *	tesseract::TessBaseAPI::GetHOCRText (int page_number)
ResultIterator *	tesseract::TessBaseAPI::GetIterator ()
MutableIterator *	tesseract::TessBaseAPI::GetMutableIterator ()
Boxa *	tesseract::TessBaseAPI::GetRegions (Pixa **pixa)
Boxa *	tesseract::TessBaseAPI::GetStrips (Pixa **pixa, int **blockids)
bool	tesseract::TessBaseAPI::GetTextDirection (int *out_offset, float *out_slope)
Boxa *	tesseract::TessBaseAPI::GetTextlines (Pixa **pixa, int **blockids)
Pix *	tesseract::TessBaseAPI::GetThresholdedImage ()
int	tesseract::TessBaseAPI::GetThresholdedImageScaleFactor () const
const char *	tesseract::TessBaseAPI::GetUnichar (int unichar_id)
char *	tesseract::TessBaseAPI::GetUNLVText ()
char *	tesseract::TessBaseAPI::GetUTF8Text ()
Boxa *	tesseract::TessBaseAPI::GetWords (Pixa **pixa)
void	tesseract::TessBaseAPI::InitTruthCallback (TruthCallback *cb)
int	tesseract::TessBaseAPI::IsValidWord (const char *word)
static TBLOB *	tesseract::TessBaseAPI::MakeTBLOB (Pix *pix)
static ROW *	tesseract::TessBaseAPI::MakeTessOCRRow (float baseline, float xheight, float descender, float ascender)
int	tesseract::TessBaseAPI::MeanTextConf ()
static void	tesseract::TessBaseAPI::NormalizeTBLOB (TBLOB *tblob, ROW *row, bool numeric_mode, DENORM *denorm)
int	tesseract::TessBaseAPI::NumDawgs () const
OcrEngineMode const	tesseract::TessBaseAPI::oem () const
bool	tesseract::TessBaseAPI::ProcessPage (Pix *pix, int page_index, const char *filename, const char *retry_config, int timeout_millisec, STRING *text_out)
bool	tesseract::TessBaseAPI::ProcessPages (const char *filename, const char *retry_config, int timeout_millisec, STRING *text_out)
int	tesseract::TessBaseAPI::Recognize (ETEXT_DESC *monitor)
int	tesseract::TessBaseAPI::RecognizeForChopTest (ETEXT_DESC *monitor)
void	tesseract::TessBaseAPI::RunAdaptiveClassifier (TBLOB *blob, const DENORM &denorm, int num_max_matches, int *unichar_ids, float *ratings, int *num_matches_returned)
void	tesseract::TessBaseAPI::set_min_orientation_margin (double margin)
void	tesseract::TessBaseAPI::SetDictFunc (DictFunc f)
void	tesseract::TessBaseAPI::SetFillLatticeFunc (FillLatticeFunc f)
void	tesseract::TessBaseAPI::SetImage (const Pix *pix)
void	tesseract::TessBaseAPI::SetImage (const unsigned char *imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line)
void	tesseract::TessBaseAPI::SetProbabilityInContextFunc (ProbabilityInContextFunc f)
void	tesseract::TessBaseAPI::SetRectangle (int left, int top, int width, int height)
void	tesseract::TessBaseAPI::SetSourceResolution (int ppi)
void	tesseract::TessBaseAPI::SetThresholder (ImageThresholder *thresholder)
Tesseract *const	tesseract::TessBaseAPI::tesseract () const

---

Detailed Description

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.

---

Function Documentation

bool tesseract::TessBaseAPI::AdaptToWordStr	(	PageSegMode	mode,
		const char *	wordstr
	)			[inherited]

Applies the given word to the adaptive classifier if possible. The word must be SPACE-DELIMITED UTF-8 - l i k e t h i s , so it can tell the boundaries of the graphemes. Assumes that SetImage/SetRectangle have been used to set the image to the given word. The mode arg should be PSM_SINGLE_WORD or PSM_CIRCLE_WORD, as that will be used to control layout analysis. The currently set PageSegMode is preserved. Returns false if adaption was not possible for some reason.

int* tesseract::TessBaseAPI::AllWordConfidences

(

)

[inherited]

Returns all word confidences (between 0 and 100) in an array, terminated by -1. The calling function must delete [] after use. The number of confidences should correspond to the number of space- delimited words in GetUTF8Text.

PageIterator* tesseract::TessBaseAPI::AnalyseLayout

(

)

[inherited]

Runs page layout analysis in the mode set by SetPageSegMode. May optionally be called prior to Recognize to get access to just the page layout results. Returns an iterator to the results. Returns NULL on error. The returned iterator must be deleted after use. WARNING! This class points to data held within the TessBaseAPI class, and therefore can only be used while the TessBaseAPI class still exists and has not been subjected to a call of Init, SetImage, Recognize, Clear, End DetectOS, or anything else that changes the internal PAGE_RES.

void tesseract::TessBaseAPI::Clear

(

)

[inherited]

Free up recognition results and any stored image data, without actually freeing any recognition data that would be time-consuming to reload. Afterwards, you must call SetImage or TesseractRect before doing any Recognize or Get* operation.

static void tesseract::TessBaseAPI::DeleteBlockList

(

BLOCK_LIST *

block_list

)

[static, inherited]

Delete a block list. This is to keep BLOCK_LIST pointer opaque and let go of including the other headers.

bool tesseract::TessBaseAPI::DetectOS

(

OSResults *

)

[inherited]

Estimates the Orientation And Script of the image.

Returns:

true if the image was processed successfully.

void tesseract::TessBaseAPI::DumpPGM

(

const char *

filename

)

[inherited]

Dump the internal binary image to a PGM file.

Deprecated:

Use GetThresholdedImage and write the image using pixWrite instead if possible.

void tesseract::TessBaseAPI::End

(

)

[inherited]

Close down tesseract and free up all memory. End() is equivalent to destructing and reconstructing your TessBaseAPI. Once End() has been used, none of the other API functions may be used other than Init and anything declared above it in the class definition.

BLOCK_LIST* tesseract::TessBaseAPI::FindLinesCreateBlockList

(

)

[inherited]

Find lines from the image making the BLOCK_LIST.

static ROW* tesseract::TessBaseAPI::FindRowForBox	(	BLOCK_LIST *	blocks,
		int	left,
		int	top,
		int	right,
		int	bottom
	)			[static, inherited]

This method returns the row to which a box of specified dimensions would belong. If no good match is found, it returns NULL.

void tesseract::TessBaseAPI::GetBlockTextOrientations	(	int **	block_orientation,
		bool **	vertical_writing
	)			[inherited]

Return text orientation of each block as determined by an earlier run of layout analysis.

char* tesseract::TessBaseAPI::GetBoxText

(

int

page_number

)

[inherited]

The recognized text is returned as a char* which is coded in the same format as a box file used in training. Returned string must be freed with the delete [] operator. Constructs coordinates in the original image - not just the rectangle. page_number is a 0-based page index that will appear in the box file.

Boxa* tesseract::TessBaseAPI::GetComponentImages	(	PageIteratorLevel	level,
		bool	text_only,
		Pixa **	pixa,
		int **	blockids
	)			[inherited]

Get the given level kind of components (block, textline, word etc.) as a leptonica-style Boxa, Pixa pair, in reading order. Can be called before or after Recognize. If blockids is not NULL, the block-id of each component is also returned as an array of one element per component. delete [] after use. If text_only is true, then only text components are returned.

Boxa* tesseract::TessBaseAPI::GetConnectedComponents

(

Pixa **

cc

)

[inherited]

Gets the individual connected (text) components (created after pages segmentation step, but before recognition) as a leptonica-style Boxa, Pixa pair, in reading order. Can be called before or after Recognize. Note: the caller is responsible for calling boxaDestroy() on the returned Boxa array and pixaDestroy() on cc array.

CubeRecoContext* tesseract::TessBaseAPI::GetCubeRecoContext

(

)

const [inherited]

Return a pointer to underlying CubeRecoContext object if present.

const Dawg* tesseract::TessBaseAPI::GetDawg

(

int

i

)

const [inherited]

Return the pointer to the i-th dawg loaded into tesseract_ object.

void tesseract::TessBaseAPI::GetFeaturesForBlob	(	TBLOB *	blob,
		const DENORM &	denorm,
		INT_FEATURE_ARRAY	int_features,
		int *	num_features,
		int *	FeatureOutlineIndex
	)			[inherited]

This method returns the features associated with the input image.

char* tesseract::TessBaseAPI::GetHOCRText

(

int

page_number

)

[inherited]

Make a HTML-formatted string with hOCR markup from the internal data structures. page_number is 0-based but will appear in the output as 1-based.

ResultIterator* tesseract::TessBaseAPI::GetIterator

(

)

[inherited]

Get a reading-order iterator to the results of LayoutAnalysis and/or Recognize. The returned iterator must be deleted after use. WARNING! This class points to data held within the TessBaseAPI class, and therefore can only be used while the TessBaseAPI class still exists and has not been subjected to a call of Init, SetImage, Recognize, Clear, End DetectOS, or anything else that changes the internal PAGE_RES.

MutableIterator* tesseract::TessBaseAPI::GetMutableIterator

(

)

[inherited]

Get a mutable iterator to the results of LayoutAnalysis and/or Recognize. The returned iterator must be deleted after use. WARNING! This class points to data held within the TessBaseAPI class, and therefore can only be used while the TessBaseAPI class still exists and has not been subjected to a call of Init, SetImage, Recognize, Clear, End DetectOS, or anything else that changes the internal PAGE_RES.

Boxa* tesseract::TessBaseAPI::GetRegions

(

Pixa **

pixa

)

[inherited]

Get the result of page layout analysis as a leptonica-style Boxa, Pixa pair, in reading order. Can be called before or after Recognize.

Boxa* tesseract::TessBaseAPI::GetStrips	(	Pixa **	pixa,
		int **	blockids
	)			[inherited]

Get textlines and strips of image regions as a leptonica-style Boxa, Pixa pair, in reading order. Enables downstream handling of non-rectangular regions. Can be called before or after Recognize. If blockids is not NULL, the block-id of each line is also returned as an array of one element per line. delete [] after use.

bool tesseract::TessBaseAPI::GetTextDirection	(	int *	out_offset,
		float *	out_slope
	)			[inherited]

Boxa* tesseract::TessBaseAPI::GetTextlines	(	Pixa **	pixa,
		int **	blockids
	)			[inherited]

Get the textlines as a leptonica-style Boxa, Pixa pair, in reading order. Can be called before or after Recognize. If blockids is not NULL, the block-id of each line is also returned as an array of one element per line. delete [] after use.

Pix* tesseract::TessBaseAPI::GetThresholdedImage

(

)

[inherited]

Get a copy of the internal thresholded image from Tesseract. Caller takes ownership of the Pix and must pixDestroy it. May be called any time after SetImage, or after TesseractRect.

int tesseract::TessBaseAPI::GetThresholdedImageScaleFactor

(

)

const [inherited]

Returns the scale factor of the thresholded image that would be returned by GetThresholdedImage() and the various GetX() methods that call GetComponentImages(). Returns 0 if no thresholder has been set.

const char* tesseract::TessBaseAPI::GetUnichar

(

int

unichar_id

)

[inherited]

This method returns the string form of the specified unichar.

char* tesseract::TessBaseAPI::GetUNLVText

(

)

[inherited]

The recognized text is returned as a char* which is coded as UNLV format Latin-1 with specific reject and suspect codes and must be freed with the delete [] operator.

char* tesseract::TessBaseAPI::GetUTF8Text

(

)

[inherited]

The recognized text is returned as a char* which is coded as UTF8 and must be freed with the delete [] operator.

Boxa* tesseract::TessBaseAPI::GetWords

(

Pixa **

pixa

)

[inherited]

Get the words as a leptonica-style Boxa, Pixa pair, in reading order. Can be called before or after Recognize.

void tesseract::TessBaseAPI::InitTruthCallback

(

TruthCallback *

cb

)

[inline, inherited]

Definition at line 656 of file baseapi.h.

int tesseract::TessBaseAPI::IsValidWord

(

const char *

word

)

[inherited]

Check whether a word is valid according to Tesseract's language model

Returns:

0 if the word is invalid, non-zero if valid.

Warning:

temporary! This function will be removed from here and placed in a separate API at some future time.

static TBLOB* tesseract::TessBaseAPI::MakeTBLOB

(

Pix *

pix

)

[static, inherited]

Returns a TBLOB corresponding to the entire input image.

static ROW* tesseract::TessBaseAPI::MakeTessOCRRow	(	float	baseline,
		float	xheight,
		float	descender,
		float	ascender
	)			[static, inherited]

Returns a ROW object created from the input row specification.

int tesseract::TessBaseAPI::MeanTextConf

(

)

[inherited]

Returns the (average) confidence value between 0 and 100.

static void tesseract::TessBaseAPI::NormalizeTBLOB	(	TBLOB *	tblob,
		ROW *	row,
		bool	numeric_mode,
		DENORM *	denorm
	)			[static, inherited]

This method baseline normalizes a TBLOB in-place. The input row is used for normalization. The denorm is an optional parameter in which the normalization-antidote is returned.

int tesseract::TessBaseAPI::NumDawgs

(

)

const [inherited]

Return the number of dawgs loaded into tesseract_ object.

OcrEngineMode const tesseract::TessBaseAPI::oem

(

)

const [inline, inherited]

Definition at line 652 of file baseapi.h.

bool tesseract::TessBaseAPI::ProcessPage	(	Pix *	pix,
		int	page_index,
		const char *	filename,
		const char *	retry_config,
		int	timeout_millisec,
		STRING *	text_out
	)			[inherited]

Recognizes a single page for ProcessPages, appending the text to text_out. The pix is the image processed - filename and page_index are metadata used by side-effect processes, such as reading a box file or formatting as hOCR. If non-zero timeout_millisec terminates processing after the timeout. If non-NULL and non-empty, and some page fails for some reason, the page is reprocessed with the retry_config config file. Useful for interactively debugging a bad page. The text is returned in text_out. Returns false on error.

bool tesseract::TessBaseAPI::ProcessPages	(	const char *	filename,
		const char *	retry_config,
		int	timeout_millisec,
		STRING *	text_out
	)			[inherited]

Recognizes all the pages in the named file, as a multi-page tiff or list of filenames, or single image, and gets the appropriate kind of text according to parameters: tessedit_create_boxfile, tessedit_make_boxes_from_boxes, tessedit_write_unlv, tessedit_create_hocr. Calls ProcessPage on each page in the input file, which may be a multi-page tiff, single-page other file format, or a plain text list of images to read. If tessedit_page_number is non-negative, processing begins at that page of a multi-page tiff file, or filelist. The text is returned in text_out. Returns false on error. If non-zero timeout_millisec terminates processing after the timeout on a single page. If non-NULL and non-empty, and some page fails for some reason, the page is reprocessed with the retry_config config file. Useful for interactively debugging a bad page.

int tesseract::TessBaseAPI::Recognize

(

ETEXT_DESC *

monitor

)

[inherited]

Recognize the image from SetAndThresholdImage, generating Tesseract internal structures. Returns 0 on success. Optional. The Get*Text functions below will call Recognize if needed. After Recognize, the output is kept internally until the next SetImage.

int tesseract::TessBaseAPI::RecognizeForChopTest

(

ETEXT_DESC *

monitor

)

[inherited]

Methods to retrieve information after SetAndThresholdImage(), Recognize() or TesseractRect(). (Recognize is called implicitly if needed.) Variant on Recognize used for testing chopper.

void tesseract::TessBaseAPI::RunAdaptiveClassifier	(	TBLOB *	blob,
		const DENORM &	denorm,
		int	num_max_matches,
		int *	unichar_ids,
		float *	ratings,
		int *	num_matches_returned
	)			[inherited]

Method to run adaptive classifier on a blob. It returns at max num_max_matches results.

void tesseract::TessBaseAPI::set_min_orientation_margin

(

double

margin

)

[inherited]

void tesseract::TessBaseAPI::SetDictFunc

(

DictFunc

f

)

[inherited]

Sets Dict::letter_is_okay_ function to point to the given function.

void tesseract::TessBaseAPI::SetFillLatticeFunc

(

FillLatticeFunc

f

)

[inherited]

Sets Wordrec::fill_lattice_ function to point to the given function.

void tesseract::TessBaseAPI::SetImage

(

const Pix *

pix

)

[inherited]

Provide an image for Tesseract to recognize. As with SetImage above, Tesseract doesn't take a copy or ownership or pixDestroy the image, so it must persist until after Recognize. Pix vs raw, which to use? Use Pix where possible. A future version of Tesseract may choose to use Pix as its internal representation and discard IMAGE altogether. Because of that, an implementation that sources and targets Pix may end up with less copies than an implementation that does not.

void tesseract::TessBaseAPI::SetImage	(	const unsigned char *	imagedata,
		int	width,
		int	height,
		int	bytes_per_pixel,
		int	bytes_per_line
	)			[inherited]

Provide an image for Tesseract to recognize. Format is as TesseractRect above. Does not copy the image buffer, or take ownership. The source image may be destroyed after Recognize is called, either explicitly or implicitly via one of the Get*Text functions. SetImage clears all recognition results, and sets the rectangle to the full image, so it may be followed immediately by a GetUTF8Text, and it will automatically perform recognition.

void tesseract::TessBaseAPI::SetProbabilityInContextFunc

(

ProbabilityInContextFunc

f

)

[inherited]

Sets Dict::probability_in_context_ function to point to the given function.

void tesseract::TessBaseAPI::SetRectangle	(	int	left,
		int	top,
		int	width,
		int	height
	)			[inherited]

Restrict recognition to a sub-rectangle of the image. Call after SetImage. Each SetRectangle clears the recogntion results so multiple rectangles can be recognized with the same image.

void tesseract::TessBaseAPI::SetSourceResolution

(

int

ppi

)

[inherited]

Set the resolution of the source image in pixels per inch so font size information can be calculated in results. Call this after SetImage().

void tesseract::TessBaseAPI::SetThresholder

(

ImageThresholder *

thresholder

)

[inline, inherited]

In extreme cases only, usually with a subclass of Thresholder, it is possible to provide a different Thresholder. The Thresholder may be preloaded with an image, settings etc, or they may be set after. Note that Tesseract takes ownership of the Thresholder and will delete it when it it is replaced or the API is destructed.

Definition at line 343 of file baseapi.h.

Tesseract* const tesseract::TessBaseAPI::tesseract

(

)

const [inline, inherited]

Definition at line 648 of file baseapi.h.