tesseract::TessBaseAPI Class Reference

#include <baseapi.h>

Public Member Functions
bool	AdaptToWordStr (PageSegMode mode, const char *wordstr)
int *	AllWordConfidences ()
PageIterator *	AnalyseLayout ()
void	Clear ()
void	ClearAdaptiveClassifier ()
bool	DetectOS (OSResults *)
void	DumpPGM (const char *filename)
void	End ()
BLOCK_LIST *	FindLinesCreateBlockList ()
void	GetBlockTextOrientations (int block_orientation, bool vertical_writing)
bool	GetBoolVariable (const char name, bool value) const
char *	GetBoxText (int page_number)
Boxa *	GetComponentImages (PageIteratorLevel level, bool text_only, Pixa pixa, int blockids)
Boxa *	GetConnectedComponents (Pixa **cc)
CubeRecoContext *	GetCubeRecoContext () const
const Dawg *	GetDawg (int i) const
bool	GetDoubleVariable (const char name, double value) const
void	GetFeaturesForBlob (TBLOB blob, const DENORM &denorm, INT_FEATURE_ARRAY int_features, int num_features, int *FeatureOutlineIndex)
char *	GetHOCRText (int page_number)
const char *	GetInitLanguagesAsString () const
bool	GetIntVariable (const char name, int value) const
ResultIterator *	GetIterator ()
void	GetLoadedLanguagesAsVector (GenericVector< STRING > *langs) const
MutableIterator *	GetMutableIterator ()
PageSegMode	GetPageSegMode () const
Boxa *	GetRegions (Pixa **pixa)
const char *	GetStringVariable (const char *name) const
Boxa *	GetStrips (Pixa pixa, int blockids)
bool	GetTextDirection (int out_offset, float out_slope)
Boxa *	GetTextlines (Pixa pixa, int blockids)
Pix *	GetThresholdedImage ()
int	GetThresholdedImageScaleFactor () const
const char *	GetUnichar (int unichar_id)
char *	GetUNLVText ()
char *	GetUTF8Text ()
bool	GetVariableAsString (const char name, STRING val)
Boxa *	GetWords (Pixa **pixa)
int	Init (const char datapath, const char language)
int	Init (const char datapath, const char language, OcrEngineMode oem)
int	Init (const char datapath, const char language, OcrEngineMode mode, char *configs, int configs_size, const GenericVector< STRING > vars_vec, const GenericVector< STRING > *vars_values, bool set_only_non_debug_params)
void	InitForAnalysePage ()
int	InitLangMod (const char datapath, const char language)
void	InitTruthCallback (TruthCallback *cb)
int	IsValidWord (const char *word)
int	MeanTextConf ()
int	NumDawgs () const
OcrEngineMode const	oem () const
void	PrintVariables (FILE *fp) const
bool	ProcessPage (Pix pix, int page_index, const char filename, const char retry_config, int timeout_millisec, STRING text_out)
bool	ProcessPages (const char filename, const char retry_config, int timeout_millisec, STRING *text_out)
void	ReadConfigFile (const char *filename)
void	ReadDebugConfigFile (const char *filename)
int	Recognize (ETEXT_DESC *monitor)
int	RecognizeForChopTest (ETEXT_DESC *monitor)
void	RunAdaptiveClassifier (TBLOB blob, const DENORM &denorm, int num_max_matches, int unichar_ids, float ratings, int num_matches_returned)
void	set_min_orientation_margin (double margin)
bool	SetDebugVariable (const char name, const char value)
void	SetDictFunc (DictFunc f)
void	SetFillLatticeFunc (FillLatticeFunc f)
void	SetImage (const Pix *pix)
void	SetImage (const unsigned char *imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line)
void	SetInputName (const char *name)
void	SetOutputName (const char *name)
void	SetPageSegMode (PageSegMode mode)
void	SetProbabilityInContextFunc (ProbabilityInContextFunc f)
void	SetRectangle (int left, int top, int width, int height)
void	SetSourceResolution (int ppi)
void	SetThresholder (ImageThresholder *thresholder)
bool	SetVariable (const char name, const char value)
	TessBaseAPI ()
Tesseract *const	tesseract () const
char *	TesseractRect (const unsigned char *imagedata, int bytes_per_pixel, int bytes_per_line, int left, int top, int width, int height)
virtual	~TessBaseAPI ()
Static Public Member Functions
static void	DeleteBlockList (BLOCK_LIST *block_list)
static ROW *	FindRowForBox (BLOCK_LIST *blocks, int left, int top, int right, int bottom)
static TBLOB *	MakeTBLOB (Pix *pix)
static ROW *	MakeTessOCRRow (float baseline, float xheight, float descender, float ascender)
static void	NormalizeTBLOB (TBLOB tblob, ROW row, bool numeric_mode, DENORM *denorm)
static const char *	Version ()
Protected Member Functions
TESS_LOCAL void	AdaptToCharacter (const char *unichar_repr, int length, float baseline, float xheight, float descender, float ascender)
TESS_LOCAL void	ClearResults ()
TESS_LOCAL void	DetectParagraphs (int debug_level)
TESS_LOCAL int	FindLines ()
TESS_LOCAL LTRResultIterator *	GetLTRIterator ()
TESS_LOCAL const PAGE_RES *	GetPageRes () const
TESS_LOCAL bool	InternalSetImage ()
TESS_LOCAL PAGE_RES *	RecognitionPass1 (BLOCK_LIST *block_list)
TESS_LOCAL PAGE_RES *	RecognitionPass2 (BLOCK_LIST block_list, PAGE_RES pass1_result)
TESS_LOCAL int	TextLength (int *blob_count)
virtual TESS_LOCAL void	Threshold (Pix **pix)
Static Protected Member Functions
static TESS_LOCAL int	TesseractExtractResult (char text, int lengths, float costs, int x0, int y0, int x1, int *y1, PAGE_RES page_res)
Protected Attributes
BLOCK_LIST *	block_list_
	The page layout.
STRING *	datapath_
	Current location of tessdata.
EquationDetect *	equ_detect_
	The equation detector.
int	image_height_
int	image_width_
STRING *	input_file_
	Name used by training code.
STRING *	language_
	Last initialized language.
OcrEngineMode	last_oem_requested_
	Last ocr language mode requested.
Tesseract *	osd_tesseract_
	For orientation & script detection.
STRING *	output_file_
	Name used by debug code.
PAGE_RES *	page_res_
	The page-level data.
GenericVector< ParagraphModel * > *	paragraph_models_
bool	recognition_done_
	page_res_ contains recognition data.
int	rect_height_
int	rect_left_
int	rect_top_
int	rect_width_
Tesseract *	tesseract_
	The underlying data object.
ImageThresholder *	thresholder_
	Image thresholding module.
TruthCallback *	truth_cb_

Detailed Description

Base class for all tesseract APIs. Specific classes can add ability to work on different inputs or produce different outputs. This class is mostly an interface layer on top of the Tesseract instance class to hide the data types so that users of this class don't have to include any other Tesseract headers.

Definition at line 102 of file baseapi.h.

Constructor & Destructor Documentation

tesseract::TessBaseAPI::TessBaseAPI ( )

virtual tesseract::TessBaseAPI::~TessBaseAPI ( ) [virtual]

Member Function Documentation

void tesseract::TessBaseAPI::ClearAdaptiveClassifier ( )

Call between pages or documents etc to free up memory and forget adaptive data.

TESS_LOCAL void tesseract::TessBaseAPI::ClearResults ( ) [protected]

Delete the pageres and block list ready for a new page.

TESS_LOCAL int tesseract::TessBaseAPI::FindLines ( ) [protected]

Find lines from the image making the BLOCK_LIST.

Returns:: 0 on success.

bool tesseract::TessBaseAPI::GetBoolVariable	(	const char *	name,
		bool *	value
	)			const

bool tesseract::TessBaseAPI::GetDoubleVariable	(	const char *	name,
		double *	value
	)			const

const char* tesseract::TessBaseAPI::GetInitLanguagesAsString ( ) const

Returns the languages string used in the last valid initialization. If the last initialization specified "deu+hin" then that will be returned. If hin loaded eng automatically as well, then that will not be included in this list. To find the languages actually loaded use GetLoadedLanguagesAsVector. The returned string should NOT be deleted.

bool tesseract::TessBaseAPI::GetIntVariable	(	const char *	name,
		int *	value
	)			const

Returns true if the parameter was found among Tesseract parameters. Fills in value with the value of the parameter.

void tesseract::TessBaseAPI::GetLoadedLanguagesAsVector ( GenericVector< STRING > * langs ) const

Returns the loaded languages in the vector of STRINGs. Includes all languages loaded by the last Init, including those loaded as dependencies of other loaded languages.

TESS_LOCAL LTRResultIterator* tesseract::TessBaseAPI::GetLTRIterator ( ) [protected]

Return an LTR Result Iterator -- used only for training, as we really want to ignore all BiDi smarts at that point. delete once you're done with it.

PageSegMode tesseract::TessBaseAPI::GetPageSegMode ( ) const

Return the current page segmentation mode.

const char* tesseract::TessBaseAPI::GetStringVariable ( const char * name ) const

Returns the pointer to the string that represents the value of the parameter if it was found among Tesseract parameters.

bool tesseract::TessBaseAPI::GetVariableAsString	(	const char *	name,
		STRING *	val
	)

Get value of named variable as a string, if it exists.

int tesseract::TessBaseAPI::Init	(	const char *	datapath,
		const char *	language
	)			`[inline]`

Definition at line 209 of file baseapi.h.

int tesseract::TessBaseAPI::Init	(	const char *	datapath,
		const char *	language,
		OcrEngineMode	oem
	)			`[inline]`

Definition at line 206 of file baseapi.h.

int tesseract::TessBaseAPI::Init	(	const char *	datapath,
		const char *	language,
		OcrEngineMode	mode,
		char **	configs,
		int	configs_size,
		const GenericVector< STRING > *	vars_vec,
		const GenericVector< STRING > *	vars_values,
		bool	set_only_non_debug_params
	)

Instances are now mostly thread-safe and totally independent, but some global parameters remain. Basically it is safe to use multiple TessBaseAPIs in different threads in parallel, UNLESS: you use SetVariable on some of the Params in classify and textord. If you do, then the effect will be to change it for all your instances.

Start tesseract. Returns zero on success and -1 on failure. NOTE that the only members that may be called before Init are those listed above here in the class definition.

The datapath must be the name of the parent directory of tessdata and must end in / . Any name after the last / will be stripped. The language is (usually) an ISO 639-3 string or NULL will default to eng. It is entirely safe (and eventually will be efficient too) to call Init multiple times on the same instance to change language, or just to reset the classifier. The language may be a string of the form [~]<lang>[+[~]<lang>]* indicating that multiple languages are to be loaded. Eg hin+eng will load Hindi and English. Languages may specify internally that they want to be loaded with one or more other languages, so the ~ sign is available to override that. Eg if hin were set to load eng by default, then hin+~eng would force loading only hin. The number of loaded languages is limited only by memory, with the caveat that loading additional languages will impact both speed and accuracy, as there is more work to do to decide on the applicable language, and there is more chance of hallucinating incorrect words. WARNING: On changing languages, all Tesseract parameters are reset back to their default values. (Which may vary between languages.) If you have a rare need to set a Variable that controls initialization for a second call to Init you should explicitly call End() and then use SetVariable before Init. This is only a very rare use case, since there are very few uses that require any parameters to be set before Init.

If set_only_non_debug_params is true, only params that do not contain "debug" in the name will be set.

void tesseract::TessBaseAPI::InitForAnalysePage ( )

Init only for page layout analysis. Use only for calls to SetImage and AnalysePage. Calls that attempt recognition will generate an error.

int tesseract::TessBaseAPI::InitLangMod	(	const char *	datapath,
		const char *	language
	)

Init only the lang model component of Tesseract. The only functions that work after this init are SetVariable and IsValidWord. WARNING: temporary! This function will be removed from here and placed in a separate API at some future time.

TESS_LOCAL bool tesseract::TessBaseAPI::InternalSetImage ( ) [protected]

Common code for setting the image. Returns true if Init has been called.

void tesseract::TessBaseAPI::PrintVariables ( FILE * fp ) const

Print Tesseract parameters to the given file.

void tesseract::TessBaseAPI::ReadConfigFile ( const char * filename )

Read a "config" file containing a set of param, value pairs. Searches the standard places: tessdata/configs, tessdata/tessconfigs and also accepts a relative or absolute path name. Note: only non-init params will be set (init params are set by Init()).

void tesseract::TessBaseAPI::ReadDebugConfigFile ( const char * filename )

Same as above, but only set debug params from the given config file.

bool tesseract::TessBaseAPI::SetDebugVariable	(	const char *	name,
		const char *	value
	)

void tesseract::TessBaseAPI::SetInputName ( const char * name )

Set the name of the input file. Needed only for training and reading a UNLV zone file.

void tesseract::TessBaseAPI::SetOutputName ( const char * name )

Set the name of the bonus output files. Needed only for debugging.

void tesseract::TessBaseAPI::SetPageSegMode ( PageSegMode mode )

Set the current page segmentation mode. Defaults to PSM_SINGLE_BLOCK. The mode is stored as an IntParam so it can also be modified by ReadConfigFile or SetVariable("tessedit_pageseg_mode", mode as string).

bool tesseract::TessBaseAPI::SetVariable	(	const char *	name,
		const char *	value
	)

Set the value of an internal "parameter." Supply the name of the parameter and the value as a string, just as you would in a config file. Returns false if the name lookup failed. Eg SetVariable("tessedit_char_blacklist", "xyz"); to ignore x, y and z. Or SetVariable("classify_bln_numeric_mode", "1"); to set numeric-only mode. SetVariable may be used before Init, but settings will revert to defaults on End(). TODO(rays) Add a command-line option to dump the parameters to stdout and add a pointer to it in the FAQ

Note: Must be called after Init(). Only works for non-init variables (init variables should be passed to Init()).

char* tesseract::TessBaseAPI::TesseractRect	(	const unsigned char *	imagedata,
		int	bytes_per_pixel,
		int	bytes_per_line,
		int	left,
		int	top,
		int	width,
		int	height
	)

Recognize a rectangle from an image and return the result as a string. May be called many times for a single Init. Currently has no error checking. Greyscale of 8 and color of 24 or 32 bits per pixel may be given. Palette color images will not work properly and must be converted to 24 bit. Binary images of 1 bit per pixel may also be given but they must be byte packed with the MSB of the first byte being the first pixel, and a 1 represents WHITE. For binary images set bytes_per_pixel=0. The recognized text is returned as a char* which is coded as UTF8 and must be freed with the delete [] operator.

Note that TesseractRect is the simplified convenience interface. For advanced uses, use SetImage, (optionally) SetRectangle, Recognize, and one or more of the Get*Text functions below.

TESS_LOCAL int tesseract::TessBaseAPI::TextLength ( int * blob_count ) [protected]

Return the length of the output text string, as UTF8, assuming one newline per line and one per block, with a terminator, and assuming a single character reject marker for each rejected character. Also return the number of recognized blobs in blob_count.

virtual TESS_LOCAL void tesseract::TessBaseAPI::Threshold ( Pix ** pix ) [protected, virtual]

Run the thresholder to make the thresholded image. If pix is not NULL, the source is thresholded to pix instead of the internal IMAGE.

static const char* tesseract::TessBaseAPI::Version ( ) [static]

Returns the version identifier as a static string. Do not delete.