tesseract  v4.0.0-17-g361f3264
Open Source OCR Engine
Advanced API

Functions

void tesseract::TessBaseAPI::SetImage (const unsigned char *imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line)
 
void tesseract::TessBaseAPI::SetImage (Pix *pix)
 
void tesseract::TessBaseAPI::SetSourceResolution (int ppi)
 
void tesseract::TessBaseAPI::SetRectangle (int left, int top, int width, int height)
 
void tesseract::TessBaseAPI::SetThresholder (ImageThresholder *thresholder)
 
Pix * tesseract::TessBaseAPI::GetThresholdedImage ()
 
Boxa * tesseract::TessBaseAPI::GetRegions (Pixa **pixa)
 
Boxa * tesseract::TessBaseAPI::GetTextlines (const bool raw_image, const int raw_padding, Pixa **pixa, int **blockids, int **paraids)
 
Boxa * tesseract::TessBaseAPI::GetTextlines (Pixa **pixa, int **blockids)
 
Boxa * tesseract::TessBaseAPI::GetStrips (Pixa **pixa, int **blockids)
 
Boxa * tesseract::TessBaseAPI::GetWords (Pixa **pixa)
 
Boxa * tesseract::TessBaseAPI::GetConnectedComponents (Pixa **cc)
 
Boxa * tesseract::TessBaseAPI::GetComponentImages (const PageIteratorLevel level, const bool text_only, const bool raw_image, const int raw_padding, Pixa **pixa, int **blockids, int **paraids)
 
Boxa * tesseract::TessBaseAPI::GetComponentImages (const PageIteratorLevel level, const bool text_only, Pixa **pixa, int **blockids)
 
int tesseract::TessBaseAPI::GetThresholdedImageScaleFactor () const
 
PageIteratortesseract::TessBaseAPI::AnalyseLayout ()
 
PageIteratortesseract::TessBaseAPI::AnalyseLayout (bool merge_similar_words)
 
int tesseract::TessBaseAPI::Recognize (ETEXT_DESC *monitor)
 
int tesseract::TessBaseAPI::RecognizeForChopTest (ETEXT_DESC *monitor)
 
bool tesseract::TessBaseAPI::ProcessPages (const char *filename, const char *retry_config, int timeout_millisec, TessResultRenderer *renderer)
 
bool tesseract::TessBaseAPI::ProcessPagesInternal (const char *filename, const char *retry_config, int timeout_millisec, TessResultRenderer *renderer)
 
bool tesseract::TessBaseAPI::ProcessPage (Pix *pix, int page_index, const char *filename, const char *retry_config, int timeout_millisec, TessResultRenderer *renderer)
 
ResultIteratortesseract::TessBaseAPI::GetIterator ()
 
MutableIteratortesseract::TessBaseAPI::GetMutableIterator ()
 
char * tesseract::TessBaseAPI::GetUTF8Text ()
 
char * tesseract::TessBaseAPI::GetHOCRText (ETEXT_DESC *monitor, int page_number)
 
char * tesseract::TessBaseAPI::GetHOCRText (int page_number)
 
char * tesseract::TessBaseAPI::GetTSVText (int page_number)
 
char * tesseract::TessBaseAPI::GetBoxText (int page_number)
 
char * tesseract::TessBaseAPI::GetUNLVText ()
 
bool tesseract::TessBaseAPI::DetectOrientationScript (int *orient_deg, float *orient_conf, const char **script_name, float *script_conf)
 
char * tesseract::TessBaseAPI::GetOsdText (int page_number)
 
int tesseract::TessBaseAPI::MeanTextConf ()
 
int * tesseract::TessBaseAPI::AllWordConfidences ()
 
bool tesseract::TessBaseAPI::AdaptToWordStr (PageSegMode mode, const char *wordstr)
 
void tesseract::TessBaseAPI::Clear ()
 
void tesseract::TessBaseAPI::End ()
 
static void tesseract::TessBaseAPI::ClearPersistentCache ()
 
int tesseract::TessBaseAPI::IsValidWord (const char *word)
 
bool tesseract::TessBaseAPI::IsValidCharacter (const char *utf8_character)
 
bool tesseract::TessBaseAPI::GetTextDirection (int *out_offset, float *out_slope)
 
void tesseract::TessBaseAPI::SetDictFunc (DictFunc f)
 
void tesseract::TessBaseAPI::SetProbabilityInContextFunc (ProbabilityInContextFunc f)
 
bool tesseract::TessBaseAPI::DetectOS (OSResults *)
 
void tesseract::TessBaseAPI::GetBlockTextOrientations (int **block_orientation, bool **vertical_writing)
 
void tesseract::TessBaseAPI::SetFillLatticeFunc (FillLatticeFunc f)
 
BLOCK_LIST * tesseract::TessBaseAPI::FindLinesCreateBlockList ()
 
static void tesseract::TessBaseAPI::DeleteBlockList (BLOCK_LIST *block_list)
 
static ROWtesseract::TessBaseAPI::MakeTessOCRRow (float baseline, float xheight, float descender, float ascender)
 
static TBLOBtesseract::TessBaseAPI::MakeTBLOB (Pix *pix)
 
static void tesseract::TessBaseAPI::NormalizeTBLOB (TBLOB *tblob, ROW *row, bool numeric_mode)
 
void tesseract::TessBaseAPI::GetFeaturesForBlob (TBLOB *blob, INT_FEATURE_STRUCT *int_features, int *num_features, int *feature_outline_index)
 
static ROWtesseract::TessBaseAPI::FindRowForBox (BLOCK_LIST *blocks, int left, int top, int right, int bottom)
 
void tesseract::TessBaseAPI::RunAdaptiveClassifier (TBLOB *blob, int num_max_matches, int *unichar_ids, float *ratings, int *num_matches_returned)
 
const char * tesseract::TessBaseAPI::GetUnichar (int unichar_id)
 
const Dawgtesseract::TessBaseAPI::GetDawg (int i) const
 
int tesseract::TessBaseAPI::NumDawgs () const
 
Tesseracttesseract::TessBaseAPI::tesseract () const
 
OcrEngineMode tesseract::TessBaseAPI::oem () const
 
void tesseract::TessBaseAPI::InitTruthCallback (TruthCallback *cb)
 
void tesseract::TessBaseAPI::set_min_orientation_margin (double margin)
 

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

◆ AdaptToWordStr()

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

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.

◆ AllWordConfidences()

int * tesseract::TessBaseAPI::AllWordConfidences ( )

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.

Returns an array of all word confidences, terminated by -1.

◆ AnalyseLayout() [1/2]

PageIterator * tesseract::TessBaseAPI::AnalyseLayout ( )

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. If merge_similar_words is true, words are combined where suitable for use with a line recognizer. Use if you want to use AnalyseLayout to find the textlines, and then want to process textline fragments with an external line recognizer. Returns nullptr on error or an empty page. 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.

◆ AnalyseLayout() [2/2]

PageIterator * tesseract::TessBaseAPI::AnalyseLayout ( bool  merge_similar_words)

◆ Clear()

void tesseract::TessBaseAPI::Clear ( )

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.

◆ ClearPersistentCache()

void tesseract::TessBaseAPI::ClearPersistentCache ( )
static

Clear any library-level memory caches. There are a variety of expensive-to-load constant data structures (mostly language dictionaries) that are cached globally – surviving the Init() and End() of individual TessBaseAPI's. This function allows the clearing of these caches.

◆ DeleteBlockList()

void tesseract::TessBaseAPI::DeleteBlockList ( BLOCK_LIST *  block_list)
static

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

◆ DetectOrientationScript()

bool tesseract::TessBaseAPI::DetectOrientationScript ( int *  orient_deg,
float *  orient_conf,
const char **  script_name,
float *  script_conf 
)

Detect the orientation of the input image and apparent script (alphabet). orient_deg is the detected clockwise rotation of the input image in degrees (0, 90, 180, 270) orient_conf is the confidence (15.0 is reasonably confident) script_name is an ASCII string, the name of the script, e.g. "Latin" script_conf is confidence level in the script Returns true on success and writes values to each parameter as an output

◆ DetectOS()

bool tesseract::TessBaseAPI::DetectOS ( OSResults osr)

Estimates the Orientation And Script of the image.

Returns
true if the image was processed successfully.

Estimates the Orientation And Script of the image. Returns true if the image was processed successfully.

◆ End()

void tesseract::TessBaseAPI::End ( )

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.

◆ FindLinesCreateBlockList()

BLOCK_LIST * tesseract::TessBaseAPI::FindLinesCreateBlockList ( )

Find lines from the image making the BLOCK_LIST.

◆ FindRowForBox()

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

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

◆ GetBlockTextOrientations()

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

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

Return text orientation of each block as determined in an earlier page layout analysis operation. Orientation is returned as the number of ccw 90-degree rotations (in [0..3]) required to make the text in the block upright (readable). Note that this may not necessary be the block orientation preferred for recognition (such as the case of vertical CJK text).

Also returns whether the text in the block is believed to have vertical writing direction (when in an upright page orientation).

The returned array is of length equal to the number of text blocks, which may be less than the total number of blocks. The ordering is intended to be consistent with GetTextLines().

◆ GetBoxText()

char * tesseract::TessBaseAPI::GetBoxText ( int  page_number)

The recognized text is returned as a char* which is coded in the same format as a box file used in training. 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. Returned string must be freed with the delete [] operator.

The recognized text is returned as a char* which is coded as a UTF8 box file. page_number is a 0-base page index that will appear in the box file. Returned string must be freed with the delete [] operator.

◆ GetComponentImages() [1/2]

Boxa * tesseract::TessBaseAPI::GetComponentImages ( const PageIteratorLevel  level,
const bool  text_only,
const bool  raw_image,
const int  raw_padding,
Pixa **  pixa,
int **  blockids,
int **  paraids 
)

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 nullptr, the block-id of each component is also returned as an array of one element per component. delete [] after use. If blockids is not nullptr, the paragraph-id of each component with its block is also returned as an array of one element per component. delete [] after use. If raw_image is true, then portions of the original image are extracted instead of the thresholded image and padded with raw_padding. If text_only is true, then only text components are returned.

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 nullptr, 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.

◆ GetComponentImages() [2/2]

Boxa* tesseract::TessBaseAPI::GetComponentImages ( const PageIteratorLevel  level,
const bool  text_only,
Pixa **  pixa,
int **  blockids 
)
inline

◆ GetConnectedComponents()

Boxa * tesseract::TessBaseAPI::GetConnectedComponents ( Pixa **  pixa)

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.

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.

◆ GetDawg()

const Dawg * tesseract::TessBaseAPI::GetDawg ( int  i) const

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

◆ GetFeaturesForBlob()

void tesseract::TessBaseAPI::GetFeaturesForBlob ( TBLOB blob,
INT_FEATURE_STRUCT int_features,
int *  num_features,
int *  feature_outline_index 
)

This method returns the features associated with the input image.

This method returns the features associated with the input blob.

◆ GetHOCRText() [1/2]

char * tesseract::TessBaseAPI::GetHOCRText ( ETEXT_DESC monitor,
int  page_number 
)

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. monitor can be used to cancel the recognition receive progress callbacks Returned string must be freed with the delete [] operator.

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. Image name/input_file_ can be set by SetInputName before calling GetHOCRText STL removed from original patch submission and refactored by rays. Returned string must be freed with the delete [] operator.

◆ GetHOCRText() [2/2]

char * tesseract::TessBaseAPI::GetHOCRText ( int  page_number)

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. Returned string must be freed with the delete [] operator.

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. Image name/input_file_ can be set by SetInputName before calling GetHOCRText STL removed from original patch submission and refactored by rays. Returned string must be freed with the delete [] operator.

◆ GetIterator()

ResultIterator * tesseract::TessBaseAPI::GetIterator ( )

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.

◆ GetMutableIterator()

MutableIterator * tesseract::TessBaseAPI::GetMutableIterator ( )

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.

◆ GetOsdText()

char * tesseract::TessBaseAPI::GetOsdText ( int  page_number)

The recognized text is returned as a char* which is coded as UTF8 and must be freed with the delete [] operator. page_number is a 0-based page index that will appear in the osd file.

◆ GetRegions()

Boxa * tesseract::TessBaseAPI::GetRegions ( Pixa **  pixa)

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

◆ GetStrips()

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

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 nullptr, the block-id of each line is also returned as an array of one element per line. delete [] after use.

◆ GetTextDirection()

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

◆ GetTextlines() [1/2]

Boxa * tesseract::TessBaseAPI::GetTextlines ( const bool  raw_image,
const int  raw_padding,
Pixa **  pixa,
int **  blockids,
int **  paraids 
)

Get the textlines as a leptonica-style Boxa, Pixa pair, in reading order. Can be called before or after Recognize. If raw_image is true, then extract from the original image instead of the thresholded image and pad by raw_padding pixels. If blockids is not nullptr, the block-id of each line is also returned as an array of one element per line. delete [] after use. If paraids is not nullptr, the paragraph-id of each line within its block is also returned as an array of one element per line. delete [] after use.

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

◆ GetTextlines() [2/2]

Boxa* tesseract::TessBaseAPI::GetTextlines ( Pixa **  pixa,
int **  blockids 
)
inline

◆ GetThresholdedImage()

Pix * tesseract::TessBaseAPI::GetThresholdedImage ( )

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.

ONLY available after SetImage if you have Leptonica installed. Get a copy of the internal thresholded image from Tesseract.

◆ GetThresholdedImageScaleFactor()

int tesseract::TessBaseAPI::GetThresholdedImageScaleFactor ( ) const

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.

◆ GetTSVText()

char * tesseract::TessBaseAPI::GetTSVText ( int  page_number)

Make a TSV-formatted string from the internal data structures. page_number is 0-based but will appear in the output as 1-based. Returned string must be freed with the delete [] operator.

◆ GetUnichar()

const char * tesseract::TessBaseAPI::GetUnichar ( int  unichar_id)

This method returns the string form of the specified unichar.

◆ GetUNLVText()

char * tesseract::TessBaseAPI::GetUNLVText ( )

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

◆ GetUTF8Text()

char * tesseract::TessBaseAPI::GetUTF8Text ( )

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

Make a text string from the internal data structures.

◆ GetWords()

Boxa * tesseract::TessBaseAPI::GetWords ( Pixa **  pixa)

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

◆ InitTruthCallback()

void tesseract::TessBaseAPI::InitTruthCallback ( TruthCallback cb)
inline

◆ IsValidCharacter()

bool tesseract::TessBaseAPI::IsValidCharacter ( const char *  utf8_character)

◆ IsValidWord()

int tesseract::TessBaseAPI::IsValidWord ( const char *  word)

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.

Check whether a word is valid according to Tesseract's language model returns 0 if the word is invalid, non-zero if valid

◆ MakeTBLOB()

TBLOB * tesseract::TessBaseAPI::MakeTBLOB ( Pix *  pix)
static

Returns a TBLOB corresponding to the entire input image.

Creates a TBLOB* from the whole pix.

◆ MakeTessOCRRow()

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

Returns a ROW object created from the input row specification.

◆ MeanTextConf()

int tesseract::TessBaseAPI::MeanTextConf ( )

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

Returns the average word confidence for Tesseract page result.

◆ NormalizeTBLOB()

void tesseract::TessBaseAPI::NormalizeTBLOB ( TBLOB tblob,
ROW row,
bool  numeric_mode 
)
static

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.

◆ NumDawgs()

int tesseract::TessBaseAPI::NumDawgs ( ) const

Return the number of dawgs loaded into tesseract_ object.

◆ oem()

OcrEngineMode tesseract::TessBaseAPI::oem ( ) const
inline

◆ ProcessPage()

bool tesseract::TessBaseAPI::ProcessPage ( Pix *  pix,
int  page_index,
const char *  filename,
const char *  retry_config,
int  timeout_millisec,
TessResultRenderer renderer 
)

Turn a single image into symbolic text.

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.

See ProcessPages for desciptions of other parameters.

◆ ProcessPages()

bool tesseract::TessBaseAPI::ProcessPages ( const char *  filename,
const char *  retry_config,
int  timeout_millisec,
TessResultRenderer renderer 
)

Turns images into symbolic text.

filename can point to a single image, a multi-page TIFF, or a plain text list of image filenames.

retry_config is useful for debugging. If not nullptr, you can fall back to an alternate configuration if a page fails for some reason.

timeout_millisec terminates processing if any single page takes too long. Set to 0 for unlimited time.

renderer is responible for creating the output. For example, use the TessTextRenderer if you want plaintext output, or the TessPDFRender to produce searchable PDF.

If tessedit_page_number is non-negative, will only process that single page. Works for multi-page tiff file, or filelist.

Returns true if successful, false on error.

◆ ProcessPagesInternal()

bool tesseract::TessBaseAPI::ProcessPagesInternal ( const char *  filename,
const char *  retry_config,
int  timeout_millisec,
TessResultRenderer renderer 
)

◆ Recognize()

int tesseract::TessBaseAPI::Recognize ( ETEXT_DESC monitor)

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.

Recognize the tesseract global image and return the result as Tesseract internal structures.

◆ RecognizeForChopTest()

int tesseract::TessBaseAPI::RecognizeForChopTest ( ETEXT_DESC monitor)

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

Tests the chopper by exhaustively running chop_one_blob.

◆ RunAdaptiveClassifier()

void tesseract::TessBaseAPI::RunAdaptiveClassifier ( TBLOB blob,
int  num_max_matches,
int *  unichar_ids,
float *  ratings,
int *  num_matches_returned 
)

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

Method to run adaptive classifier on a blob.

◆ set_min_orientation_margin()

void tesseract::TessBaseAPI::set_min_orientation_margin ( double  margin)

◆ SetDictFunc()

void tesseract::TessBaseAPI::SetDictFunc ( DictFunc  f)

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

◆ SetFillLatticeFunc()

void tesseract::TessBaseAPI::SetFillLatticeFunc ( FillLatticeFunc  f)

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

◆ SetImage() [1/2]

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

Provide an image for Tesseract to recognize. Format is as TesseractRect above. Copies the image buffer and converts to Pix. 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.

◆ SetImage() [2/2]

void tesseract::TessBaseAPI::SetImage ( Pix *  pix)

Provide an image for Tesseract to recognize. As with SetImage above, Tesseract takes its own copy of the image, so it need not persist until after Recognize. Pix vs raw, which to use? Use Pix where possible. Tesseract uses Pix as its internal representation and it is therefore more efficient to provide a Pix directly.

◆ SetProbabilityInContextFunc()

void tesseract::TessBaseAPI::SetProbabilityInContextFunc ( ProbabilityInContextFunc  f)

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

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

Parameters
fA single function that returns the probability of the current "character" (in general a utf-8 string), given the context of a previous utf-8 string.

◆ SetRectangle()

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

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.

◆ SetSourceResolution()

void tesseract::TessBaseAPI::SetSourceResolution ( int  ppi)

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

◆ SetThresholder()

void tesseract::TessBaseAPI::SetThresholder ( ImageThresholder thresholder)
inline

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.

◆ tesseract()

Tesseract* tesseract::TessBaseAPI::tesseract ( ) const
inline